You are here

Baker, Jay Alan

Overview:

As a radiologist in the Division of Breast Imaging, I am interested in studying techniques to better detect and assess breast lesions that may represent breast cancer. The major focus of my research activity includes both basic science and clinical approaches to developing computer-aided diagnosis, novel digital imaging techniques such as digital breast tomosynthesis, advanced ultrasound techniques, and MRI to detect and classify breast lesions.

Breast cancer is the most common malignancy occurring in women and the second most frequent cause of non-skin cancer deaths among women. Screening mammography programs have repeatedly shown a reduction in the mortality from breast cancer by 30 to 60%. However, breast imaging suffers from a lack of specificity. The result is that 60 to 80% of breast biopsies performed in this country are for benign lesions and are therefore - in retrospect - unnecessary. Because of the overlap in imaging features of benign and malignant lesions, however, these lesions cannot be differentiated without tissue sampling, and the extraordinary number of breast biopsies performed markedly increases the cost of breast cancer prevention programs and is an impediment to breast screening for some women. Our work has focused on building computer aided classification systems to assist the radiologist in differentiating benign from malignant breast lesions without the use of invasive biopsies. In our systems, imaging features of breast lesions are combined using artificial intelligence techniques with information such as the patient's age, family history, and change from prior imaging studies to determine the likelihood that a particular lesion is malignant. This information can guide the radiologist to offer follow-up imaging rather than biopsy for those women with lesions that are very unlikely to be breast cancer.

A new focus of research in our lab is the development of full field digital mammography (FFDM) systems that acquire mammographic information using a digital detector rather than film. The advantage of this technique is the possibility of developing advanced applications such as tomosynthesis, contrast enhanced mammography, and dual energy imaging, as well as clinical advantages such as the ability to manipulate the appearance of the image after acquisition and improve film storage and transport. We are collaborating with a major imaging equipment manufacturer to develop both their commercial FFDM system and to develop tomosynthesis using that system. Tomosynthesis is a technique in which several low dose X-ray images of the breast are obtained at various angles, and thin tomographic slices of the breast are reconstructed. This technique removes the problem of overlapping breast tissue, making detection of breast lesions easier, and, in theory, improving the sensitivity of mammography.
Other efforts in our lab have focused on evaluation of elastography in breast ultrasound. Elastography uses ultrasound systems to determine the stiffness of a breast lesion, often by applying a small burst of sound energy toward a breast mass and measuring changes in the shape of the mass. Since most breast cancers are firm, they will deform less than normal breast tissue or benign masses. Our preliminary work to-date suggests that elastography systems are not sufficiently accurately to safely avoid biopsy of a suspicious breast lesion. However, elastography systems may be aid in the accurate diagnosis of breast cysts and assist in avoiding unnecessary cyst aspirations.

Finally, we are also studying the use of spectroscopy in breast MRI. MR spectroscopy provides information on the chemical makeup of a small volume of breast tissue. Breast cancers often contain a substance called choline while normal tissue and benign lesions do not. We are studying ways to assess the level of choline in breast cancers before and shortly after administration of chemotheraphy to determine whether a patient’s cancer will respond to a particular chemotherapy. Although these studies are only in preliminary stages, if successful they may help clinicians determine whether a particular chemotherapy regimen is likely to be successful.

Positions:

Professor of Radiology

Radiology, Breast Imaging
School of Medicine

Member of the Duke Cancer Institute

Duke Cancer Institute
School of Medicine

Chief, Breast Imaging

Radiology, Breast Imaging
School of Medicine

Education:

B.A. 1988

B.A. — University of Pennsylvania

M.D. 1992

M.D. — Duke University

Grants:

Genomic Diversity and the Microenvironment as Drivers of Progression in DCIS

Administered By
Surgery, Advanced Oncologic and Gastrointestinal Surgery
AwardedBy
Department of Defense
Role
Co Investigator
Start Date
September 30, 2014
End Date
September 29, 2020

City of Hope / Contract to continue work on 1U01CA189283-01A1

Administered By
Biostatistics & Bioinformatics
AwardedBy
City of Hope
Role
Investigator
Start Date
October 01, 2015
End Date
July 31, 2020

Machine learning and collaborative filtering tools for personalized education in digital breast tomosynthesis

Administered By
Radiology
AwardedBy
National Institutes of Health
Role
Co Investigator
Start Date
September 01, 2016
End Date
May 31, 2020

(PQC3) Genomic Diversity and Microenvironment as Drivers of Metastasis in DCIS

Administered By
Surgery, Advanced Oncologic and Gastrointestinal Surgery
AwardedBy
National Institutes of Health
Role
Co Investigator
Start Date
August 01, 2014
End Date
July 31, 2018

Preoperative Breast Radiotherapy: A Tool to Provide Individualized and Biologically-Based Radiation Therapy

Administered By
Radiation Oncology
AwardedBy
Gateway for Cancer Research
Role
Collaborator
Start Date
July 01, 2015
End Date
June 30, 2016

Improved education in digital breast tomosynthesis using machine learning and computer vision tools

Administered By
Radiology
AwardedBy
Radiological Society of North America
Role
Investigator
Start Date
July 01, 2014
End Date
March 31, 2016

Combined breast MRI/biomarker strategies to identify aggressive biology

Administered By
Medicine, Medical Oncology
AwardedBy
National Institutes of Health
Role
Investigator
Start Date
August 01, 2015
End Date
September 30, 2015

Tension-Stat3-miR-mediated metastasis

Administered By
Medicine, Medical Oncology
AwardedBy
University of California - San Francisco
Role
Investigator
Start Date
April 01, 2015
End Date
September 30, 2015

(PQA5) 'Dose and Mechanisms of Exercise in Breast Cancer Prevention'

Administered By
Radiation Oncology
AwardedBy
National Institutes of Health
Role
Co Investigator
Start Date
September 23, 2013
End Date
February 14, 2014

3D Digital Breast Phantoms For Multimodality Research

Administered By
Radiology
AwardedBy
National Institutes of Health
Role
Investigator
Start Date
January 01, 2010
End Date
January 31, 2014

Information-Theoretic Based CAD in Mammography

Administered By
Radiology
AwardedBy
National Institutes of Health
Role
Clinical Investigator
Start Date
July 01, 2003
End Date
June 30, 2011

Tomosynthesis for Improved Breast Cancer Detection

Administered By
Radiology
AwardedBy
National Institutes of Health
Role
Clinical Investigator
Start Date
June 20, 2006
End Date
April 30, 2011

Reducing Benign Breast Biopsies with Computer Modeling

Administered By
Radiology, Breast Imaging
AwardedBy
National Institutes of Health
Role
Principal Investigator
Start Date
June 01, 2003
End Date
May 31, 2008

FDG-PEM Detection - Characterization of Breast Cancer

Administered By
Radiology, Breast Imaging
AwardedBy
National Institutes of Health
Role
Investigator
Start Date
September 01, 2004
End Date
August 31, 2007

Breast Elemental Composition Imaging

Administered By
Radiology
AwardedBy
National Institutes of Health
Role
Investigator
Start Date
April 02, 2004
End Date
March 31, 2007

Resolution Requirements for Mammographic Displays

Administered By
Radiology
AwardedBy
National Institutes of Health
Role
Clinical Investigator
Start Date
July 01, 2003
End Date
June 30, 2006

Predicting Breast Cancer With Ultrasound and Mammography

Administered By
Radiology
AwardedBy
National Institutes of Health
Role
Clinical Associate
Start Date
March 01, 2002
End Date
February 28, 2005

Improved Diagnosis of Breast Microcalcification Clusters

Administered By
Radiology
AwardedBy
National Institutes of Health
Role
Co Investigator
Start Date
July 01, 2001
End Date
June 30, 2004
Show More

Publications:

Patient Anxiety Before and Immediately After Imaging-Guided Breast Biopsy Procedures: Impact of Radiologist-Patient Communication.

The aim of this study was to evaluate patient anxiety and its association with perceived radiologist-patient communication in the setting of imaging-guided breast biopsy.After informed consent was obtained, 138 women recommended for imaging-guided breast procedures completed questionnaires immediately before and after biopsies, measuring state anxiety using the State-Trait Anxiety Inventory (range, 20-80). Before biopsies, women also completed questionnaires regarding their perceived communication with the radiologists recommending the procedures (modified Questionnaire on the Quality of Physician-Patient Interaction), demographic characteristics, and medical history; immediately after the biopsies, they completed a measure of perceived communication with the radiologists performing the biopsies. Experience levels (eg, attending radiologist, fellow) of the radiologists recommending and performing the biopsies were recorded. Data were analyzed using paired and independent t tests, one-way analysis of variance, Pearson's correlations, and multiple linear regression analyses.Average prebiopsy anxiety was 44.5 ± 12.4 (range, 20-77) on a scale ranging from 20 to 80 points. Perceived communication with radiologists recommending biopsies averaged 52.4 ± 11.5 (range, 18-65). Better communication with radiologists recommending biopsies was significantly associated with lower levels of prebiopsy anxiety (r = -0.22, P = .01). After the biopsies, women's anxiety significantly decreased (paired t = -7.32, P < .001). Better communication with radiologists performing biopsies (mean, 57.8 ± 8.4; range, 32-65) was associated with lower postbiopsy anxiety after accounting for patients' baseline anxiety levels (β = -0.17, P = .04). White women reported higher prebiopsy and postbiopsy anxiety; nonwhite women reported poorer communication with recommending radiologists.Patients' perceptions of better communication with radiologists were associated with lower levels of anxiety before and after biopsies. These results have implications for radiologist training and adherence to mammographic screening.

Authors
Miller, LS; Shelby, RA; Balmadrid, MH; Yoon, S; Baker, JA; Wildermann, L; Soo, MS
MLA Citation
Miller, LS, Shelby, RA, Balmadrid, MH, Yoon, S, Baker, JA, Wildermann, L, and Soo, MS. "Patient Anxiety Before and Immediately After Imaging-Guided Breast Biopsy Procedures: Impact of Radiologist-Patient Communication." Journal of the American College of Radiology : JACR 13.11S (November 2016): e62-e71.
PMID
27814826
Source
epmc
Published In
Journal of the American College of Radiology
Volume
13
Issue
11S
Publish Date
2016
Start Page
e62
End Page
e71
DOI
10.1016/j.jacr.2016.09.034

Suspicious breast calcifications undergoing stereotactic biopsy in women ages 70 and over: Breast cancer incidence by BI-RADS descriptors.

To determine the malignancy rate overall and for specific BI-RADS descriptors in women ≥70 years who undergo stereotactic biopsy for calcifications.We retrospectively reviewed 14,577 consecutive mammogram reports in 6839 women ≥70 years to collect 231 stereotactic biopsies of calcifications in 215 women. Cases with missing images or histopathology and calcifications associated with masses, distortion, or asymmetries were excluded. Three breast radiologists determined BI-RADS descriptors by majority. Histology, hormone receptor status, and lymph node status were correlated with BI-RADS descriptors.There were 131 (57 %) benign, 22 (10 %) atypia/lobular carcinomas in situ, 55 (24 %) ductal carcinomas in situ (DCIS), and 23 (10 %) invasive diagnoses. Twenty-seven (51 %) DCIS cases were high-grade. Five (22 %) invasive cases were high-grade, two (9 %) were triple-negative, and three (12 %) were node-positive. Malignancy was found in 49 % (50/103) of fine pleomorphic, 50 % (14/28) of fine linear, 25 % (10/40) of amorphous, 20 % (3/15) of round, 3 % (1/36) of coarse heterogeneous, and 0 % (0/9) of dystrophic calcifications.Among women ≥70 years that underwent stereotactic biopsy for calcifications only, we observed a high rate of malignancy. Additionally, coarse heterogeneous calcifications may warrant a probable benign designation.• Cancer rates of biopsied calcifications in women ≥70 years are high • Radiologists should not dismiss suspicious calcifications in older women • Coarse heterogeneous calcifications may warrant a probable benign designation.

Authors
Grimm, LJ; Johnson, DY; Johnson, KS; Baker, JA; Soo, MS; Hwang, ES; Ghate, SV
MLA Citation
Grimm, LJ, Johnson, DY, Johnson, KS, Baker, JA, Soo, MS, Hwang, ES, and Ghate, SV. "Suspicious breast calcifications undergoing stereotactic biopsy in women ages 70 and over: Breast cancer incidence by BI-RADS descriptors." European radiology (October 17, 2016).
PMID
27752832
Source
epmc
Published In
European Radiology
Publish Date
2016

Impact of Breast Density Notification Legislation on Radiologists' Practices of Reporting Breast Density: A Multi-State Study.

Purpose To evaluate the impact of breast density notification legislation on breast density reporting by radiologists nationally. Materials and Methods The institutional review board exempted this HIPAA-compliant retrospective study from the requirement for informed consent. State-level data over a 5-year period on breast density categorization and breast cancer detection rate were collected from the National Mammography Database (NMD). Z tests were used to calculate differences in proportions. Results Facilities in 13 of 17 states that had breast density notification legislation as of 2014 submitted data to the NMD before and after law enactment. A total of 1 333 541 mammographic studies (hereafter called "mammograms") over a 30-month period, beginning 20 months before and continuing 10 months after law enactment, were included in the analysis. There was a small but statistically significant decrease in the percentage of mammograms reported as showing dense breast tissue (hereafter called "dense mammograms") in the month before law enactment compared with the month after (43.0% [22 338 of 52 000] vs 40.0% [18 604 of 46 464], P < .001). There was no statistically significant difference in the percentage of mammograms reported as dense in the month before law enactment compared with the 10th month after (43.0% [22 338 of 52 000] vs 42.8% [15 835 of 36 991], P = .65). There were no significant differences in the breast cancer detection rate between the month before and the month after law enactment (3.9 vs 3.8 cancers per 1000 mammograms, P = .79) or between the month before law enactment and the 10th month after (3.9 vs 4.2 cancers per 1000 mammograms, P = .55). In 21 analyzed states without breast density notification legislation, the percentage of mammograms reported as dense did not decrease below 42.8% (43 363 of 101 394) from 2010 to 2014, in contrast to 13 analyzed states with breast density notification legislation, which reached a nadir of 39.3% (20 965 of 53 360) (P < .001). Conclusion The percentage of mammograms reported as dense slightly decreased immediately after enactment of breast density notification legislation but then returned to prelegislation percentages within 10 months. (©) RSNA, 2016.

Authors
Bahl, M; Baker, JA; Bhargavan-Chatfield, M; Brandt, EK; Ghate, SV
MLA Citation
Bahl, M, Baker, JA, Bhargavan-Chatfield, M, Brandt, EK, and Ghate, SV. "Impact of Breast Density Notification Legislation on Radiologists' Practices of Reporting Breast Density: A Multi-State Study." Radiology 280.3 (September 2016): 701-706.
PMID
27018643
Source
epmc
Published In
Radiology
Volume
280
Issue
3
Publish Date
2016
Start Page
701
End Page
706
DOI
10.1148/radiol.2016152457

How does c-view image quality compare with conventional 2D FFDM?

The FDA approved the use of digital breast tomosynthesis (DBT) in 2011 as an adjunct to 2D full field digital mammography (FFDM) with the constraint that all DBT acquisitions must be paired with a 2D image to assure adequate interpretative information is provided. Recently manufacturers have developed methods to provide a synthesized 2D image generated from the DBT data with the hope of sparing patients the radiation exposure from the FFDM acquisition. While this much needed alternative effectively reduces the total radiation burden, differences in image quality must also be considered. The goal of this study was to compare the intrinsic image quality of synthesized 2D c-view and 2D FFDM images in terms of resolution, contrast, and noise.Two phantoms were utilized in this study: the American College of Radiology mammography accreditation phantom (ACR phantom) and a novel 3D printed anthropomorphic breast phantom. Both phantoms were imaged using a Hologic Selenia Dimensions 3D system. Analysis of the ACR phantom includes both visual inspection and objective automated analysis using in-house software. Analysis of the 3D anthropomorphic phantom includes visual assessment of resolution and Fourier analysis of the noise.Using ACR-defined scoring criteria for the ACR phantom, the FFDM images scored statistically higher than c-view according to both the average observer and automated scores. In addition, between 50% and 70% of c-view images failed to meet the nominal minimum ACR accreditation requirements-primarily due to fiber breaks. Software analysis demonstrated that c-view provided enhanced visualization of medium and large microcalcification objects; however, the benefits diminished for smaller high contrast objects and all low contrast objects. Visual analysis of the anthropomorphic phantom showed a measureable loss of resolution in the c-view image (11 lp/mm FFDM, 5 lp/mm c-view) and loss in detection of small microcalcification objects. Spectral analysis of the anthropomorphic phantom showed higher total noise magnitude in the FFDM image compared with c-view. Whereas the FFDM image contained approximately white noise texture, the c-view image exhibited marked noise reduction at midfrequency and high frequency with far less noise suppression at low frequencies resulting in a mottled noise appearance.Their analysis demonstrates many instances where the c-view image quality differs from FFDM. Compared to FFDM, c-view offers a better depiction of objects of certain size and contrast, but provides poorer overall resolution and noise properties. Based on these findings, the utilization of c-view images in the clinical setting requires careful consideration, especially if considering the discontinuation of FFDM imaging. Not explicitly explored in this study is how the combination of DBT + c-view performs relative to DBT + FFDM or FFDM alone.

Authors
Nelson, JS; Wells, JR; Baker, JA; Samei, E
MLA Citation
Nelson, JS, Wells, JR, Baker, JA, and Samei, E. "How does c-view image quality compare with conventional 2D FFDM?." Medical physics 43.5 (May 2016): 2538-.
PMID
27147364
Source
epmc
Published In
Medical physics
Volume
43
Issue
5
Publish Date
2016
Start Page
2538
DOI
10.1118/1.4947293

Reply to "Conventional Ductography Combined With Digital Breast Tomosynthesis for Imaging of Pathologic Nipple Discharge".

Authors
Bahl, M; Baker, JA; Ghate, SV
MLA Citation
Bahl, M, Baker, JA, and Ghate, SV. "Reply to "Conventional Ductography Combined With Digital Breast Tomosynthesis for Imaging of Pathologic Nipple Discharge"." AJR. American journal of roentgenology 206.2 (February 2016): W45-.
PMID
26797381
Source
epmc
Published In
AJR. American journal of roentgenology
Volume
206
Issue
2
Publish Date
2016
Start Page
W45
DOI
10.2214/ajr.15.15606

In Estimating Overdiagnosis, Details Matter.

Authors
Baker, JA
MLA Citation
Baker, JA. "In Estimating Overdiagnosis, Details Matter." Academic radiology 23.1 (January 2016): 115-116.
PMID
26514438
Source
epmc
Published In
Academic Radiology
Volume
23
Issue
1
Publish Date
2016
Start Page
115
End Page
116
DOI
10.1016/j.acra.2015.08.034

Evaluation of Pathologic Nipple Discharge: What is the Added Diagnostic Value of MRI?

To determine the diagnostic value of magnetic resonance imaging (MRI) for the evaluation of patients with pathologic nipple discharge.We performed a retrospective review of women with nipple discharge who underwent breast MRI between January 1, 2004, and December 31, 2013. Radiographic findings, pathology results, and clinical notes were reviewed. Sensitivity, specificity, positive predictive value, and negative predictive value of MRI were calculated.Over a 10-year period, 103 women (mean age 46 years, range 25-72 years) underwent MRI for evaluation of nipple discharge. Ninety-one patients (88 %) underwent surgical excision or had clinical and/or radiographic follow-up at least 2 years after presentation and thus comprise the study population. Eleven (30 %) of 37 patients with MRIs coded as American College of Radiology Breast Imaging-Reporting and Data System (BI-RADS) 4 of 5 were diagnosed with ductal carcinoma in situ (n = 6) or invasive adenocarcinoma (n = 5). Seven (64 %) of 11 patients diagnosed with malignancy had a negative mammographic and sonographic workup. None of the patients with MRIs coded as BI-RADS 1, 2, or 3 was diagnosed with malignancy immediately after presentation or during the 2-year follow-up period. The sensitivity and specificity of MRI for the detection of malignancy were 100 % (11 of 11) and 68 % (54 of 80), respectively. The positive predictive value and negative predictive value were 37 and 100 %, respectively.MRI is a valuable additional diagnostic tool for the evaluation of pathologic nipple discharge when conventional imaging is negative. A negative MRI in this symptomatic population may obviate the need for duct exploration and excision.

Authors
Bahl, M; Baker, JA; Greenup, RA; Ghate, SV
MLA Citation
Bahl, M, Baker, JA, Greenup, RA, and Ghate, SV. "Evaluation of Pathologic Nipple Discharge: What is the Added Diagnostic Value of MRI?." Annals of surgical oncology 22 Suppl 3 (December 2015): S435-S441.
PMID
26249144
Source
epmc
Published In
Annals of Surgical Oncology
Volume
22 Suppl 3
Publish Date
2015
Start Page
S435
End Page
S441
DOI
10.1245/s10434-015-4792-9

Architectural Distortion on Mammography: Correlation With Pathologic Outcomes and Predictors of Malignancy.

The objective of our study was to determine the risk of malignancy associated with architectural distortion and to evaluate the imaging and clinical features that may contribute to the prediction of malignancy in the setting of architectural distortion.We performed a retrospective review of architectural distortion cases from January 1, 2004, to December 31, 2013. Imaging findings and pathology outcomes were reviewed.Over the 10-year study period, architectural distortion that was considered to be suspicious for or highly suggestive of malignancy was present in 435 of 231,051 (0.2%) mammographic examinations. Cases were excluded if the main finding described was a mass with an associated feature of architectural distortion (n = 62) or if no pathology results were available (n = 4). Two hundred seventy-five cases of invasive adenocarcinoma or ductal carcinoma in situ (DCIS) were identified; the positive predictive value (PPV) was therefore 74.5% (275/369). DCIS alone was identified in only 4.1% (15/369). The most common benign finding on pathology was a radial scar or complex sclerosing lesion (27/369, 7.3%). Architectural distortion was less likely to represent malignancy on screening mammography than on diagnostic mammography (67.0% vs 83.1%, respectively; p < 0.001). Architectural distortion without a sonographic correlate was less likely to represent malignancy than architectural distortion with a correlate (27.9% vs 82.9%, respectively; p < 0.001). There was no statistically significant difference in the malignancy rate between pure architectural distortion and architectural distortion with calcifications or asymmetries (73.0% vs 78.8%; p = 0.26).The PPV of architectural distortion for malignancy is 74.5%. Architectural distortion is less likely to represent malignancy if detected on screening mammography than on diagnostic mammography or if there is no sonographic correlate.

Authors
Bahl, M; Baker, JA; Kinsey, EN; Ghate, SV
MLA Citation
Bahl, M, Baker, JA, Kinsey, EN, and Ghate, SV. "Architectural Distortion on Mammography: Correlation With Pathologic Outcomes and Predictors of Malignancy." AJR. American journal of roentgenology 205.6 (December 2015): 1339-1345.
PMID
26587943
Source
epmc
Published In
AJR. American journal of roentgenology
Volume
205
Issue
6
Publish Date
2015
Start Page
1339
End Page
1345
DOI
10.2214/ajr.15.14628

Preoperative Partial Breast Radiation Therapy: Short-term Imaging Outcomes With Two Unique Treatment Regimens

Authors
Horton, JK; Baker, JA; Blitzblau, R; Georgiade, GS; Hwang, ES; Duffy, EA; Morgan, M; Feigenberg, SJ; Citron, W; Kesmodel, S; Bellavance, E; Drogula, C; Tkaczuk, K; Galandak, J; Nichols, EM
MLA Citation
Horton, JK, Baker, JA, Blitzblau, R, Georgiade, GS, Hwang, ES, Duffy, EA, Morgan, M, Feigenberg, SJ, Citron, W, Kesmodel, S, Bellavance, E, Drogula, C, Tkaczuk, K, Galandak, J, and Nichols, EM. "Preoperative Partial Breast Radiation Therapy: Short-term Imaging Outcomes With Two Unique Treatment Regimens." November 1, 2015.
Source
wos-lite
Published In
International Journal of Radiation Oncology, Biology, Physics
Volume
93
Issue
3
Publish Date
2015
Start Page
E46
End Page
E46

Anxiety prior to breast biopsy: Relationships with length of time from breast biopsy recommendation to biopsy procedure and psychosocial factors.

This study investigated how time from breast biopsy recommendation to biopsy procedure affected pre-biopsy anxiety (N = 140 women), and whether the relationship between wait time and anxiety was affected by psychosocial factors (chronic life stress, traumatic events, social support). Analyses showed a significant interaction between wait time and chronic life stress. Increased time from biopsy recommendation was associated with greater anxiety in women with low levels of life stress. Women with high levels of life stress experienced increased anxiety regardless of wait time. These results suggest that women may benefit from shorter wait times and receiving strategies for managing anxiety.

Authors
Hayes Balmadrid, MA; Shelby, RA; Wren, AA; Miller, LS; Yoon, SC; Baker, JA; Wildermann, LA; Soo, MS
MLA Citation
Hayes Balmadrid, MA, Shelby, RA, Wren, AA, Miller, LS, Yoon, SC, Baker, JA, Wildermann, LA, and Soo, MS. "Anxiety prior to breast biopsy: Relationships with length of time from breast biopsy recommendation to biopsy procedure and psychosocial factors." Journal of health psychology (September 30, 2015).
PMID
26424811
Source
epmc
Published In
Journal of Health Psychology
Publish Date
2015

A phase 1 trial of preoperative partial breast radiation therapy: Patient selection, target delineation, and dose delivery.

Diffusion of accelerated partial breast irradiation into clinical practice is limited by the need for specialized equipment and training. The accessible external beam technique yields unacceptable complication rates, likely from large postoperative target volumes. We designed a phase 1 trial evaluating preoperative radiation therapy to the intact tumor using widely available technology.Patients received 15, 18, or 21 Gy in a single fraction to the breast tumor plus margin. Magnetic resonance imaging (MRI) was used in conjunction with standard computed tomography (CT)-based planning to identify contrast enhancing tumor. Skin markers and an intratumor biopsy marker were used for verification during treatment.MRI imaging was critical for target delineation because not all breast tumors were reliably identified on CT scan. Breast shape differences were consistently seen between CT and MRI but did not impede image registration or tumor identification. Target volumes were markedly smaller than historical postoperative volumes, and normal tissue constraints were easily met. A biopsy marker within the breast proved sufficient for setup localization.This single fraction linear accelerator-based partial breast irradiation approach can be easily incorporated at most treatment centers. In vivo targeting may improve accuracy and can reduce the dose to normal tissues.

Authors
Blitzblau, RC; Arya, R; Yoo, S; Baker, JA; Chang, Z; Palta, M; Duffy, E; Horton, JK
MLA Citation
Blitzblau, RC, Arya, R, Yoo, S, Baker, JA, Chang, Z, Palta, M, Duffy, E, and Horton, JK. "A phase 1 trial of preoperative partial breast radiation therapy: Patient selection, target delineation, and dose delivery." Practical radiation oncology 5.5 (September 2015): e513-e520.
PMID
25834942
Source
epmc
Published In
Practical Radiation Oncology
Volume
5
Issue
5
Publish Date
2015
Start Page
e513
End Page
e520
DOI
10.1016/j.prro.2015.02.002

Frequency of Malignancy and Imaging Characteristics of Probably Benign Lesions Seen at Breast MRI.

OBJECTIVE: The purposes of this study were to evaluate the frequency, follow-up compliance, and cancer rate of MRI BI-RADS category 3 lesions and to determine the cancer rate for individual BI-RADS descriptors. MATERIALS AND METHODS: A retrospective review was conducted of breast MRI examinations with an assessment of probably benign (BI-RADS category 3) from among 4279 consecutive breast MRI examinations performed from January 2005 through December 2009. The review revealed 282 (6.6%) examinations with 332 lesions defined as BI-RADS 3. Pathologic results, 2 years of follow-up imaging findings, or both were reviewed. The frequency of BI-RADS 3 assessments, follow-up imaging compliance, and cancer yield were calculated. Three fellowship-trained breast imagers reevaluated all lesions and recorded descriptors from the MRI lexicon of the fifth edition of the BI-RADS atlas. The distribution and likelihood of malignancy for each descriptor were calculated. RESULTS: The follow-up compliance rate was 84.3% (280/332), and the malignancy rate was 4.3% (12/280). There were 50 (17.9%) individual foci, 61 (21.8%) multiple foci, 74 (26.4%) masses, and 95 (33.9%) nonmass enhancement lesions. Masses were most commonly oval (59.5% [44/74]), circumscribed (75.7% [56/74]), and homogeneously enhancing (43.2% [32/74]). Nonmass enhancement was most commonly focal (57.9% [55/95]) with heterogeneous enhancement (53.7% [51/95]) Most of the lesions had persistent kinetics (74.3% [208/280]). The background parenchymal enhancement was most commonly mild (51.1% [143/280]). CONCLUSION: MRI BI-RADS category 3 is not frequently used, and the levels of patient compliance with follow-up imaging are acceptable. The cancer yield for probably benign lesions is greater for MRI-detected than for mammographically detected lesions, especially for specific BI-RADS descriptors.

Authors
Grimm, LJ; Anderson, AL; Baker, JA; Johnson, KS; Walsh, R; Yoon, SC; Ghate, SV
MLA Citation
Grimm, LJ, Anderson, AL, Baker, JA, Johnson, KS, Walsh, R, Yoon, SC, and Ghate, SV. "Frequency of Malignancy and Imaging Characteristics of Probably Benign Lesions Seen at Breast MRI." AJR. American journal of roentgenology 205.2 (August 2015): 442-447.
PMID
26204298
Source
epmc
Published In
AJR. American journal of roentgenology
Volume
205
Issue
2
Publish Date
2015
Start Page
442
End Page
447
DOI
10.2214/ajr.14.13530

Diagnostic Value of Ultrasound in Female Patients With Nipple Discharge.

The purpose of this study was to assess the contribution of ultrasound to the evaluation of patients with pathologic nipple discharge.A retrospective review was conducted of the records of females who presented with nipple discharge between January 1, 2009, and December 31, 2011. Pathologic nipple discharge was defined as discharge with one or more of the following features: unilateral, clear or bloody, and spontaneous. Patients underwent bilateral mammography followed by ultrasound directed at the subareolar portion of the affected breast. Radiologic findings and pathologic results were reviewed.Over a 3-year period, 327 females (mean age, 48 years; range, 13-88 years) presented with nipple discharge. Among these patients, 273 (83%) underwent surgical excision or clinical or radiographic follow-up at least 2 years after presentation and composed the study population. Among the 273 patients, 262 (96%) underwent mammography and 246 (90%) underwent sonography. Among 252 patients who had at least one pathologic feature of nipple discharge and underwent surgical excision or at least 2 years of follow-up, a total of 20 (8%) cases of ductal carcinoma in situ (DCIS) or invasive adenocarcinoma were diagnosed. DCIS or invasive adenocarcinoma was diagnosed in eight patients with normal sonographic findings. For the detection of DCIS and invasive adenocarcinoma, the sensitivity and specificity of ultrasound were 56% (10/18) and 75% (170/228); the sensitivity and specificity of mammography were 15% (3/20) and 98% (237/242).For females presenting with pathologic nipple discharge, ultrasound is a useful diagnostic tool and may be worth including in the routine evaluation.

Authors
Bahl, M; Baker, JA; Greenup, RA; Ghate, SV
MLA Citation
Bahl, M, Baker, JA, Greenup, RA, and Ghate, SV. "Diagnostic Value of Ultrasound in Female Patients With Nipple Discharge." AJR. American journal of roentgenology 205.1 (July 2015): 203-208.
PMID
26102400
Source
epmc
Published In
AJR. American journal of roentgenology
Volume
205
Issue
1
Publish Date
2015
Start Page
203
End Page
208
DOI
10.2214/ajr.14.13354

Preoperative Single-Fraction Partial Breast Radiation Therapy: A Novel Phase 1, Dose-Escalation Protocol With Radiation Response Biomarkers.

Women with biologically favorable early-stage breast cancer are increasingly treated with accelerated partial breast radiation (PBI). However, treatment-related morbidities have been linked to the large postoperative treatment volumes required for external beam PBI. Relative to external beam delivery, alternative PBI techniques require equipment that is not universally available. To address these issues, we designed a phase 1 trial utilizing widely available technology to 1) evaluate the safety of a single radiation treatment delivered preoperatively to the small-volume, intact breast tumor and 2) identify imaging and genomic markers of radiation response.Women aged ≥55 years with clinically node-negative, estrogen receptor-positive, and/or progesterone receptor-positive HER2-, T1 invasive carcinomas, or low- to intermediate-grade in situ disease ≤2 cm were enrolled (n=32). Intensity modulated radiation therapy was used to deliver 15 Gy (n=8), 18 Gy (n=8), or 21 Gy (n=16) to the tumor with a 1.5-cm margin. Lumpectomy was performed within 10 days. Paired pre- and postradiation magnetic resonance images and patient tumor samples were analyzed.No dose-limiting toxicity was observed. At a median follow-up of 23 months, there have been no recurrences. Physician-rated cosmetic outcomes were good/excellent, and chronic toxicities were grade 1 to 2 (fibrosis, hyperpigmentation) in patients receiving preoperative radiation only. Evidence of dose-dependent changes in vascular permeability, cell density, and expression of genes regulating immunity and cell death were seen in response to radiation.Preoperative single-dose radiation therapy to intact breast tumors is well tolerated. Radiation response is marked by early indicators of cell death in this biologically favorable patient cohort. This study represents a first step toward a novel partial breast radiation approach. Preoperative radiation should be tested in future clinical trials because it has the potential to challenge the current treatment paradigm and provide a path forward to identify radiation response biomarkers.

Authors
Horton, JK; Blitzblau, RC; Yoo, S; Geradts, J; Chang, Z; Baker, JA; Georgiade, GS; Chen, W; Siamakpour-Reihani, S; Wang, C; Broadwater, G; Groth, J; Palta, M; Dewhirst, M; Barry, WT; Duffy, EA; Chi, J-TA; Hwang, ES
MLA Citation
Horton, JK, Blitzblau, RC, Yoo, S, Geradts, J, Chang, Z, Baker, JA, Georgiade, GS, Chen, W, Siamakpour-Reihani, S, Wang, C, Broadwater, G, Groth, J, Palta, M, Dewhirst, M, Barry, WT, Duffy, EA, Chi, J-TA, and Hwang, ES. "Preoperative Single-Fraction Partial Breast Radiation Therapy: A Novel Phase 1, Dose-Escalation Protocol With Radiation Response Biomarkers." International journal of radiation oncology, biology, physics 92.4 (July 2015): 846-855.
PMID
26104938
Source
epmc
Published In
International Journal of Radiation Oncology, Biology, Physics
Volume
92
Issue
4
Publish Date
2015
Start Page
846
End Page
855
DOI
10.1016/j.ijrobp.2015.03.007

Interobserver Variability Between Breast Imagers Using the Fifth Edition of the BI-RADS MRI Lexicon.

OBJECTIVE: The purpose of this study was to assess the interobserver variability of users of the MRI lexicon in the fifth edition of the BI-RADS atlas. MATERIALS AND METHODS: Three breast imaging specialists reviewed 280 routine clinical breast MRI findings reported as BI-RADS category 3. Lesions reported as BI-RADS 3 were chosen because variability in the use of BI-RADS descriptors may influence which lesions are classified as probably benign. Each blinded reader reviewed every study and recorded breast features (background parenchymal enhancement) and lesion features (lesion morphology, mass shape, mass margin, mass internal enhancement, nonmass enhancement distribution, nonmass enhancement internal enhancement, enhancement kinetics) according to the fifth edition of the BI-RADS lexicon and provided a final BI-RADS assessment. Interobserver variability was calculated for each breast and lesion feature and for the final BI-RADS assessment. RESULTS: Interobserver variability for background parenchymal enhancement was fair (ĸ = 0.28). There was moderate agreement on lesion morphology (ĸ = 0.53). For masses, there was substantial agreement on shape (ĸ = 0.72), margin (ĸ = 0.78), and internal enhancement (ĸ = 0.69). For nonmass enhancement, there was substantial agreement on distribution (ĸ = 0.69) and internal enhancement (ĸ = 0.62). There was slight agreement on lesion kinetics (ĸ = 0.19) and final BI-RADS assessment (ĸ = 0.11). CONCLUSION: There is moderate to substantial agreement on most MRI BI-RADS lesion morphology descriptors, particularly mass and nonmass enhancement features, which are important predictors of malignancy. Considerable disagreement remains, however, among experienced readers whether to follow particular findings.

Authors
Grimm, LJ; Anderson, AL; Baker, JA; Johnson, KS; Walsh, R; Yoon, SC; Ghate, SV
MLA Citation
Grimm, LJ, Anderson, AL, Baker, JA, Johnson, KS, Walsh, R, Yoon, SC, and Ghate, SV. "Interobserver Variability Between Breast Imagers Using the Fifth Edition of the BI-RADS MRI Lexicon." AJR. American journal of roentgenology 204.5 (May 2015): 1120-1124.
PMID
25905951
Source
epmc
Published In
AJR. American journal of roentgenology
Volume
204
Issue
5
Publish Date
2015
Start Page
1120
End Page
1124
DOI
10.2214/ajr.14.13047

Can breast cancer molecular subtype help to select patients for preoperative MR imaging?

PURPOSE: To assess whether breast cancer molecular subtype classified by surrogate markers can be used to predict the extent of clinically relevant disease with preoperative breast magnetic resonance (MR) imaging. MATERIALS AND METHODS: In this HIPAA-compliant, institutional review board-approved study, informed consent was waived. Preoperative breast MR imaging reports from 441 patients were reviewed for multicentric and/or multifocal disease, lymph node involvement, skin and/or nipple invasion, chest wall and/or pectoralis muscle invasion, or contralateral disease. Pathologic reports were reviewed to confirm the MR imaging findings and for hormone receptors (estrogen and progesterone subtypes), human epidermal growth factor receptor type 2 (HER2 subtype), tumor size, and tumor grade. Surrogates were used to categorize tumors by molecular subtype: hormone receptor positive and HER2 negative (luminal A subtype); hormone receptor positive and HER2 positive (luminal B subtype); hormone receptor negative and HER2 positive (HER2 subtype); hormone receptor negative and HER2 negative (basal subtype). All patients included in the study had a histologic correlation with MR imaging findings or they were excluded. χ(2) analysis was used to compare differences between subtypes, with multivariate logistic regression analysis used to assess for variable independence. RESULTS: Identified were 289 (65.5%) luminal A, 45 (10.2%) luminal B, 26 (5.9%) HER2, and 81 (18.4%) basal subtypes. Among subtypes, significant differences were found in the frequency of multicentric and/or multifocal disease (luminal A, 27.3% [79 of 289]; luminal B, 53.3% [24 of 45]; HER2, 65.4% [17 of 26]; basal, 27.2% [22 of 81]; P < .001) and lymph node involvement (luminal A, 17.3% [50 of 289]; luminal B, 35.6% [26 of 45]; HER2, 34.6% [nine of 26]; basal 24.7% [20 of 81]; P = .014). Multivariate analysis showed that molecular subtype was independently predictive of multifocal and/or multicentric disease. CONCLUSION: Preoperative breast MR imaging is significantly more likely to help detect multifocal and/or multicentric disease and lymph node involvement in luminal B and HER2 molecular subtype breast cancers. Molecular subtype may help to select patients for preoperative breast MR imaging.

Authors
Grimm, LJ; Johnson, KS; Marcom, PK; Baker, JA; Soo, MS
MLA Citation
Grimm, LJ, Johnson, KS, Marcom, PK, Baker, JA, and Soo, MS. "Can breast cancer molecular subtype help to select patients for preoperative MR imaging?." Radiology 274.2 (February 2015): 352-358.
PMID
25325325
Source
epmc
Published In
Radiology
Volume
274
Issue
2
Publish Date
2015
Start Page
352
End Page
358
DOI
10.1148/radiol.14140594

Abstract P5-14-04: Preoperative single-fraction partial breast radiotherapy – Initial results from a novel phase I dose-escalation protocol with exploration of radiation response biomarkers

Authors
Horton, JK; Blitzblau, RC; Yoo, S; Georgiade, GS; Geradts, J; Baker, JA; Chang, Z; Broadwater, G; Barry, W; Duffy, EA; Hwang, ES
MLA Citation
Horton, JK, Blitzblau, RC, Yoo, S, Georgiade, GS, Geradts, J, Baker, JA, Chang, Z, Broadwater, G, Barry, W, Duffy, EA, and Hwang, ES. "Abstract P5-14-04: Preoperative single-fraction partial breast radiotherapy – Initial results from a novel phase I dose-escalation protocol with exploration of radiation response biomarkers." December 15, 2013.
Source
crossref
Published In
Cancer Research
Volume
73
Issue
24 Supplement
Publish Date
2013
Start Page
P5-14-04
End Page
P5-14-04
DOI
10.1158/0008-5472.SABCS13-P5-14-04

Preoperative Single:Fraction Partial Breast Radiation Therapy: A Novel Phase 1 Dose-Escalation Protocol and Exploration of Breast Cancer Radiation Response

Authors
Horton, JK; Blitzblau, RC; Yoo, S; Georgiade, GS; Geradts, J; Baker, JA; Chang, Z; Duffy, E; Hwang, ES
MLA Citation
Horton, JK, Blitzblau, RC, Yoo, S, Georgiade, GS, Geradts, J, Baker, JA, Chang, Z, Duffy, E, and Hwang, ES. "Preoperative Single:Fraction Partial Breast Radiation Therapy: A Novel Phase 1 Dose-Escalation Protocol and Exploration of Breast Cancer Radiation Response." October 1, 2013.
Source
wos-lite
Published In
International Journal of Radiation Oncology, Biology, Physics
Volume
87
Issue
2
Publish Date
2013
Start Page
S229
End Page
S229

Cancelation of MRI guided breast biopsies for suspicious breast lesions identified at 3.0 T MRI: reasons, rates, and outcomes.

RATIONALE AND OBJECTIVES: To determine the cancelation rate of magnetic resonance imaging (MRI)-guided procedures in suspicious breast lesions initially detected at 3.0 Tesla (T) MRI. MATERIALS AND METHODS: With institutional review board approval, a Health Insurance Portability and Accountability Act-compliant retrospective review of 117 suspicious 3.0 T MRI-detected lesions in 101 patients scheduled to undergo MRI-guided procedures was performed; informed consent was waived. Patient information, imaging features, and outcome data were collected and compared among completed and canceled procedures using Fisher's exact test. RESULTS: MRI-guided breast biopsies were canceled in 13% (15/117) because of lesion nonvisualization, including three (20%) masses, one (1%) focus, and 11 (73%) areas of nonmasslike enhancement. Median lesion size was 1.1 cm. Sixty percent (9/15) of nonvisualized lesions were associated with minimal or mild background parenchymal enhancement at MRI. The nonvisualization rate was not associated with patient age, menopausal status, lesion type, size, breast density, or background parenchymal enhancement (P > .7 for each). No cancers were detected at original lesion sites in 14 (93%) patients undergoing follow-up imaging (n = 11) or mastectomy (n = 3) for cancer elsewhere; one (7%) was lost to follow-up. CONCLUSION: The MRI-guided breast biopsy cancelation rate from nonvisualization of suspicious lesions originally detected with 3.0 T MRI scanning was 13%, similar to rates reported for lesions detected at 1.0 and 1.5 T MRI. No cancers were detected on follow-up imaging. Canceling MRI-guided biopsies because of lesion nonvisualization is a reasonable approach if measures are taken to ensure lesion resolution at the time of biopsy and at imaging follow-up.

Authors
Johnson, KS; Baker, JA; Lee, SS; Soo, MS
MLA Citation
Johnson, KS, Baker, JA, Lee, SS, and Soo, MS. "Cancelation of MRI guided breast biopsies for suspicious breast lesions identified at 3.0 T MRI: reasons, rates, and outcomes." Acad Radiol 20.5 (May 2013): 569-575.
PMID
23473719
Source
pubmed
Published In
Academic Radiology
Volume
20
Issue
5
Publish Date
2013
Start Page
569
End Page
575
DOI
10.1016/j.acra.2013.01.005

Multidisciplinary care of patients with early-stage breast cancer.

There is a compelling need for close coordination and integration of multiple specialties in the management of patients with early-stage breast cancer. Optimal patient care and outcomes depend on the sequential and often simultaneous participation and dialogue between specialists in imaging, pathologic and molecular diagnostic and prognostic stratification, and the therapeutic specialties of surgery, radiation oncology, and medical oncology. These are but a few of the various disciplines needed to provide modern, sophisticated management. The essential role for coordinated involvement of the entire health care team in optimal management of patients with early-stage breast cancer is likely to increase further.

Authors
Lyman, GH; Baker, J; Geradts, J; Horton, J; Kimmick, G; Peppercorn, J; Pruitt, S; Scheri, RP; Hwang, ES
MLA Citation
Lyman, GH, Baker, J, Geradts, J, Horton, J, Kimmick, G, Peppercorn, J, Pruitt, S, Scheri, RP, and Hwang, ES. "Multidisciplinary care of patients with early-stage breast cancer." Surg Oncol Clin N Am 22.2 (April 2013): 299-317. (Review)
PMID
23453336
Source
pubmed
Published In
Surgical Oncology Clinics of North America
Volume
22
Issue
2
Publish Date
2013
Start Page
299
End Page
317
DOI
10.1016/j.soc.2012.12.005

Patient Anxiety Before and Immediately After Imaging-Guided Breast Biopsy Procedures: Impact of Radiologist-Patient Communication

Purpose: The aim of this study was to evaluate patient anxiety and its association with perceived radiologist-patient communication in the setting of imaging-guided breast biopsy. Methods: After informed consent was obtained, 138 women recommended for imaging-guided breast procedures completed questionnaires immediately before and after biopsies, measuring state anxiety using the State-Trait Anxiety Inventory (range, 20-80). Before biopsies, women also completed questionnaires regarding their perceived communication with the radiologists recommending the procedures (modified Questionnaire on the Quality of Physician-Patient Interaction), demographic characteristics, and medical history; immediately after the biopsies, they completed a measure of perceived communication with the radiologists performing the biopsies. Experience levels (eg, attending radiologist, fellow) of the radiologists recommending and performing the biopsies were recorded. Data were analyzed using paired and independent t tests, one-way analysis of variance, Pearson's correlations, and multiple linear regression analyses. Results: Average prebiopsy anxiety was 44.5 ± 12.4 (range, 20-77) on a scale ranging from 20 to 80 points. Perceived communication with radiologists recommending biopsies averaged 52.4 ± 11.5 (range, 18-65). Better communication with radiologists recommending biopsies was significantly associated with lower levels of prebiopsy anxiety (r = -0.22, P = .01). After the biopsies, women's anxiety significantly decreased (paired t = -7.32, P < .001). Better communication with radiologists performing biopsies (mean, 57.8 ± 8.4; range, 32-65) was associated with lower postbiopsy anxiety after accounting for patients' baseline anxiety levels (β = -0.17, P = .04). White women reported higher prebiopsy and postbiopsy anxiety; nonwhite women reported poorer communication with recommending radiologists. Conclusions: Patients' perceptions of better communication with radiologists were associated with lower levels of anxiety before and after biopsies. These results have implications for radiologist training and adherence to mammographic screening. © 2013 American College of Radiology.

Authors
Miller, LS; Shelby, RA; Balmadrid, MH; Yoon, S; Baker, JA; Wildermann, L; Soo, MS
MLA Citation
Miller, LS, Shelby, RA, Balmadrid, MH, Yoon, S, Baker, JA, Wildermann, L, and Soo, MS. "Patient Anxiety Before and Immediately After Imaging-Guided Breast Biopsy Procedures: Impact of Radiologist-Patient Communication." JACR Journal of the American College of Radiology (2013).
PMID
23499400
Source
scival
Published In
Journal of the American College of Radiology
Publish Date
2013
DOI
10.1016/j.jacr.2012.11.005

Cancelation of MRI Guided Breast Biopsies for Suspicious Breast Lesions Identified at 3.0 T MRI. Reasons, Rates, and Outcomes

Rationale and Objectives: To determine the cancelation rate of magnetic resonance imaging (MRI)-guided procedures in suspicious breast lesions initially detected at 3.0 Tesla (T) MRI. Materials and Methods: With institutional review board approval, a Health Insurance Portability and Accountability Act-compliant retrospective review of 117 suspicious 3.0 T MRI-detected lesions in 101 patients scheduled to undergo MRI-guided procedures was performed; informed consent was waived. Patient information, imaging features, and outcome data were collected and compared among completed and canceled procedures using Fisher's exact test. Results: MRI-guided breast biopsies were canceled in 13% (15/117) because of lesion nonvisualization, including three (20%) masses, one (1%) focus, and 11 (73%) areas of nonmasslike enhancement. Median lesion size was 1.1 cm. Sixty percent (9/15) of nonvisualized lesions were associated with minimal or mild background parenchymal enhancement at MRI. The nonvisualization rate was not associated with patient age, menopausal status, lesion type, size, breast density, or background parenchymal enhancement (P > .7 for each). No cancers were detected at original lesion sites in 14 (93%) patients undergoing follow-up imaging (n = 11) or mastectomy (n = 3) for cancer elsewhere; one (7%) was lost to follow-up. Conclusion: The MRI-guided breast biopsy cancelation rate from nonvisualization of suspicious lesions originally detected with 3.0 T MRI scanning was 13%, similar to rates reported for lesions detected at 1.0 and 1.5 T MRI. No cancers were detected on follow-up imaging. Canceling MRI-guided biopsies because of lesion nonvisualization is a reasonable approach if measures are taken to ensure lesion resolution at the time of biopsy and at imaging follow-up. © 2013 AUR.

Authors
Johnson, KS; Baker, JA; Lee, SS; Soo, MS
MLA Citation
Johnson, KS, Baker, JA, Lee, SS, and Soo, MS. "Cancelation of MRI Guided Breast Biopsies for Suspicious Breast Lesions Identified at 3.0 T MRI. Reasons, Rates, and Outcomes." Academic Radiology 20.5 (2013): 569-575.
Source
scival
Published In
Academic Radiology
Volume
20
Issue
5
Publish Date
2013
Start Page
569
End Page
575
DOI
10.1016/j.acra.2013.01.005

Patient anxiety before and immediately after imaging-guided breast biopsy procedures: Impact of radiologist-patient communication

Purpose: The aim of this study was to evaluate patient anxiety and its association with perceived radiologist-patient communication in the setting of imaging-guided breast biopsy. Methods: After informed consent was obtained, 138 women recommended for imaging-guided breast procedures completed questionnaires immediately before and after biopsies, measuring state anxiety using the State-Trait Anxiety Inventory (range, 20-80). Before biopsies, women also completed questionnaires regarding their perceived communication with the radiologists recommending the procedures (modified Questionnaire on the Quality of Physician-Patient Interaction), demographic characteristics, and medical history; immediately after the biopsies, they completed a measure of perceived communication with the radiologists performing the biopsies. Experience levels (eg, attending radiologist, fellow) of the radiologists recommending and performing the biopsies were recorded. Data were analyzed using paired and independent t tests, one-way analysis of variance, Pearson's correlations, and multiple linear regression analyses. Results: Average prebiopsy anxiety was 44.5 ± 12.4 (range, 20-77) on a scale ranging from 20 to 80 points. Perceived communication with radiologists recommending biopsies averaged 52.4 ± 11.5 (range, 18-65). Better communication with radiologists recommending biopsies was significantly associated with lower levels of prebiopsy anxiety (r = -0.22, P =.01). After the biopsies, women's anxiety significantly decreased (paired t = -7.32, P <.001). Better communication with radiologists performing biopsies (mean, 57.8 ± 8.4; range, 32-65) was associated with lower postbiopsy anxiety after accounting for patients' baseline anxiety levels (β = -0.17, P =.04). White women reported higher prebiopsy and postbiopsy anxiety; nonwhite women reported poorer communication with recommending radiologists. Conclusions: Patients' perceptions of better communication with radiologists were associated with lower levels of anxiety before and after biopsies. These results have implications for radiologist training and adherence to mammographic screening. © 2013 American College of Radiology.

Authors
Miller, LS; Shelby, RA; Balmadrid, MH; Yoon, S; Baker, JA; Wildermann, L; Soo, MS
MLA Citation
Miller, LS, Shelby, RA, Balmadrid, MH, Yoon, S, Baker, JA, Wildermann, L, and Soo, MS. "Patient anxiety before and immediately after imaging-guided breast biopsy procedures: Impact of radiologist-patient communication." Journal of the American College of Radiology 10.6 (2013): 423-431.
Source
scival
Published In
Journal of the American College of Radiology
Volume
10
Issue
6
Publish Date
2013
Start Page
423
End Page
431
DOI
10.1016/j.jacr.2012.11.005

Pseudoangiomatous stromal hyperplasia (PASH) causing massive breast enlargement: MRI findings.

Authors
Johnson, KS; Bentley, RC; Kelly Marcom, P; Baker, JA
MLA Citation
Johnson, KS, Bentley, RC, Kelly Marcom, P, and Baker, JA. "Pseudoangiomatous stromal hyperplasia (PASH) causing massive breast enlargement: MRI findings." Breast J 18.6 (November 2012): 600-601.
PMID
23110315
Source
pubmed
Published In
The Breast Journal
Volume
18
Issue
6
Publish Date
2012
Start Page
600
End Page
601
DOI
10.1111/tbj.12026

Identifying error-making patterns in assessment of mammographic BI-RADS descriptors among radiology residents using statistical pattern recognition.

RATIONALE AND OBJECTIVE: The objective of this study is to test the hypothesis that there are patterns in erroneous assessment of BI-RADS features among radiology trainees when interpreting mammographic masses and that these patterns can be captured in individualized statistical user models. Identifying these patterns could be useful in personalizing and adapting educational material to complement the individual weaknesses of each trainee during his or her mammography education. MATERIALS AND METHODS: Reading data of 33 mammographic cases containing masses was used. The cases were individually described by 10 radiology residents using four BI-RADS features: mass shape, mass margin, mass density and parenchyma density. For each resident, an individual model was automatically constructed that predicts likelihood (HIGH or LOW) of erroneously assigning each BI-RADS descriptor by the resident. Error was defined as deviation of the resident's assessment from the expert assessments. We evaluated the predictive performance of the models using leave-one-out crossvalidation. RESULTS: The user models were able to predict which assessments have higher likelihood of error. The proportion of actual errors to the number of situations in which these errors could potentially occur was significantly higher (P < .05) when user-model assigned HIGH likelihood of error than when LOW likelihood of error was assigned for three of the four BI-RADS features. Overall, the difference between the HIGH and LOW likelihood of error groups was statistically significant (P < .0001) combining all four features. CONCLUSION: Error making in BI-RADS descriptor assessment appears to follow patterns that can be captured with statistical pattern recognition-based user models.

Authors
Mazurowski, MA; Barnhart, HX; Baker, JA; Tourassi, GD
MLA Citation
Mazurowski, MA, Barnhart, HX, Baker, JA, and Tourassi, GD. "Identifying error-making patterns in assessment of mammographic BI-RADS descriptors among radiology residents using statistical pattern recognition." Acad Radiol 19.7 (July 2012): 865-871.
PMID
22459643
Source
pubmed
Published In
Academic Radiology
Volume
19
Issue
7
Publish Date
2012
Start Page
865
End Page
871
DOI
10.1016/j.acra.2012.01.012

Suspicious breast lesions detected at 3.0 T magnetic resonance imaging: clinical and histological outcomes.

RATIONALE AND OBJECTIVES: To evaluate the imaging features and histological and clinical outcomes of a series of suspicious, mammographically occult breast lesions detected at 3.0 T magnetic resonance imaging (MRI). MATERIALS AND METHODS: Approval was obtained from the institutional review board. A Health Insurance Portability and Accountability Act-compliant retrospective review was performed of 121 suspicious, mammographically occult lesions detected on 3.0 T contrast-enhanced breast MRI. All 121 lesions underwent histological sampling. Radiology and clinic reports were reviewed for patient demographics, MRI indication and findings, biopsy and localization details, histological results, and follow-up information. Positive predictive value (PPV) of biopsy recommendations were calculated and compared for screening versus diagnostic cases. Likelihood of malignancy was also compared with lesion size. Statistical analyses were performed using chi-square, Fisher's exact, and two-tail z-tests. RESULTS: Overall 43 malignancies were diagnosed from 121 suspicious, mammographically occult 3.0 T MRI-detected lesions. Seventy-eight (64%) of the 121 were benign. The overall PPV of 3.0 T MRI-detected lesions was 36% (43/121). The PPV for biopsy in the screening setting (22% [10/45]) was statistically significantly less (P = .018) compared to the PPV of a biopsy recommendation in the diagnostic setting (43% [33/76]). There was no correlation between lesion size and the likelihood of detecting malignancy. CONCLUSION: Our PPV of suspicious, mammographically occult, breast lesions detected at 3.0 T breast MRI is similar to the PPV reported previously for suspicious breast lesions detected at 1.5 T. This study supports the use of 3.0 T breast MRI for both screening and diagnostic breast imaging.

Authors
Johnson, KS; Baker, JA; Lee, SS; Soo, MS
MLA Citation
Johnson, KS, Baker, JA, Lee, SS, and Soo, MS. "Suspicious breast lesions detected at 3.0 T magnetic resonance imaging: clinical and histological outcomes." Acad Radiol 19.6 (June 2012): 667-674.
PMID
22459645
Source
pubmed
Published In
Academic Radiology
Volume
19
Issue
6
Publish Date
2012
Start Page
667
End Page
674
DOI
10.1016/j.acra.2012.02.016

Using the BI-RADS lexicon in a restrictive form of double reading as a strategy for minimizing screening mammography recall rates.

OBJECTIVE: The purpose of this article is to determine the potential reduction in screening recall rates by strictly following standardized BI-RADS lexicon for lesions seen on screening mammography. MATERIALS AND METHODS: Of 3084 consecutive mammograms performed at our screening facilities, 345 women with 437 lesions were recalled for additional imaging and constituted our study population. Three radiologists retrospectively classified lesions using the standard BI-RADS lexicon and assigned each to one of four groups: group A, the finding met criteria for recall by the BI-RADS lexicon; group B, the finding did not meet strict BI-RADS criteria for recall but was sufficiently indeterminate to warrant recall by the majority of the study panel; group C, the finding was classifiable by the BI-RADS lexicon but was not recalled because it was benign or stable; and group D, the questioned finding was not considered an abnormality by our study panel. Recall rates and the cancer detection rate were determined. The adjusted recall rate was calculated for lesions considered appropriate for recall (group A), and the reduction in the recall rate was determined. RESULTS: Nineteen malignancies were detected in our recalled population, for a cancer detection rate of 0.65%. All 19 malignancies were lesions considered appropriate for recall (group A). If only group A lesions had been recalled, the recall rate would have decreased from 11.4% to 6.2%, representing a 46% reduction in recalls without affecting the cancer detection rate. CONCLUSION: Using the BI-RADS lexicon as a decision-making aid may help adjust thresholds for recalling indeterminate or suspicious lesions and reduce recall rates from screening mammography.

Authors
Ghate, SV; Baker, JA; Kim, CE; Johnson, KS; Walsh, R; Soo, MSC
MLA Citation
Ghate, SV, Baker, JA, Kim, CE, Johnson, KS, Walsh, R, and Soo, MSC. "Using the BI-RADS lexicon in a restrictive form of double reading as a strategy for minimizing screening mammography recall rates." AJR Am J Roentgenol 198.4 (April 2012): 962-970.
PMID
22451567
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
198
Issue
4
Publish Date
2012
Start Page
962
End Page
970
DOI
10.2214/AJR.11.6648

Breast tomosynthesis: state-of-the-art and review of the literature.

Authors
Baker, JA; Lo, JY
MLA Citation
Baker, JA, and Lo, JY. "Breast tomosynthesis: state-of-the-art and review of the literature." Acad Radiol 18.10 (October 2011): 1298-1310. (Review)
PMID
21893296
Source
pubmed
Published In
Academic Radiology
Volume
18
Issue
10
Publish Date
2011
Start Page
1298
End Page
1310
DOI
10.1016/j.acra.2011.06.011

Imaging-guided preoperative hookwire localization of nonpalpable extramammary lesions.

OBJECTIVE: Imaging-guided hookwire localization of nonpalpable lesions in the breast is frequently performed preoperatively. Outside the breast, this procedure is useful for planning resection of lesions in anatomic regions without intrinsic landmarks. The purpose of this study was to review an experience with hookwire localization of nonpalpable extramammary lesions. CONCLUSION: Preoperative imaging-guided hookwire localization is a useful technique that allows precise exploration and resection of nonpalpable lesions and increases confidence that the lesions have been entirely resected.

Authors
Brown, KJ; Bashir, MR; Baker, JA; Tyler, DS; Paulson, EK
MLA Citation
Brown, KJ, Bashir, MR, Baker, JA, Tyler, DS, and Paulson, EK. "Imaging-guided preoperative hookwire localization of nonpalpable extramammary lesions." AJR Am J Roentgenol 197.3 (September 2011): W525-W527.
PMID
21862783
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
197
Issue
3
Publish Date
2011
Start Page
W525
End Page
W527
DOI
10.2214/AJR.10.6176

Titanium vs carbon coated ceramic breast tissue marker clips: 3T MR susceptibility artifact and local signal disturbance.

RATIONALE AND OBJECTIVES: Spectroscopy signal of a breast lesion may be disrupted by the presence of metal from a biopsy marking clip. This study compares the size of magnetic resonance (MR) susceptibility artifacts and degree of local spectroscopy signal disturbance created by conventional titanium tissue marker clips to that of a novel carbon coated ceramic breast tissue marker clip. MATERIALS AND METHODS: Five breast tissue marker clips were embedded in a gelatin breast phantom. The phantoms were imaged on a 3T MR scanner, and three-dimensional T1-weighted gradient echo images were obtained. The area of the susceptibility artifact was calculated and compared for each clip. Single voxel point resolved spectroscopy spectra (SVS) were acquired for three ceramic clips aligned along the superoinferior, anteroposterior, and left-right axes, respectively. Measurements were repeated for an area of pure gelatin and for one similarly sized titanium clip located arbitrarily in the main field. Water spectra were obtained, and line widths and areas of the water peaks were compared. RESULTS: All five clips were easily visible on MR imaging. The ceramic marker clip produced less apparent artifact when compared with the metallic clips. Spectral analysis demonstrated local frequency shifts around all clips. Line widths varied from 7 to 92 Hz in the voxels on and around the titanium clip and from 4 to 18 Hz around the ceramic clips. CONCLUSION: The ceramic breast tissue marker clip produced less susceptibility artifact and less line broadening on 3T MR imaging than conventional titanium clips. This tissue marker may reduce artifact and improve consistency of breast MR spectroscopy.

Authors
Ghate, SV; Baker, JA; Hawkins, AD; Soher, BJ
MLA Citation
Ghate, SV, Baker, JA, Hawkins, AD, and Soher, BJ. "Titanium vs carbon coated ceramic breast tissue marker clips: 3T MR susceptibility artifact and local signal disturbance." Acad Radiol 18.6 (June 2011): 770-773.
PMID
21419666
Source
pubmed
Published In
Academic Radiology
Volume
18
Issue
6
Publish Date
2011
Start Page
770
End Page
773
DOI
10.1016/j.acra.2011.01.008

Comparative performance of multiview stereoscopic and mammographic display modalities for breast lesion detection.

PURPOSE: Mammography is known to be one of the most difficult radiographic exams to interpret. Mammography has important limitations, including the superposition of normal tissue that can obscure a mass, chance alignment of normal tissue to mimic a true lesion and the inability to derive volumetric information. It has been shown that stereomammography can overcome these deficiencies by showing that layers of normal tissue lay at different depths. If standard stereomammography (i.e., a single stereoscopic pair consisting of two projection images) can significantly improve lesion detection, how will multiview stereoscopy (MVS), where many projection images are used, compare to mammography? The aim of this study was to assess the relative performance of MVS compared to mammography for breast mass detection. METHODS: The MVS image sets consisted of the 25 raw projection images acquired over an arc of approximately 45 degrees using a Siemens prototype breast tomosynthesis system. The mammograms were acquired using a commercial Siemens FFDM system. The raw data were taken from both of these systems for 27 cases and realistic simulated mass lesions were added to duplicates of the 27 images at the same local contrast. The images with lesions (27 mammography and 27 MVS) and the images without lesions (27 mammography and 27 MVS) were then postprocessed to provide comparable and representative image appearance across the two modalities. All 108 image sets were shown to five full-time breast imaging radiologists in random order on a state-of-the-art stereoscopic display. The observers were asked to give a confidence rating for each image (0 for lesion definitely not present, 100 for lesion definitely present). The ratings were then compiled and processed using ROC and variance analysis. RESULTS: The mean AUC for the five observers was 0.614 +/- 0.055 for mammography and 0.778 +/- 0.052 for multiview stereoscopy. The difference of 0.164 +/- 0.065 was statistically significant with a p-value of 0.0148. CONCLUSIONS: The differences in the AUCs and the p-value suggest that multiview stereoscopy has a statistically significant advantage over mammography in the detection of simulated breast masses. This highlights the dominance of anatomical noise compared to quantum noise for breast mass detection. It also shows that significant lesion detection can be achieved with MVS without any of the artifacts associated with tomosynthesis.

Authors
Webb, LJ; Samei, E; Lo, JY; Baker, JA; Ghate, SV; Kim, C; Soo, MS; Walsh, R
MLA Citation
Webb, LJ, Samei, E, Lo, JY, Baker, JA, Ghate, SV, Kim, C, Soo, MS, and Walsh, R. "Comparative performance of multiview stereoscopic and mammographic display modalities for breast lesion detection." Med Phys 38.4 (April 2011): 1972-1980.
Website
http://hdl.handle.net/10161/2508
PMID
21626930
Source
pubmed
Published In
Medical physics
Volume
38
Issue
4
Publish Date
2011
Start Page
1972
End Page
1980
DOI
10.1118/1.3562901

Computer-aided classification of breast masses: performance and interobserver variability of expert radiologists versus residents.

PURPOSE: To evaluate the interobserver variability in descriptions of breast masses by dedicated breast imagers and radiology residents and determine how any differences in lesion description affect the performance of a computer-aided diagnosis (CAD) computer classification system. MATERIALS AND METHODS: Institutional review board approval was obtained for this HIPAA-compliant study, and the requirement to obtain informed consent was waived. Images of 50 breast lesions were individually interpreted by seven dedicated breast imagers and 10 radiology residents, yielding 850 lesion interpretations. Lesions were described with use of 11 descriptors from the Breast Imaging Reporting and Data System, and interobserver variability was calculated with the Cohen κ statistic. Those 11 features were selected, along with patient age, and merged together by a linear discriminant analysis (LDA) classification model trained by using 1005 previously existing cases. Variability in the recommendations of the computer model for different observers was also calculated with the Cohen κ statistic. RESULTS: A significant difference was observed for six lesion features, and radiology residents had greater interobserver variability in their selection of five of the six features than did dedicated breast imagers. The LDA model accurately classified lesions for both sets of observers (area under the receiver operating characteristic curve = 0.94 for residents and 0.96 for dedicated imagers). Sensitivity was maintained at 100% for residents and improved from 98% to 100% for dedicated breast imagers. For residents, the computer model could potentially improve the specificity from 20% to 40% (P < .01) and the κ value from 0.09 to 0.53 (P < .001). For dedicated breast imagers, the computer model could increase the specificity from 34% to 43% (P = .16) and the κ value from 0.21 to 0.61 (P < .001). CONCLUSION: Among findings showing a significant difference, there was greater interobserver variability in lesion descriptions among residents; however, an LDA model using data from either dedicated breast imagers or residents yielded a consistently high performance in the differentiation of benign from malignant breast lesions, demonstrating potential for improving specificity and decreasing interobserver variability in biopsy recommendations.

Authors
Singh, S; Maxwell, J; Baker, JA; Nicholas, JL; Lo, JY
MLA Citation
Singh, S, Maxwell, J, Baker, JA, Nicholas, JL, and Lo, JY. "Computer-aided classification of breast masses: performance and interobserver variability of expert radiologists versus residents." Radiology 258.1 (January 2011): 73-80.
PMID
20971779
Source
pubmed
Published In
Radiology
Volume
258
Issue
1
Publish Date
2011
Start Page
73
End Page
80
DOI
10.1148/radiol.10081308

Is surgical excision of core biopsy proven benign papillomas of the breast necessary?

RATIONALE AND OBJECTIVES: The aim of this study was to determine if core biopsy-proven benign papillomas of the breast need to be surgically excised. MATERIALS AND METHODS: Mammographic and pathologic database review from January 1994 to January 2004 revealed 178 papillary lesions diagnosed by core biopsy in 176 women (mean age, 59 years). All lesions had >or=24 months of imaging follow-up (n = 75) or surgical correlation (n = 103). Details regarding core biopsy technique, lesion appearance, pathologic results, imaging-histopathologic concordance, and follow-up imaging were recorded. Core and surgical pathologic results were correlated. RESULTS: Of the 178 papillary lesions diagnosed at core needle biopsy, 120 (67%) were initially diagnosed as benign without atypia. The core biopsy diagnoses of benignity were confirmed for all 120 lesions by either surgical excision (n = 45) or stability after >or=2 years of imaging follow-up (n = 75). Of the remaining 58 papillary lesions, 50 were found to be atypical at core needle biopsy; 15 of those 50 (29%) were upgraded to malignancies at surgical excision. Eight of the 178 lesions (5%) were initially diagnosed as malignant papillary lesions at core needle biopsy. Seven of these eight (88%) were confirmed malignant at excision. None of the surgically proven cancers was diagnosed as benign at core biopsy. CONCLUSIONS: Close imaging follow-up rather than excision of core biopsy-proven benign papillomas was adequate given careful imaging-histopathologic correlation and excision of all atypical and discordant lesions. Individual centers should evaluate their own data and tailor their practices accordingly.

Authors
Bennett, LE; Ghate, SV; Bentley, R; Baker, JA
MLA Citation
Bennett, LE, Ghate, SV, Bentley, R, and Baker, JA. "Is surgical excision of core biopsy proven benign papillomas of the breast necessary?." Acad Radiol 17.5 (May 2010): 553-557.
PMID
20223685
Source
pubmed
Published In
Academic Radiology
Volume
17
Issue
5
Publish Date
2010
Start Page
553
End Page
557
DOI
10.1016/j.acra.2010.01.001

Individualized computer-aided education in mammography based on user modeling: concept and preliminary experiments.

PURPOSE: The authors propose the framework for an individualized adaptive computer-aided educational system in mammography that is based on user modeling. The underlying hypothesis is that user models can be developed to capture the individual error making patterns of radiologists-in-training. In this pilot study, the authors test the above hypothesis for the task of breast cancer diagnosis in mammograms. METHODS: The concept of a user model was formalized as the function that relates image features to the likelihood/extent of the diagnostic error made by a radiologist-in-training and therefore to the level of difficulty that a case will pose to the radiologist-in-training (or "user"). Then, machine learning algorithms were implemented to build such user models. Specifically, the authors explored k-nearest neighbor, artificial neural networks, and multiple regression for the task of building the model using observer data collected from ten Radiology residents at Duke University Medical Center for the problem of breast mass diagnosis in mammograms. For each resident, a user-specific model was constructed that predicts the user's expected level of difficulty for each presented case based on two BI-RADS image features. In the experiments, leave-one-out data handling scheme was applied to assign each case to a low-predicted-difficulty or a high-predicted-difficulty group for each resident based on each of the three user models. To evaluate whether the user model is useful in predicting difficulty, the authors performed statistical tests using the generalized estimating equations approach to determine whether the mean actual error is the same or not between the low-predicted-difficulty group and the high-predicted-difficulty group. RESULTS: When the results for all observers were pulled together, the actual errors made by residents were statistically significantly higher for cases in the high-predicted-difficulty group than for cases in the low-predicted-difficulty group for all modeling algorithms (p < or = 0.002 for all methods). This indicates that the user models were able to accurately predict difficulty level of the analyzed cases. Furthermore, the authors determined that among the two BI-RADS features that were used in this study, mass margin was the most useful in predicting individual user errors. CONCLUSIONS: The pilot study shows promise for developing individual user models that can accurately predict the level of difficulty that each case will pose to the radiologist-in-training. These models could allow for constructing adaptive computer-aided educational systems in mammography.

Authors
Mazurowski, MA; Baker, JA; Barnhart, HX; Tourassi, GD
MLA Citation
Mazurowski, MA, Baker, JA, Barnhart, HX, and Tourassi, GD. "Individualized computer-aided education in mammography based on user modeling: concept and preliminary experiments." Med Phys 37.3 (March 2010): 1152-1160.
PMID
20384251
Source
pubmed
Published In
Medical physics
Volume
37
Issue
3
Publish Date
2010
Start Page
1152
End Page
1160
DOI
10.1118/1.3301575

Sonography in the identification of calciphylaxis of the breast.

Authors
Bukhman, R; Scheri, RP; Selim, MA; Baker, JA
MLA Citation
Bukhman, R, Scheri, RP, Selim, MA, and Baker, JA. "Sonography in the identification of calciphylaxis of the breast." J Ultrasound Med 29.1 (January 2010): 129-133.
PMID
20040786
Source
pubmed
Published In
Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine
Volume
29
Issue
1
Publish Date
2010
Start Page
129
End Page
133

Clinical prototype of autonomous breast biopsy robot guided by 4Dultrasound

Our laboratory previously conducted feasibility studies of autonomousrobotic breast biopsy guided by 4D ultrasound. Using a complete 3D image volume,processed by elementary thresholding algorithms with no human intervention, therobot was able to successfully target bright voxels representingmicro-calcifications and dark regions representing cysts in turkey breasttissue. We now describe a clinical prototype of a computer-controlled single armrobot guided by 4D ultrasound which can autonomously locate a breast lesion andthen fire a spring-loaded biopsy needle into the lesion. RMS error in a watertank experiment locating a bright point target was 2.82 mm. © 2010 IEEE.

Authors
Liang, K; Light, ED; Baker, JA; Lachmann, F; Collins, J; Smith, SW
MLA Citation
Liang, K, Light, ED, Baker, JA, Lachmann, F, Collins, J, and Smith, SW. "Clinical prototype of autonomous breast biopsy robot guided by 4Dultrasound." Proceedings - IEEE Ultrasonics Symposium (2010): 2348-2351.
Source
scival
Published In
Proceedings of the IEEE Ultrasonics Symposium
Publish Date
2010
Start Page
2348
End Page
2351
DOI
10.1109/ULTSYM.2010.5935778

Novel tumor sampling strategies to enable microarray gene expression signatures in breast cancer: a study to determine feasibility and reproducibility in the context of clinical care.

Feasibility and reproducibility of microarray biomarkers in clinical settings are doubted because of reliance on fresh frozen tissue. We sought to develop and validate a paradigm of frozen tissue collection from early breast tumors to enable use of microarray in oncology practice. Frozen core needle biopsies (CNBx) were collected from 150 clinical stage I patients during image-guided diagnostic biopsy and/or surgery. Histology and tumor content from frozen cores were compared to diagnostic specimens. Twenty-eight patients had microarray analysis to examine accuracy and reproducibility of predictive gene signatures developed for estrogen receptor (ER) and HER2. One hundred twenty-seven (85%) of 150 patients had at least one frozen core containing cancer suitable for microarray analysis. Larger tumor size, ex vivo biopsy, and use of a new specimen device increased the likelihood of obtaining adequate specimens. Sufficient quality RNA was obtained from 90% of tumor cores. Microarray signatures predicting ER and HER2 expression were developed in training sets of up to 363 surgical samples and were applied to microarray data obtained from core samples collected in clinical settings. In these samples, prediction of ER and HER2 expression achieved a sensitivity/specificity of 94%/100%, and 82%/72%, respectively. Predictions were reproducible in 83-100% of paired samples. Frozen CNBx can be readily obtained from most breast cancers without interfering with pathologic evaluation in routine clinical settings. Collection of tumor tissue at diagnostic biopsy and/or at surgery from lumpectomy specimens using image guidance resulted in sufficient samples for array analysis from over 90% of patients. Sampling of breast cancer for microarray data is reproducible and feasible in clinical practice and can yield signatures predictive of multiple breast cancer phenotypes.

Authors
Tebbit, CL; Zhai, J; Untch, BR; Ellis, MJ; Dressman, HK; Bentley, RC; Baker, JA; Marcom, PK; Nevins, JR; Marks, JR; Olson, JA
MLA Citation
Tebbit, CL, Zhai, J, Untch, BR, Ellis, MJ, Dressman, HK, Bentley, RC, Baker, JA, Marcom, PK, Nevins, JR, Marks, JR, and Olson, JA. "Novel tumor sampling strategies to enable microarray gene expression signatures in breast cancer: a study to determine feasibility and reproducibility in the context of clinical care." Breast Cancer Res Treat 118.3 (December 2009): 635-643.
PMID
19224362
Source
pubmed
Published In
Breast Cancer Research and Treatment
Volume
118
Issue
3
Publish Date
2009
Start Page
635
End Page
643
DOI
10.1007/s10549-008-0301-1

Optimized image acquisition for breast tomosynthesis in projection and reconstruction space.

Breast tomosynthesis has been an exciting new development in the field of breast imaging. While the diagnostic improvement via tomosynthesis is notable, the full potential of tomosynthesis has not yet been realized. This may be attributed to the dependency of the diagnostic quality of tomosynthesis on multiple variables, each of which needs to be optimized. Those include dose, number of angular projections, and the total angular span of those projections. In this study, the authors investigated the effects of these acquisition parameters on the overall diagnostic image quality of breast tomosynthesis in both the projection and reconstruction space. Five mastectomy specimens were imaged using a prototype tomosynthesis system. 25 angular projections of each specimen were acquired at 6.2 times typical single-view clinical dose level. Images at lower dose levels were then simulated using a noise modification routine. Each projection image was supplemented with 84 simulated 3 mm 3D lesions embedded at the center of 84 nonoverlapping ROIs. The projection images were then reconstructed using a filtered backprojection algorithm at different combinations of acquisition parameters to investigate which of the many possible combinations maximizes the performance. Performance was evaluated in terms of a Laguerre-Gauss channelized Hotelling observer model-based measure of lesion detectability. The analysis was also performed without reconstruction by combining the model results from projection images using Bayesian decision fusion algorithm. The effect of acquisition parameters on projection images and reconstructed slices were then compared to derive an optimization rule for tomosynthesis. The results indicated that projection images yield comparable but higher performance than reconstructed images. Both modes, however, offered similar trends: Performance improved with an increase in the total acquisition dose level and the angular span. Using a constant dose level and angular span, the performance rolled off beyond a certain number of projections, indicating that simply increasing the number of projections in tomosynthesis may not necessarily improve its performance. The best performance for both projection images and tomosynthesis slices was obtained for 15-17 projections spanning an angular are of approximately 45 degrees--the maximum tested in our study, and for an acquisition dose equal to single-view mammography. The optimization framework developed in this framework is applicable to other reconstruction techniques and other multiprojection systems.

Authors
Chawla, AS; Lo, JY; Baker, JA; Samei, E
MLA Citation
Chawla, AS, Lo, JY, Baker, JA, and Samei, E. "Optimized image acquisition for breast tomosynthesis in projection and reconstruction space." Med Phys 36.11 (November 2009): 4859-4869.
PMID
19994493
Source
pubmed
Published In
Medical physics
Volume
36
Issue
11
Publish Date
2009
Start Page
4859
End Page
4869
DOI
10.1118/1.3231814

Breast self-examination: defining a cohort still in need.

BACKGROUND: The value of breast self-examination (BSE) to detect early breast cancer is controversial. METHODS: Within an institutional review board-approved prospective study, 147 high-risk women were enrolled from 2004 to 2007. Yearly clinical examination, BSE teaching, and mammography were performed simultaneously followed by interval breast magnetic resonance imaging (MRI). Women underwent additional BSE teaching at 6 months. Women reporting a mass on BSE underwent clinical evaluation. RESULTS: Fourteen breast cancers were detected in 12 women. BSE detected 6/14 breast cancers versus 6/14 detected by MRI and 2/14 by mammography. Of 24 masses detected by BSE, 6/24 were malignant. The sensitivity, specificity, and predictive value of BSE to detect breast cancer were 58.3%, 87.4%, and 29.2%, respectively. The sensitivity, specificity, and predictive value of a Breast Image Reporting and Data System (BI-RADS) score of >or=4 on MRI were 66.7%, 88.9%, and 34.8%, respectively. CONCLUSIONS: BSE detects new breast cancers in high-risk women undergoing screening mammogram, CBE, and yearly breast MRI.

Authors
Wilke, LG; Broadwater, G; Rabiner, S; Owens, E; Yoon, S; Ghate, S; Scott, V; Walsh, R; Baker, J; Soo, MS; Ibarra-Drendall, C; Stouder, A; Robertson, S; Barron, A; Seewaldt, V
MLA Citation
Wilke, LG, Broadwater, G, Rabiner, S, Owens, E, Yoon, S, Ghate, S, Scott, V, Walsh, R, Baker, J, Soo, MS, Ibarra-Drendall, C, Stouder, A, Robertson, S, Barron, A, and Seewaldt, V. "Breast self-examination: defining a cohort still in need." Am J Surg 198.4 (October 2009): 575-579.
PMID
19800471
Source
pubmed
Published In
American Journal of Surgery
Volume
198
Issue
4
Publish Date
2009
Start Page
575
End Page
579
DOI
10.1016/j.amjsurg.2009.06.012

Can compression be reduced for breast tomosynthesis? Monte carlo study on mass and microcalcification conspicuity in tomosynthesis.

PURPOSE: To assess, in a voxelized anthropomorphic breast phantom, how the conspicuity of breast masses and microcalcifications may be affected by applying reduced breast compression in tomosynthesis. MATERIALS AND METHODS: A breast tomosynthesis system was modeled by using a Monte Carlo program and a voxelized anthropomorphic breast phantom. The Monte Carlo program created simulated tomosynthesis projection images, which were reconstructed by using filtered back-projection software. Reconstructed images were analyzed for mass and microcalcification conspicuity, or the ratio of the lesion contrast to the anatomic and quantum noise surrounding the lesion. This analysis was performed at two compression levels (standard and 12.5% reduction) and for two breast compression thicknesses (4 and 6 cm). The change in conspicuity was analyzed for significance by using a bootstrap method and a paired Student t test. RESULTS: While keeping the glandular radiation dose constant with respective standard and reduced compression levels, the mean mass conspicuities were 1.39 +/- 0.15 (standard error of the mean) and 1.46 +/- 0.22 for a 4-cm breast compression phantom and 1.26 +/- 0.15 and 1.22 +/- 0.20 for a 6-cm breast phantom, and the mean microcalcification conspicuities were 16.2 +/- 2.87 and 18.6 +/- 2.63 for a 4-cm breast phantom and 11.4 +/- 1.11 and 10.6 +/- 1.18 for a 6-cm breast compression phantom. CONCLUSION: For constant glandular dose, mass and microcalcification conspicuity remained approximately constant with decreased compression. Constant conspicuity implies that reduced compression would have a minimal effect on radiologists' performance, which suggests that there is justification for a measured reduction of breast compression for breast tomosynthesis, increasing the comfort of women undergoing the examination.

Authors
Saunders, RS; Samei, E; Lo, JY; Baker, JA
MLA Citation
Saunders, RS, Samei, E, Lo, JY, and Baker, JA. "Can compression be reduced for breast tomosynthesis? Monte carlo study on mass and microcalcification conspicuity in tomosynthesis." Radiology 251.3 (June 2009): 673-682.
PMID
19474373
Source
pubmed
Published In
Radiology
Volume
251
Issue
3
Publish Date
2009
Start Page
673
End Page
682
DOI
10.1148/radiol.2521081278

The influence of increased ambient lighting on mass detection in mammograms.

RATIONALE AND OBJECTIVES: Recent research has provided evidence that in reading rooms equipped with liquid crystal displays (LCDs), a measured increase of ambient lighting may improve clinicians' detection performance. In agreement with this research, the American College of Radiology (ACR) has recommended a moderate increase of ambient lighting in mammography reading rooms. This study was designed to examine the effect of a controlled increase of ambient lighting in mammography reading rooms on the diagnostic performance of breast imaging radiologists. MATERIALS AND METHODS: Four breast imaging radiologists read 86 mammograms (43 containing subtle cancerous masses and 43 normal) under low (E = 1 lux) and elevated (E = 50 lux) ambient lighting levels on a Digital Imaging and Communications in Medicine-calibrated, medical-grade LCD. Radiologists were asked to identify cancerous masses and to rate their detection confidence. Observer areas under the curve (AUCs) were calculated using a receiver-operating characteristic analysis of fully paired results. Additionally, average observer selection times under both ambient lighting levels were determined. RESULTS: Average radiologist AUCs decreased with elevated ambient lighting (0.78 +/- 0.03 to 0.72 +/- 0.04). Observer performance differences, however, were of the same order of magnitude as interobserver variability and were not statistically significant. Average selection times under increased ambient lighting remained constant or decreased, with the greatest decrease occurring for false-positive (20.4 +/- 18.9 to 14.4 +/- 9.6 seconds) and true-positive (18.0 +/- 13.8 to 12.9 +/- 9.4 seconds) selections. CONCLUSION: The results agree with those of previous studies in that observer performance differences under a controlled increase of ambient lighting are not statistically significant. On the basis of these findings and ACR guidelines, a moderate increase of ambient lighting in mammography reading rooms is still suggested, but further research with additional cases and observers should be considered.

Authors
Pollard, BJ; Samei, E; Chawla, AS; Baker, J; Ghate, S; Kim, C; Soo, MS; Hashimoto, N
MLA Citation
Pollard, BJ, Samei, E, Chawla, AS, Baker, J, Ghate, S, Kim, C, Soo, MS, and Hashimoto, N. "The influence of increased ambient lighting on mass detection in mammograms." Acad Radiol 16.3 (March 2009): 299-304.
PMID
19201358
Source
pubmed
Published In
Academic Radiology
Volume
16
Issue
3
Publish Date
2009
Start Page
299
End Page
304
DOI
10.1016/j.acra.2008.08.017

Automated breast mass detection in 3D reconstructed tomosynthesis volumes: a featureless approach.

The purpose of this study was to propose and implement a computer aided detection (CADe) tool for breast tomosynthesis. This task was accomplished in two stages-a highly sensitive mass detector followed by a false positive (FP) reduction stage. Breast tomosynthesis data from 100 human subject cases were used, of which 25 subjects had one or more mass lesions and the rest were normal. For stage 1, filter parameters were optimized via a grid search. The CADe identified suspicious locations were reconstructed to yield 3D CADe volumes of interest. The first stage yielded a maximum sensitivity of 93% with 7.7 FPs/breast volume. Unlike traditional CADe algorithms in which the second stage FP reduction is done via feature extraction and analysis, instead information theory principles were used with mutual information as a similarity metric. Three schemes were proposed, all using leave-one-case-out cross validation sampling. The three schemes, A, B, and C, differed in the composition of their knowledge base of regions of interest (ROIs). Scheme A's knowledge base was comprised of all the mass and FP ROIs generated by the first stage of the algorithm. Scheme B had a knowledge base that contained information from mass ROIs and randomly extracted normal ROIs. Scheme C had information from three sources of information-masses, FPs, and normal ROIs. Also, performance was assessed as a function of the composition of the knowledge base in terms of the number of FP or normal ROIs needed by the system to reach optimal performance. The results indicated that the knowledge base needed no more than 20 times as many FPs and 30 times as many normal ROIs as masses to attain maximal performance. The best overall system performance was 85% sensitivity with 2.4 FPs per breast volume for scheme A, 3.6 FPs per breast volume for scheme B, and 3 FPs per breast volume for scheme C.

Authors
Singh, S; Tourassi, GD; Baker, JA; Samei, E; Lo, JY
MLA Citation
Singh, S, Tourassi, GD, Baker, JA, Samei, E, and Lo, JY. "Automated breast mass detection in 3D reconstructed tomosynthesis volumes: a featureless approach." Med Phys 35.8 (August 2008): 3626-3636.
PMID
18777923
Source
pubmed
Published In
Medical physics
Volume
35
Issue
8
Publish Date
2008
Start Page
3626
End Page
3636
DOI
10.1118/1.2953562

A mathematical model platform for optimizing a multiprojection breast imaging system.

Multiprojection imaging is a technique in which a plurality of digital radiographic images of the same patient are acquired within a short interval of time from slightly different angles. Information from each image is combined to determine the final diagnosis. Projection data are either reconstructed into slices as in the case of tomosynthesis or analyzed directly as in the case of multiprojection correlation imaging technique, thereby avoiding reconstruction artifacts. In this study, the authors investigated the optimum geometry of acquisitions of a multiprojection breast correlation imaging system in terms of the number of projections and their total angular span that yield maximum performance in a task that models clinical decision. Twenty-five angular projections of each breast from 82 human subjects in our breast tomosynthesis database were each supplemented with a simulated 3 mm mass. An approach based on Laguerre-Gauss channelized Hotelling observer was developed to assess the detectability of the mass in terms of receiver operating characteristic (ROC) curves. Two methodologies were developed to integrate results from individual projections into one combined ROC curve as the overall figure of merit. To optimize the acquisition geometry, different components of acquisitions were changed to investigate which one of the many possible configurations maximized the area under the combined ROC curve. Optimization was investigated under two acquisition dose conditions corresponding to a fixed total dose delivered to the patient and a variable dose condition, based on the number of projections used. In either case, the detectability was dependent on the number of projections used, the total angular span of those projections, and the acquisition dose level. In the first case, the detectability approximately followed a bell curve as a function of the number of projections with the maximum between 8 and 16 projections spanning angular arcs of about 23 degrees-45 degrees, respectively. In the second case, the detectability increased with the number of projections approaching an asymptote at 11-17 projections for an angular span of about 45 degrees. These results indicate the inherent information content of the multi-projection image data reflecting the relative role of quantum and anatomical noise in multiprojection breast imaging. The optimization scheme presented here may be applied to any multiprojection imaging modalities and may be extended by including reconstruction in the case of digital breast tomosynthesis and breast computed tomography.

Authors
Chawla, AS; Samei, E; Saunders, RS; Lo, JY; Baker, JA
MLA Citation
Chawla, AS, Samei, E, Saunders, RS, Lo, JY, and Baker, JA. "A mathematical model platform for optimizing a multiprojection breast imaging system." Med Phys 35.4 (April 2008): 1337-1345.
PMID
18491528
Source
pubmed
Published In
Medical physics
Volume
35
Issue
4
Publish Date
2008
Start Page
1337
End Page
1345
DOI
10.1118/1.2885367

Training neural network classifiers for medical decision making: the effects of imbalanced datasets on classification performance.

This study investigates the effect of class imbalance in training data when developing neural network classifiers for computer-aided medical diagnosis. The investigation is performed in the presence of other characteristics that are typical among medical data, namely small training sample size, large number of features, and correlations between features. Two methods of neural network training are explored: classical backpropagation (BP) and particle swarm optimization (PSO) with clinically relevant training criteria. An experimental study is performed using simulated data and the conclusions are further validated on real clinical data for breast cancer diagnosis. The results show that classifier performance deteriorates with even modest class imbalance in the training data. Further, it is shown that BP is generally preferable over PSO for imbalanced training data especially with small data sample and large number of features. Finally, it is shown that there is no clear preference between oversampling and no compensation approach and some guidance is provided regarding a proper selection.

Authors
Mazurowski, MA; Habas, PA; Zurada, JM; Lo, JY; Baker, JA; Tourassi, GD
MLA Citation
Mazurowski, MA, Habas, PA, Zurada, JM, Lo, JY, Baker, JA, and Tourassi, GD. "Training neural network classifiers for medical decision making: the effects of imbalanced datasets on classification performance." Neural Netw 21.2-3 (March 2008): 427-436.
PMID
18272329
Source
pubmed
Published In
Neural Networks
Volume
21
Issue
2-3
Publish Date
2008
Start Page
427
End Page
436
DOI
10.1016/j.neunet.2007.12.031

4-13 Effect of Computer-Aided Detection on Independent Double Reading of Paired Screen-Film and Full-Field Digital Screening Mammograms

Authors
Baker, JA
MLA Citation
Baker, JA. "4-13 Effect of Computer-Aided Detection on Independent Double Reading of Paired Screen-Film and Full-Field Digital Screening Mammograms." Breast Diseases 18.4 (2008): 357--.
Source
scival
Published In
Breast Diseases: A Year Book Quarterly
Volume
18
Issue
4
Publish Date
2008
Start Page
357-
DOI
10.1016/S1043-321X(07)80394-8

Does image quality matter? Impact of resolution and noise on mammographic task performance.

The purpose of this study was to examine the effects of different resolution and noise levels on task performance in digital mammography. This study created an image set with images at three different resolution levels, corresponding to three digital display devices, and three different noise levels, with noise magnitudes similar to full clinical dose, half clinical dose, and quarter clinical dose. The images were read by five experienced breast imaging radiologists. The data were then analyzed to compute two accuracy statistics (overall classification accuracy and lesion detection accuracy) and performance at four diagnostic tasks (detection of microcalcifications, benign masses, malignant masses, and discrimination of benign and malignant masses). Human observer results showed decreasing display resolution had little effect on overall classification accuracy and individual diagnostic task performance, but increasing noise caused overall classification accuracy to decrease by a statistically significant 21% as the breast dose went to one quarter of its normal clinical value. The noise effects were most prominent for the tasks of microcalcification detection and mass discrimination. When the noise changed from full clinical dose to quarter clinical dose, the microcalcification detection performance fell from 89% to 67% and the mass discrimination performance decreased from 93% to 79%, while malignant mass detection performance remained relatively constant with values of 88% and 84%, respectively. As a secondary aim, the image set was also analyzed by two observer models to examine whether their performance was similar to humans. Observer models differed from human observers and each other in their sensitivity to resolution degradation and noise. The primary conclusions of this study suggest that quantum noise appears to be the dominant image quality factor in digital mammography, affecting radiologist performance much more profoundly than display resolution.

Authors
Saunders, RS; Baker, JA; Delong, DM; Johnson, JP; Samei, E
MLA Citation
Saunders, RS, Baker, JA, Delong, DM, Johnson, JP, and Samei, E. "Does image quality matter? Impact of resolution and noise on mammographic task performance." Med Phys 34.10 (October 2007): 3971-3981.
PMID
17985642
Source
pubmed
Published In
Medical physics
Volume
34
Issue
10
Publish Date
2007
Start Page
3971
End Page
3981
DOI
10.1118/1.2776253

Breast mass lesions: computer-aided diagnosis models with mammographic and sonographic descriptors.

PURPOSE: To retrospectively develop and evaluate computer-aided diagnosis (CAD) models that include both mammographic and sonographic descriptors. MATERIALS AND METHODS: Institutional review board approval was obtained for this HIPAA-compliant study. A waiver of informed consent was obtained. Mammographic and sonographic examinations were performed in 737 patients (age range, 17-87 years), which yielded 803 breast mass lesions (296 malignant, 507 benign). Radiologist-interpreted features from mammograms and sonograms were used as input features for linear discriminant analysis (LDA) and artificial neural network (ANN) models to differentiate benign from malignant lesions. An LDA with all the features was compared with an LDA with only stepwise-selected features. Classification performances were quantified by using receiver operating characteristic (ROC) analysis and were evaluated in a train, validate, and retest scheme. On the retest set, both LDAs were compared with radiologist assessment score of malignancy. RESULTS: Both the LDA and ANN achieved high classification performance with cross validation (area under the ROC curve [A(z)] = 0.92 +/- 0.01 [standard deviation] and (0.90)A(z) = 0.54 +/- 0.08 for LDA, A(z) = 0.92 +/- 0.01 and (0.90)A(z) = 0.55 +/- 0.08 for ANN). Results of both models generalized well to the retest set, with no significant performance differences between the validate and retest sets (P > .1). On the retest set, there were no significant performance differences between LDA with all features and LDA with only the stepwise-selected features (P > .3) and between either LDA and radiologist assessment score (P > .2). CONCLUSION: Results showed that combining mammographic and sonographic descriptors in a CAD model can result in high classification and generalization performance. On the retest set, LDA performance matched radiologist classification performance.

Authors
Jesneck, JL; Lo, JY; Baker, JA
MLA Citation
Jesneck, JL, Lo, JY, and Baker, JA. "Breast mass lesions: computer-aided diagnosis models with mammographic and sonographic descriptors." Radiology 244.2 (August 2007): 390-398.
PMID
17562812
Source
pubmed
Published In
Radiology
Volume
244
Issue
2
Publish Date
2007
Start Page
390
End Page
398
DOI
10.1148/radiol.2442060712

Digital mammography: effects of reduced radiation dose on diagnostic performance.

PURPOSE: To experimentally determine the relationship between radiation dose and observer accuracy in the detection and discrimination of simulated lesions for digital mammography. MATERIALS AND METHODS: This HIPAA-compliant study received institutional review board approval; the informed consent requirement was waived. Three hundred normal craniocaudal images were selected from an existing database of digital mammograms. Simulated mammographic lesions that mimicked benign and malignant masses and clusters of microcalcifications (3.3-7.4 cm in diameter) were then superimposed on images. Images were rendered without and with added radiographic noise to simulate effects of reducing the radiation dose to one half and one quarter of the clinical dose. Images were read by five experienced breast imaging radiologists. Results were analyzed to determine effects of reduced dose on overall interpretation accuracy, detection of microcalcifications and masses, discrimination between benign and malignant masses, and interpretation time. RESULTS: Overall accuracy decreased from 0.83 with full dose to 0.78 and 0.62 with half and quarter doses, respectively. The decrease associated with transition from full dose to quarter dose was significant (P < .01), primarily because of an effect on detection of microcalcifications (P < .01) and discrimination of masses (P < .05). The level of dose reduction did not significantly affect detection of malignant masses (P > .5). However, reduced dose resulted in an increased mean interpretation time per image by 28% (P < .0001). CONCLUSION: These findings suggest that dose reduction in digital mammography has a measurable but modest effect on diagnostic accuracy. The small magnitude of the effect in response to the drastic reduction of dose suggests potential for modest dose reductions in digital mammography.

Authors
Samei, E; Saunders, RS; Baker, JA; Delong, DM
MLA Citation
Samei, E, Saunders, RS, Baker, JA, and Delong, DM. "Digital mammography: effects of reduced radiation dose on diagnostic performance." Radiology 243.2 (May 2007): 396-404.
PMID
17356178
Source
pubmed
Published In
Radiology
Volume
243
Issue
2
Publish Date
2007
Start Page
396
End Page
404
DOI
10.1148/radiol.2432061065

Minimal Screening Mammography Recall Rates Using Standardized BI-RADS Criteria

Authors
Ghate, SV; Kim, C; Johnson, K; Baker, JA; Soo, MC
MLA Citation
Ghate, SV, Kim, C, Johnson, K, Baker, JA, and Soo, MC. "Minimal Screening Mammography Recall Rates Using Standardized BI-RADS Criteria." AMERICAN JOURNAL OF ROENTGENOLOGY 188.5 (May 2007).
Source
wos-lite
Published In
AJR. American journal of roentgenology
Volume
188
Issue
5
Publish Date
2007

Comparison of LCD and CRT displays based on efficacy for digital mammography.

RATIONALE AND OBJECTIVES: To compare two display technologies, cathode ray tube (CRT) and liquid crystal display (LCD), in terms of diagnostic accuracy for several common clinical tasks in digital mammography. MATERIALS AND METHODS: Simulated masses and microcalcifications were inserted into normal digital mammograms to produce an image set of 400 images. Images were viewed on one CRT and one LCD medical-quality display device by five experienced breast-imaging radiologists who rated the images using a categorical rating paradigm. The observer data were analyzed to determine overall classification accuracy, overall lesion detection accuracy, and accuracy for four specific diagnostic tasks: detection of benign masses, malignant masses, and microcalcifications, and discrimination of benign and malignant masses. RESULTS: Radiologists had similar overall classification accuracy (LCD: 0.83 +/- 0.01, CRT: 0.82 +/- 0.01) and lesion detection accuracy (LCD: 0.87 +/- 0.01, CRT: 0.85 +/- 0.01) on both displays. The difference in accuracy between LCD and CRT for the detection of benign masses, malignant masses, and microcalcifications, and discrimination of benign and malignant masses was -0.019 +/- 0.009, 0.020 +/- 0.008, 0.012 +/- 0.013, and 0.0094 +/- 0.011, respectively. Overall, the two displays did not exhibit any statistically significant difference (P > .05). CONCLUSION: This study explored the suitability of two different soft-copy displays for the viewing of mammographic images. It found that LCD and CRT displays offer similar clinical utility for mammographic tasks.

Authors
Saunders, RS; Samei, E; Baker, J; Delong, D; Soo, MS; Walsh, R; Pisano, E; Kuzmiak, CM; Pavic, D
MLA Citation
Saunders, RS, Samei, E, Baker, J, Delong, D, Soo, MS, Walsh, R, Pisano, E, Kuzmiak, CM, and Pavic, D. "Comparison of LCD and CRT displays based on efficacy for digital mammography." Acad Radiol 13.11 (November 2006): 1317-1326.
PMID
17070449
Source
pubmed
Published In
Academic Radiology
Volume
13
Issue
11
Publish Date
2006
Start Page
1317
End Page
1326
DOI
10.1016/j.acra.2006.07.017

Optimized approach to decision fusion of heterogeneous data for breast cancer diagnosis.

As more diagnostic testing options become available to physicians, it becomes more difficult to combine various types of medical information together in order to optimize the overall diagnosis. To improve diagnostic performance, here we introduce an approach to optimize a decision-fusion technique to combine heterogeneous information, such as from different modalities, feature categories, or institutions. For classifier comparison we used two performance metrics: The receiving operator characteristic (ROC) area under the curve [area under the ROC curve (AUC)] and the normalized partial area under the curve (pAUC). This study used four classifiers: Linear discriminant analysis (LDA), artificial neural network (ANN), and two variants of our decision-fusion technique, AUC-optimized (DF-A) and pAUC-optimized (DF-P) decision fusion. We applied each of these classifiers with 100-fold cross-validation to two heterogeneous breast cancer data sets: One of mass lesion features and a much more challenging one of microcalcification lesion features. For the calcification data set, DF-A outperformed the other classifiers in terms of AUC (p < 0.02) and achieved AUC=0.85 +/- 0.01. The DF-P surpassed the other classifiers in terms of pAUC (p < 0.01) and reached pAUC=0.38 +/- 0.02. For the mass data set, DF-A outperformed both the ANN and the LDA (p < 0.04) and achieved AUC=0.94 +/- 0.01. Although for this data set there were no statistically significant differences among the classifiers' pAUC values (pAUC=0.57 +/- 0.07 to 0.67 +/- 0.05, p > 0.10), the DF-P did significantly improve specificity versus the LDA at both 98% and 100% sensitivity (p < 0.04). In conclusion, decision fusion directly optimized clinically significant performance measures, such as AUC and pAUC, and sometimes outperformed two well-known machine-learning techniques when applied to two different breast cancer data sets.

Authors
Jesneck, JL; Nolte, LW; Baker, JA; Floyd, CE; Lo, JY
MLA Citation
Jesneck, JL, Nolte, LW, Baker, JA, Floyd, CE, and Lo, JY. "Optimized approach to decision fusion of heterogeneous data for breast cancer diagnosis." Med Phys 33.8 (August 2006): 2945-2954.
Website
http://hdl.handle.net/10161/207
PMID
16964873
Source
pubmed
Published In
Medical physics
Volume
33
Issue
8
Publish Date
2006
Start Page
2945
End Page
2954
DOI
10.1118/1.2208934

Simulation of mammographic lesions.

RATIONALE AND OBJECTIVES: This study presents a method for generating breast masses and microcalcifications in mammography via simulation. This simulation method allows for the creation of large image datasets with particular lesions, which may serve as a useful tool for perception studies measuring imaging system performance. MATERIALS AND METHODS: The study first characterized the radiographic appearance of both masses and microcalcifications, examining the following five properties: contrast, edge gradient profile of masses, edge characteristics of masses, shapes of individual microcalcifications, and shapes of microcalcification distributions. The characterization results then guided the development of routines that created simulated masses and microcalcifications. The quality of the simulations was verified by experienced breast imaging radiologists who evaluated simulated and real lesions and rated whether a given lesion had a realistic appearance. RESULTS: The radiologists rated real and simulated lesions to have similarly realistic appearances. Using receiver operating characteristic analysis to characterize the degree of similarity, the results showed an A(z) of 0.68 +/- 0.07 for benign masses, 0.65 +/- 0.07 for malignant masses, and 0.62 +/- 0.07 for microcalcifications, thus showing notable overlap in the simulated and real lesion ratings. CONCLUSION: This research introduced a new approach for simulating breast masses and microcalcifications that relied on anatomic characteristics measured from real lesions. Results from an observer performance experiment indicate that our simulation routine produced realistic simulations of masses and microcalcifications as judged by expert radiologists.

Authors
Saunders, R; Samei, E; Baker, J; Delong, D
MLA Citation
Saunders, R, Samei, E, Baker, J, and Delong, D. "Simulation of mammographic lesions." Acad Radiol 13.7 (July 2006): 860-870.
PMID
16777560
Source
pubmed
Published In
Academic Radiology
Volume
13
Issue
7
Publish Date
2006
Start Page
860
End Page
870
DOI
10.1016/j.acra.2006.03.015

MRI-guided vacuum-assisted breast biopsy with a handheld portable biopsy system.

OBJECTIVE: The purpose of this study was to evaluate a compact portable 10-gauge handheld battery-operated vacuum-assisted biopsy system for MRI-guided breast biopsy. CONCLUSION: The compact portable battery-operated biopsy system can be used successfully for MRI-guided core breast biopsy and is an alternative to current systems.

Authors
Ghate, SV; Rosen, EL; Soo, MSC; Baker, JA
MLA Citation
Ghate, SV, Rosen, EL, Soo, MSC, and Baker, JA. "MRI-guided vacuum-assisted breast biopsy with a handheld portable biopsy system." AJR Am J Roentgenol 186.6 (June 2006): 1733-1736.
PMID
16714667
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
186
Issue
6
Publish Date
2006
Start Page
1733
End Page
1736
DOI
10.2214/AJR.05.0551

Streaming detection for evaluation of indeterminate sonographic breast masses: a pilot study.

OBJECTIVE: Streaming detection is a novel sonography technique that uses ultrasonic energy to induce movement in cyst fluid that is detected on Doppler sonography. This pilot study evaluates the utility of streaming detection for differentiating cysts from solid masses in breast lesions that are indeterminate on sonography. SUBJECTS AND METHODS: Thirty-nine lesions-11 simple cysts and seven solid masses (control group) and 21 masses with indeterminate findings for the diagnosis of a cyst versus a solid lesion (study group)-in 34 patients were evaluated using streaming detection. All lesions underwent cyst aspiration or biopsy (n = 35) or were diagnosed simple cysts (n = 4) on sonography. Lesion size and depth were recorded. Streaming detection software was placed on conventional sonography units. Acoustic pulses were focused on the lesion, and if fluid movement was generated, it was seen on the spectral Doppler display as velocity away from the transducer. Lesions were then aspirated or underwent biopsy, and the viscosity of the aspirated fluid was recorded. The sensitivity and specificity of the technique and the effect of cyst size, cyst depth, and fluid viscosity in diagnosing fluid-filled cysts were assessed. RESULTS: Overall, 31 cysts and eight solid masses (seven benign, one carcinoma) were diagnosed in the study and control groups. Aspiration of indeterminate lesions resulted in 20 cysts and one solid mass. Lesions ranged in size from 4 to 47 mm and in depth from 4 to 29 mm. In the control group, streaming detection correctly showed nine of the 11 simple cysts (sensitivity, 82%; positive predictive value, 100%), and acoustic streaming was absent in all seven solid masses (specificity, 100%; negative predictive value, 78%). Of the indeterminate lesions, streaming detection allowed correct identification of 10 of 20 cysts (sensitivity, 50%; positive predictive value, 100%). Acoustic streaming was not detected in the one solid study group lesion. Neither cyst size or depth nor fluid viscosity had a significant effect on the ability to detect fluid. CONCLUSION: The streaming detection technique improved differentiation of cysts from solid masses in indeterminate lesions and has potential for reducing the number of recommended cyst aspirations for the diagnosis of indeterminate breast masses.

Authors
Soo, MS; Ghate, SV; Baker, JA; Rosen, EL; Walsh, R; Warwick, BN; Ramachandran, AR; Nightingale, KR
MLA Citation
Soo, MS, Ghate, SV, Baker, JA, Rosen, EL, Walsh, R, Warwick, BN, Ramachandran, AR, and Nightingale, KR. "Streaming detection for evaluation of indeterminate sonographic breast masses: a pilot study." AJR Am J Roentgenol 186.5 (May 2006): 1335-1341.
PMID
16632728
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
186
Issue
5
Publish Date
2006
Start Page
1335
End Page
1341
DOI
10.2214/AJR.05.0005

Computer-aided diagnosis in breast imaging: Where do we go after detection?

Authors
Lo, JY; Bilska-Wolak, AO; Baker, JA; Tourassi, GD; Floyd, CE; Markey, MK
MLA Citation
Lo, JY, Bilska-Wolak, AO, Baker, JA, Tourassi, GD, Floyd, CE, and Markey, MK. "Computer-aided diagnosis in breast imaging: Where do we go after detection?." Recent Advances in Breast Imaging, Mammography, and Computer-Aided Diagnosis of Breast Cancer. April 10, 2006. 871-900.
Source
scopus
Publish Date
2006
Start Page
871
End Page
900
DOI
10.1117/3.651880.ch27

Gaussian frequency blending algorithm with Matrix Inversion Tomosynthesis (MITS) and Filtered Back Projection (FBP) for better digital breast tomosynthesis reconstruction

Breast cancer is a major problem and the most common cancer among women. The nature of conventional mammography makes it very difficult to distinguish a cancer from overlying breast tissues. Digital Tomosynthesis refers to a three-dimensional imaging technique that allows reconstruction of an arbitrary set of planes in the breast from limited-angle series of projection images as the x-ray source moves. Several tomosynthesis algorithms have been proposed, including Matrix Inversion Tomosynthesis (MITS) and Filtered Back Projection (FBP) that have been investigated in our lab. MITS shows better high frequency response in removing out-of-plane blur, while FBP shows better low frequency noise prosperities. This paper presents an effort to combine MITS and FBP for better breast tomosynthesis reconstruction. A high-pass Gaussian filter was designed and applied to three-slice "slabbing" MITS reconstructions. A low-pass Gaussian filter was designed and applied to the FBP reconstructions. A frequency weighting parameter was studied to blend the high-passed MITS with low-passed FBP frequency components. Four different reconstruction methods were investigated and compared with human subject images: 1) MITS blended with Shift-And-Add (SAA), 2) FBP alone, 3) FBP with applied Hamming and Gaussian Filters, and 4) Gaussian Frequency Blending (GFB) of MITS and FBP. Results showed that, compared with FBP, Gaussian Frequency Blending (GFB) has better performance for high frequency content such as better reconstruction of micro-calcifications and removal of high frequency noise. Compared with MITS, GFB showed more low frequency breast tissue content.

Authors
Chen, Y; Lo, JY; Baker, JA; III, JTD
MLA Citation
Chen, Y, Lo, JY, Baker, JA, and III, JTD. "Gaussian frequency blending algorithm with Matrix Inversion Tomosynthesis (MITS) and Filtered Back Projection (FBP) for better digital breast tomosynthesis reconstruction." Progress in Biomedical Optics and Imaging - Proceedings of SPIE 6142 I (2006).
Source
scival
Published In
Proceedings of SPIE
Volume
6142 I
Publish Date
2006
DOI
10.1117/12.652264

The effect of data set size on computer-aided diagnosis of breast cancer: Comparing decision fusion to a linear discriminant

Data sets with relatively few observations (cases) in medical research are common, especially if the data are expensive or difficult to collect. Such small sample sizes usually do not provide enough information for computer models to learn data patterns well enough for good prediction and generalization. As a model that may be able to maintain good classification performance in the presence of limited data, we used decision fusion. In this study, we investigated the effect of sample size on the generalization ability of both linear discriminant analysis (LDA) and decision fusion. Subsets of large data sets were selected by a bootstrap sampling method, which allowed us to estimate the mean and standard deviation of the classification performance as a function of data set size. We applied the models to two breast cancer data sets and compared the models using receiver operating characteristic (ROC) analysis. For the more challenging calcification data set, decision fusion reached its maximum classification performance of AUC = 0.80±0.04 at 50 samples and pAUC = 0.34±0.05 at 100 samples. The LDA reached a lower performance and required many more cases, with a maximum of AUC = 0.68±0.04 and pAUC = 0.12±0.05 at 450 samples. For the mass data set, the two classifiers had more similar performance, with AUC = 0.92±0.02 and pAUC = 0.48±0.02 at 50 samples for decision fusion and AUC = 0.92±0.03 and pAUC = 0.55±0.04 at 500 samples for the LDA.

Authors
Jesneck, JL; Nolte, LW; Baker, JA; Lo, JY
MLA Citation
Jesneck, JL, Nolte, LW, Baker, JA, and Lo, JY. "The effect of data set size on computer-aided diagnosis of breast cancer: Comparing decision fusion to a linear discriminant." Progress in Biomedical Optics and Imaging - Proceedings of SPIE 6146 (2006).
Source
scival
Published In
Proceedings of SPIE
Volume
6146
Publish Date
2006
DOI
10.1117/12.655235

Reply [2]

Authors
Soo, MS; Ghate, S; Baker, JA; Rosen, E
MLA Citation
Soo, MS, Ghate, S, Baker, JA, and Rosen, E. "Reply [2]." American Journal of Roentgenology 186.3 (2006): 902-903.
Source
scival
Published In
AJR. American journal of roentgenology
Volume
186
Issue
3
Publish Date
2006
Start Page
902
End Page
903
DOI
10.2214/AJR.06.5013-1

Computer aid for decision to biopsy breast masses on mammography: validation on new cases.

RATIONALE AND OBJECTIVES: The purpose of this study was to validate the performance of a previously developed computer aid for breast mass classification for mammography on a new, independent database of cases not used for algorithm development. MATERIALS AND METHODS: A computer aid (classifier) based on the likelihood ratio (LRb) was previously developed on a database of 670 mass cases. The 670 cases (245 malignant) from one medical institution were described using 16 features from the American College of Radiology Breast Imaging-Reporting and Data System lexicon and patient history findings. A separate database of 151 (43 malignant) validation cases were collected that were previously unseen by the classifier. These new validation cases were evaluated by the classifier without retraining. Performance evaluation methods included Receiver Operating Characteristic (ROC), round-robin, and leave-one-out bootstrap sampling. RESULTS: The performance of the classifier on the training data yielded an average ROC area of 0.90 +/- 0.02 and partial ROC area (0.90AUC) of 0.60 +/- 0.06. The exact nonparametric performance on the validation set of 151 cases yielded a ROC area of 0.88 and 0.90AUC of 0.57. Using a 100% sensitivity cutoff threshold established on the training data (100% negative predictive value), the classifier correctly identified 100% of the malignant masses in the validation test set, while potentially obviating 26% of the biopsies performed on benign masses. CONCLUSION: The LRb classifier performed consistently on new data that was not used for classifier development. The LRb classifier shows promise as a potential aid in reducing the number of biopsies performed on benign masses.

Authors
Bilska-Wolak, AO; Floyd, CE; Lo, JY; Baker, JA
MLA Citation
Bilska-Wolak, AO, Floyd, CE, Lo, JY, and Baker, JA. "Computer aid for decision to biopsy breast masses on mammography: validation on new cases." Acad Radiol 12.6 (June 2005): 671-680.
PMID
15935965
Source
pubmed
Published In
Academic Radiology
Volume
12
Issue
6
Publish Date
2005
Start Page
671
End Page
680
DOI
10.1016/j.acra.2005.02.011

The effects of gray scale image processing on digital mammography interpretation performance.

RATIONALE AND OBJECTIVES: To determine the effects of three image-processing algorithms on diagnostic accuracy of digital mammography in comparison with conventional screen-film mammography. MATERIALS AND METHODS: A total of 201 cases consisting of nonprocessed soft copy versions of the digital mammograms acquired from GE, Fischer, and Trex digital mammography systems (1997-1999) and conventional screen-film mammograms of the same patients were interpreted by nine radiologists. The raw digital data were processed with each of three different image-processing algorithms creating three presentations-manufacturer's default (applied and laser printed to film by each of the manufacturers), MUSICA, and PLAHE-were presented in soft copy display. There were three radiologists per presentation. RESULTS: Area under the receiver operating characteristic curve for GE digital mass cases was worse than screen-film for all digital presentations. The area under the receiver operating characteristic for Trex digital mass cases was better, but only with images processed with the manufacturer's default algorithm. Sensitivity for GE digital mass cases was worse than screen film for all digital presentations. Specificity for Fischer digital calcifications cases was worse than screen film for images processed in default and PLAHE algorithms. Specificity for Trex digital calcifications cases was worse than screen film for images processed with MUSICA. CONCLUSION: Specific image-processing algorithms may be necessary for optimal presentation for interpretation based on machine and lesion type.

Authors
Cole, EB; Pisano, ED; Zeng, D; Muller, K; Aylward, SR; Park, S; Kuzmiak, C; Koomen, M; Pavic, D; Walsh, R; Baker, J; Gimenez, EI; Freimanis, R
MLA Citation
Cole, EB, Pisano, ED, Zeng, D, Muller, K, Aylward, SR, Park, S, Kuzmiak, C, Koomen, M, Pavic, D, Walsh, R, Baker, J, Gimenez, EI, and Freimanis, R. "The effects of gray scale image processing on digital mammography interpretation performance." Acad Radiol 12.5 (May 2005): 585-595.
PMID
15866131
Source
pubmed
Published In
Academic Radiology
Volume
12
Issue
5
Publish Date
2005
Start Page
585
End Page
595
DOI
10.1016/j.acra.2005.01.017

Accuracy of segmentation of a commercial computer-aided detection system for mammography.

PURPOSE: To assess the accuracy of segmentation in a commercially available computer-aided detection (CAD) system. MATERIALS AND METHODS: Approval for this study was obtained from the authors' institutional review board. Informed consent was not required by the board for this review, as data were stripped of patient identifiers. Two thousand twenty mammograms from 507 women were analyzed with the hardware and software of a commercial CAD system. The accuracy of the segmentation process was determined semiquantitatively and categorized as near perfect if the skin line of the breast was accurately detected, acceptable if only subcutaneous fat was excluded, or unacceptable if any breast parenchyma was excluded from consideration. The accuracy of segmentation was compared for different breast densities and film sizes by using logistic regression (P < .05). RESULTS: Overall, segmentation was near perfect or acceptable in almost 96.8% of images. However, segmentation defects were significantly more common in mammograms with heterogeneously dense breast tissue (8% unacceptable) than in those with fatty replaced (0% unacceptable), scattered (1.2% unacceptable), or extremely dense (1.8% unacceptable) breast parenchyma (P < .05). For images with unacceptable segmentation, the average percentage of breast parenchyma excluded was almost 25% (range, 5%-100%), with no significant differences among breast densities. CONCLUSION: For one commercial CAD system, segmentation was usually near perfect or acceptable but was unacceptable more than five times more frequently for mammograms of breasts with heterogeneously dense parenchyma than for those with all other breast densities. On average, one-quarter of the breast parenchyma was excluded from CAD analysis for images with unacceptable segmentation.

Authors
Baker, JA; Rosen, EL; Crockett, MM; Lo, JY
MLA Citation
Baker, JA, Rosen, EL, Crockett, MM, and Lo, JY. "Accuracy of segmentation of a commercial computer-aided detection system for mammography." Radiology 235.2 (May 2005): 385-390.
PMID
15770043
Source
pubmed
Published In
Radiology
Volume
235
Issue
2
Publish Date
2005
Start Page
385
End Page
390
DOI
10.1148/radiol.2352040899

Comparison of recall and cancer detection rates for immediate versus batch interpretation of screening mammograms.

PURPOSE: To retrospectively compare recall and cancer detection rates between immediate and subsequent batch methods for interpretation of screening mammograms. MATERIALS AND METHODS: Institutional review board approval was obtained, and informed consent was waived. Retrospective analysis was performed for 8698 screening mammograms obtained between January 1 and October 31, 2001, which were interpreted either immediately (n = 4113) or subsequently with batch method (n = 4585). Data were collected from data reporting system and patient billing records. Patients with high risk factors were excluded; 3441 patients were in the immediate group, and 3932 were in the batch group. The two groups were compared with respect to age, breast density, and availability of comparison films with Wilcoxon rank sum test. Recall rates and cancer detection rates for each group were determined and compared with Pearson chi(2) test; false-negative rates were compared with Fischer exact test. RESULTS: A significant difference (P < .001) was noted in recall rates between immediate (18%) and batch (14%) groups; however, no significant difference (P = .7) was noted in cancer detection rates (immediate, 0.5%; batch, 0.4%). Mean age of patients was 56.8 years (age range, 21-96 years) in the immediate group and 56.2 years (age range 24-98 years) in the batch group (P = .02). Comparison of breast densities between groups indicates no statistically significant difference (P = .4). The batch group had significantly fewer comparison mammograms (3106 [79%]) available than the immediate group (2856 [83%]) (P < .001). There was no significant difference in false-negative rates between the immediate group (0.1%) and the batch group (0.1%) (P > .99). CONCLUSION: Immediate interpretation of screening mammograms resulted in a statistically significant increase in recalls and additional clinical work-ups of perceived abnormalities; however, no significant difference in cancer detection rate was detected between groups.

Authors
Ghate, SV; Soo, MS; Baker, JA; Walsh, R; Gimenez, EI; Rosen, EL
MLA Citation
Ghate, SV, Soo, MS, Baker, JA, Walsh, R, Gimenez, EI, and Rosen, EL. "Comparison of recall and cancer detection rates for immediate versus batch interpretation of screening mammograms." Radiology 235.1 (April 2005): 31-35.
PMID
15798165
Source
pubmed
Published In
Radiology
Volume
235
Issue
1
Publish Date
2005
Start Page
31
End Page
35
DOI
10.1148/radiol.2351040699

BI-RADS for sonography: positive and negative predictive values of sonographic features.

OBJECTIVE: The purpose of this study was to assess the positive predictive value (PPV) and negative predictive value (NPV) of features described in the new sonographic BI-RADS lexicon for evaluating solid masses with known histologic diagnoses. MATERIALS AND METHODS: Sonograms of 403 solid lesions were analyzed by one of three dedicated breast radiologists. Each lesion was described using features from the sonographic BI-RADS lexicon. Lesion description and biopsy results were correlated. PPV and NPV were calculated. RESULTS: Histologic results showed that 141 (35%) of 403 masses were malignant. Sonographic BI-RADS descriptors showing high predictive value for malignancy include spiculated margin (86%, 19/22), irregular shape (62%, 102/164), and nonparallel orientation (69%, 75/109). Sonographic BI-RADS descriptors highly predictive of benign lesions include circumscribed margin (90%, 160/178), parallel orientation (78%, 228/294), and oval shape (84%, 200/237). For the sonographic BI-RADS features of mass margin, shape, orientation, lesion boundary, echo pattern, and posterior acoustic features, descriptors chosen were significantly (p < 0.001) different for malignant and benign masses. CONCLUSION: Descriptors from the new sonographic BI-RADS lexicon can be useful in differentiating benign from malignant solid masses.

Authors
Hong, AS; Rosen, EL; Soo, MS; Baker, JA
MLA Citation
Hong, AS, Rosen, EL, Soo, MS, and Baker, JA. "BI-RADS for sonography: positive and negative predictive values of sonographic features." AJR Am J Roentgenol 184.4 (April 2005): 1260-1265.
PMID
15788607
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
184
Issue
4
Publish Date
2005
Start Page
1260
End Page
1265
DOI
10.2214/ajr.184.4.01841260

Computer-aided detection of amorphous calcifications.

OBJECTIVE: Computer-aided detection (CAD) systems have been used successfully to detect malignant calcifications on mammography, with sensitivities ranging from 86% to 99%. Amorphous calcifications are a subset of small indistinct calcifications of intermediate concern that have a 20% likelihood of being malignant and that are frequently overlooked on mammography. The purpose of our study was to determine the sensitivity of one commercially available CAD system for detecting amorphous calcifications. MATERIALS AND METHODS: A commercially available CAD system evaluated mammograms of 82 patients with 85 mammographically detected and histologically sampled groups of amorphous calcifications (21 malignant, 14 high risk, and 50 benign). The sensitivity of the system for detecting the calcifications on at least one image of the two-view mammographic examination (case sensitivity) and on each individual mammographic image (image sensitivity) was determined. Findings were correlated with results from large core needle biopsy or surgical excision in each case. RESULTS: The CAD system detected amorphous calcifications in 43 of 85 cases (case sensitivity, 51%) and in 59 of 146 mammographic images (image sensitivity, 40%). The case sensitivities by histologic outcome were 57% for malignant calcifications, 29% for high-risk calcifications, and 54% for benign calcifications. An average of 2.0 false-positive marks were displayed per case. CONCLUSION: The CAD sensitivity for malignant amorphous calcifications is markedly lower than previously reported for all malignant calcifications. Breast imaging radiologists who use CAD systems should continue to search diligently for these difficult-to-detect lesions.

Authors
Soo, MS; Rosen, EL; Xia, JQ; Ghate, S; Baker, JA
MLA Citation
Soo, MS, Rosen, EL, Xia, JQ, Ghate, S, and Baker, JA. "Computer-aided detection of amorphous calcifications." AJR Am J Roentgenol 184.3 (March 2005): 887-892.
PMID
15728613
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
184
Issue
3
Publish Date
2005
Start Page
887
End Page
892
DOI
10.2214/ajr.184.3.01840887

Detection of primary breast carcinoma with a dedicated, large-field-of-view FDG PET mammography device: initial experience.

PURPOSE: To prospectively assess a dedicated, large field of view positron emission tomography (PET) mammographic device for imaging primary breast carcinoma. MATERIALS AND METHODS: Institutional review board approval was obtained for this study, and all patients provided written informed consent prior to participation. Subjects were recruited from a cohort of patients in whom diagnostic mammography and/or ultrasonography demonstrated lesions that were highly suggestive of malignancy. Twenty-three patients who met the inclusion criteria were subsequently imaged by using a dedicated PET mammography unit that was developed in conjunction with the Thomas Jefferson National Accelerator Facility (Newport News, Va). One hour after administration of 2.0-2.5 mCi (74.0-93.5 MBq) of fluorodeoxyglucose, 5-minute PET mammography of the affected breast was performed. Images were processed and reconstructed in the transverse craniocaudal and coronal planes. For each lesion, image-guided core-needle biopsy was performed immediately after PET mammography. Conventional mammography results and histologic findings were correlated with PET mammography images. The sensitivity, specificity, negative predictive value, and positive predictive value of PET mammography for demonstrating malignant lesions were calculated. RESULTS: PET mammography demonstrated 20 focal abnormalities, of which 18 were malignant and two were benign. Both benign lesions represented areas of fat necrosis. Three of 20 malignant lesions demonstrated at conventional mammography were not demonstrated at PET mammography. The overall sensitivity of PET mammography for malignancy was 86% (95% confidence interval: 65%, 95%), with a positive predictive value of 90% (95% confidence interval: 70%, 97%). The calculated specificity was 33% (95% confidence interval: 2%, 79%), and the negative predictive value was 25% (95% confidence interval: 1%, 70%). CONCLUSION: These pilot data suggest that PET mammography can demonstrate small primary breast malignancies.

Authors
Rosen, EL; Turkington, TG; Soo, MS; Baker, JA; Coleman, RE
MLA Citation
Rosen, EL, Turkington, TG, Soo, MS, Baker, JA, and Coleman, RE. "Detection of primary breast carcinoma with a dedicated, large-field-of-view FDG PET mammography device: initial experience." Radiology 234.2 (February 2005): 527-534.
PMID
15671006
Source
pubmed
Published In
Radiology
Volume
234
Issue
2
Publish Date
2005
Start Page
527
End Page
534
DOI
10.1148/radiol.2342040654

Effect of display resolution on the detection of mammographie lesions

For diagnosis of breast cancer by mammography, the mammograms must be viewed by a radiologist. The purpose of this study was to determine the effect of display resolution on the specific clinical task of detection of breast lesions by a human observer. Using simulation techniques, this study proceeded through four stages. First, we inserted simulated masses and calcifications into raw digital mammograms. The resulting images were processed according to standard image processing techniques and appropriately windowed and leveled. The processed images were blurred according to MTFs measured from a clinical Cathode Ray Tube display. JNDMetrix, a Visual Discrimination Model, examined the images to estimate human detection. The model results suggested that detection of masses and calcifications decreased under standard CRT resolution. Future work will confirm these results with human observer studies. (This work was supported by grants NIH R21-CA95308 and USAMRMC W81XWH-04-1-0323.).

Authors
Jr, RSS; Samei, E; Johnson, J; Baker, J
MLA Citation
Jr, RSS, Samei, E, Johnson, J, and Baker, J. "Effect of display resolution on the detection of mammographie lesions." Progress in Biomedical Optics and Imaging - Proceedings of SPIE 5749 (2005): 243-250.
Source
scival
Published In
Proceedings of SPIE
Volume
5749
Publish Date
2005
Start Page
243
End Page
250
DOI
10.1117/12.595682

Computer-aided detection in screening mammography: variability in cues.

PURPOSE: To evaluate the variability of true-positive and false-positive cues by using a commercially available computer-aided detection (CAD) system for analysis of 50 malignancies in a screening population. MATERIALS AND METHODS: Fifty breast cancers detected at screening were analyzed by using a commercially available CAD system. Mean patient age was 62.2 years. Each set of mammograms (craniocaudal and mediolateral oblique views) was digitized and analyzed by the CAD system 10 times. One radiologist compared CAD output with the location of the malignancy at mammography and determined whether each lesion was marked accurately in one mammographic view, both views, or neither. Sensitivity and reproducibility of the CAD system were determined for both case- and image-based analysis. RESULTS: Overall sensitivity of the CAD system when at least one of the two mammographic views was marked correctly (case-base sensitivity) was 82.4%. Sensitivity when each mammographic view was considered separately (image-based sensitivity) was 61.1%. For case-based analysis, variability in true-positive CAD cues was demonstrated for 14 of 50 (28%) cases. For image-based analysis, inconsistency in CAD output was observed in 33 of 100 (33%) mammographic views that contained malignancies detected at screening. However, the CAD system consistently detected 40-43 of the 50 breast cancers in each of the 10 CAD runs. Variability for false-positive marks was significantly greater than that for true-positive marks. CONCLUSION: Inconsistency was demonstrated for CAD analysis of breast cancers detected at screening. However, the CAD system was reasonably consistent in the overall number of cancers identified from run to run. Greater variability of the CAD system was also demonstrated for false-positive marks, as compared with true-positive marks.

Authors
Baker, JA; Lo, JY; Delong, DM; Floyd, CE
MLA Citation
Baker, JA, Lo, JY, Delong, DM, and Floyd, CE. "Computer-aided detection in screening mammography: variability in cues." Radiology 233.2 (November 2004): 411-417.
PMID
15358850
Source
pubmed
Published In
Radiology
Volume
233
Issue
2
Publish Date
2004
Start Page
411
End Page
417
DOI
10.1148/radiol.2332031200

Accuracy of MRI in the detection of residual breast cancer after neoadjuvant chemotherapy

Authors
Rosen, EL; Blackwell, KL; Baker, JA; Orel, SG
MLA Citation
Rosen, EL, Blackwell, KL, Baker, JA, and Orel, SG. "Accuracy of MRI in the detection of residual breast cancer after neoadjuvant chemotherapy." Breast Diseases 15.2 (2004): 140-142.
Source
scival
Published In
Breast Diseases: A Year Book Quarterly
Volume
15
Issue
2
Publish Date
2004
Start Page
140
End Page
142

Accuracy of a collagen-plug biopsy site marking device deployed after stereotactic core needle breast biopsy.

OBJECTIVE: The goal of this study was to compare the accuracy of clip placement of a collagen-plug biopsy marking device with that of the more conventional, previously evaluated metallic tissue-marking clips. SUBJECTS AND METHODS. The placement accuracy of 31 collagen-plug marking devices was compared with the placement accuracy of 43 metallic marker clips deployed at biopsies performed between August 1, 2002, and November 20, 2002. The precision of marker placement was assessed by determining the position of the clip relative to the targeted mammographic lesion. Statistical analysis comparing the distance from the clip to the targeted lesion was performed. RESULTS: Using a two-group Wilcoxon's rank sum test, we found the clip-to-target distances for the collagen-plug central titanium marker were significantly different from the clip-to-target distances of the conventional metallic marker clips (p = 0.04). There were significantly fewer cases in which the clip-to-target distance was 1 cm or greater on at least one mammographic projection with the collagen-plug marker (5/31) than with the conventional metallic marker clip (19/43) (chi-square test, p = 0.02). CONCLUSION: The collagen-plug marking device is an effective alternative to existing marker clips, and use of this device may result in fewer cases in which the marker clip is substantially displaced (> or = 1 cm) away from the actual biopsy site.

Authors
Rosen, EL; Baker, JA; Soo, MS
MLA Citation
Rosen, EL, Baker, JA, and Soo, MS. "Accuracy of a collagen-plug biopsy site marking device deployed after stereotactic core needle breast biopsy." AJR Am J Roentgenol 181.5 (November 2003): 1295-1299.
PMID
14573422
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
181
Issue
5
Publish Date
2003
Start Page
1295
End Page
1299
DOI
10.2214/ajr.181.5.1811295

Accuracy of MRI in the detection of residual breast cancer after neoadjuvant chemotherapy.

OBJECTIVE: This study was undertaken to evaluate the ability of MRI to accurately show residual primary breast malignancy in women treated with neoadjuvant chemotherapy. MATERIALS AND METHODS: Twenty-one patients with locally advanced primary breast carcinoma underwent contrast-enhanced MRI before and after treatment with neoadjuvant anthracycline-based chemotherapy. For each patient, the maximum extent of the MRI abnormality was measured both before and after treatment. These measurements were subsequently compared with physical examination findings and histologic results to determine the ability of MRI to accurately reveal tumor extent after neoadjuvant chemotherapy. RESULTS: MRI after chemotherapy showed a correlation coefficient of 0.75 with histology, which was better than physical examination (r = 0.61). MRI underestimated the extent of residual tumor in two patients by more than 1 cm (including one false-negative examination), was within 1 cm in 12 of 21 patients, and overestimated tumor extent by more than 1 cm in seven of 21 patients. CONCLUSION: MRI can show residual malignancy after neoadjuvant chemotherapy better than physical examination, particularly in patients who have not had a complete clinical response to therapy.

Authors
Rosen, EL; Blackwell, KL; Baker, JA; Soo, MS; Bentley, RC; Yu, D; Samulski, TV; Dewhirst, MW
MLA Citation
Rosen, EL, Blackwell, KL, Baker, JA, Soo, MS, Bentley, RC, Yu, D, Samulski, TV, and Dewhirst, MW. "Accuracy of MRI in the detection of residual breast cancer after neoadjuvant chemotherapy." AJR Am J Roentgenol 181.5 (November 2003): 1275-1282.
PMID
14573420
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
181
Issue
5
Publish Date
2003
Start Page
1275
End Page
1282
DOI
10.2214/ajr.181.5.1811275

Computer-aided detection (CAD) in screening mammography: sensitivity of commercial CAD systems for detecting architectural distortion.

OBJECTIVE: Computer-aided detection (CAD) algorithms have successfully revealed breast masses and microcalcifications on screening mammography. The purpose of our study was to evaluate the sensitivity of commercially available CAD systems for revealing architectural distortion, the third most common appearance of breast cancer. MATERIALS AND METHODS: Two commercially available CAD systems were used to evaluate screening mammograms obtained in 43 patients with 45 mammographically detected regions of architectural distortion. For each CAD system, we determined the sensitivity for revealing architectural distortion on at least one image of the two-view mammographic examination (case sensitivity) and for each individual mammogram (image sensitivity). Surgical biopsy results were available for each case of architectural distortion. RESULTS: Architectural distortion was deemed present and actionable by a panel of expert breast imagers in 80 views of the 45 cases. One CAD system detected distortion in 22 of 45 cases of distortion (case sensitivity, 49%) and in 30 of 80 mammograms (image sensitivity, 38%); it displayed 0.7 false-positive marks per image. Another CAD system identified distortion in 15 of 45 cases (case sensitivity, 33%) and 17 of 80 mammograms (image sensitivity, 21%); it displayed 1.27 false-positive marks per image. Sensitivity for malignancy-caused distortion was similar to or lower than sensitivity for all causes of distortion. CONCLUSION: Fewer than one half of the cases of architectural distortion were detected by the two most widely available CAD systems used for interpretations of screening mammograms. Considerable improvement in the sensitivity of CAD systems is needed for detecting this type of lesion. Practicing breast imagers who use CAD systems should remain vigilant for architectural distortion.

Authors
Baker, JA; Rosen, EL; Lo, JY; Gimenez, EI; Walsh, R; Soo, MS
MLA Citation
Baker, JA, Rosen, EL, Lo, JY, Gimenez, EI, Walsh, R, and Soo, MS. "Computer-aided detection (CAD) in screening mammography: sensitivity of commercial CAD systems for detecting architectural distortion." AJR Am J Roentgenol 181.4 (October 2003): 1083-1088.
PMID
14500236
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
181
Issue
4
Publish Date
2003
Start Page
1083
End Page
1088
DOI
10.2214/ajr.181.4.1811083

Sonographic detection and sonographically guided biopsy of breast microcalcifications.

OBJECTIVE: The purpose of this study was to evaluate the ability of sonography to depict and guide biopsies of mammographically suspicious microcalcifications and to reveal the mammographic features and histologic outcomes of lesions amenable to sonographically guided biopsy. SUBJECTS AND METHODS: . Suspicious clusters of microcalcifications without other mammographic abnormalities were evaluated on sonography before biopsy and divided into two groups: those with and those without microcalcifications seen on sonography. Sonographically detected lesions underwent sonographically guided biopsy; lesions not seen on sonography underwent mammographically guided biopsy. Imaging features and histologies were correlated, and the positive predictive value of sonography was determined. RESULTS: Of 111 lesions (105 patients), 26 lesions (23%) were identified and underwent sonographically guided biopsy; 85 lesions (77%) were not identified sonographically. The diameters of microcalcification clusters in the sonographically identified group were significantly larger (p = 0.0005) and contained larger numbers of microcalcification particles (p = 0.038) compared with clusters not identified sonographically. Sonographically identified lesions were seen as masses (77%) or dilated ducts (23%) with echogenic foci. Sonographically identified lesions were more likely to be malignant than those not seen on sonography (69% vs 21%, respectively; p < 0.00002). Of 38 malignant lesions, those visible on sonography were more likely to be invasive than those not seen on sonography (72% vs 28%, respectively; p = 0.018). In malignant lesions undergoing core biopsy and surgical excision, the extent of disease was underestimated less with sonographically guided biopsy (7%, 1/15) than with stereotactic biopsy (33%, 5/15). CONCLUSION: Suspicious microcalcifications are seen infrequently on sonography (23%) but, when detected, can be successfully biopsied with sonographic guidance and more frequently are malignant and represent invasive cancer than those seen on mammography alone.

Authors
Soo, MS; Baker, JA; Rosen, EL
MLA Citation
Soo, MS, Baker, JA, and Rosen, EL. "Sonographic detection and sonographically guided biopsy of breast microcalcifications." AJR Am J Roentgenol 180.4 (April 2003): 941-948.
PMID
12646433
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
180
Issue
4
Publish Date
2003
Start Page
941
End Page
948
DOI
10.2214/ajr.180.4.1800941

A clinical study of adaptive beamforming using time-delay adjustments on a 1-D array

Time-delay estimation is made using echoes from a user-selected target region, to which the transmit focus is applied to maximize signal coherence. The estimated time-delay profile is split into 2 components using a least-squares fitting: one component indic ates an effective speed of sound, while the other is the residual time -delay error. On subsequent transmit and receive beamforming, the compensation can be made using the first component through modifying normal beamforming calculations, or, in addition, with the second component applied as well. These modifications were made in near real-time on the Elegra™, and were used to perform breast scanning on 7 patients. Images from the clinical scanning will be presented, along with the corresponding channel data and the estimated time-delay profiles. The results indicate that the compensation scheme resulted in significant improvement in image quality in some cases, while in some other cases, the effect is weak or unstable. One of the causes is that the selected target region may contain a cluster of a few strong scatterers and exhibit complex scattering signatures that are mistaken as propagation distortion. Other causes include the isoplanatic patch size, the elevation dimension of each array element, and the limitation of time -delay correction. These causes will be demonstrated using data obtained from clinical scanning and phantom measurements.

Authors
Liu, D-LD; Baker, JA; Behren, PV
MLA Citation
Liu, D-LD, Baker, JA, and Behren, PV. "A clinical study of adaptive beamforming using time-delay adjustments on a 1-D array." Proceedings of the IEEE Ultrasonics Symposium 1 (2003): 339-342.
Source
scival
Published In
Proceedings of the IEEE Ultrasonics Symposium
Volume
1
Publish Date
2003
Start Page
339
End Page
342

Imaging-guided core needle biopsy of papillary lesions of the breast.

OBJECTIVE: Our objective was to assess the incidence of papillary lesions of the breast diagnosed at imaging-guided core needle biopsy and the need for surgical excision after a benign diagnosis. MATERIALS AND METHODS: This retrospective study included 1374 patients with consecutive suspicious breast lesions that underwent either mammography or sonographically guided large-core needle breast biopsy. Fifty-seven lesions (4%) were classified as papillary lesions. Eleven of the 57 cases were lost to follow-up (n = 6) or had not yet shown 2 years of stability (n = 5) and were excluded from this study. The remaining 46 papillary lesions constitute our study population. RESULTS: Surgical excision was performed in 17 (37%) of 46 papillary lesions. In the group of patients whose lesions were recommended for excision because carcinoma was identified at core biopsy, surgical excision revealed one false-positive and two true-positive diagnoses. In four cases, histologic diagnoses of the excisional biopsy and the core needle biopsy were discordant. One false-positive finding at core needle biopsy initially was interpreted as invasive ductal carcinoma on the basis of core needle biopsy specimens. In three false-negative findings, the initial diagnosis at core needle biopsy was upgraded after surgical excision. Two cases of papilloma with adjacent atypical ductal hyperplasia and one of atypical papilloma were upgraded to ductal carcinoma in situ after surgical excision. Imaging follow-up was performed in the remaining 29 patients. All lesions were stable or had decreased in size during the 2-year follow-up period. The negative predictive value of core needle biopsy for excluding malignancy among the papillary lesions diagnosed in our study was 93%. CONCLUSION: When the histologic diagnosis is benign, our data suggest that papillary lesions may be safely managed with imaging follow-up rather than with surgical excision. However, atypical papillary lesions or those associated with atypia require surgical excision because histologic underestimation occurs at a frequency similar to that in other atypical lesions undergoing core needle biopsy.

Authors
Rosen, EL; Bentley, RC; Baker, JA; Soo, MS
MLA Citation
Rosen, EL, Bentley, RC, Baker, JA, and Soo, MS. "Imaging-guided core needle biopsy of papillary lesions of the breast." AJR Am J Roentgenol 179.5 (November 2002): 1185-1192.
PMID
12388496
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
179
Issue
5
Publish Date
2002
Start Page
1185
End Page
1192
DOI
10.2214/ajr.179.5.1791185

Interpretation of digital mammograms: comparison of speed and accuracy of soft-copy versus printed-film display.

PURPOSE: To compare the speed and accuracy of the interpretations of digital mammograms by radiologists by using printed-film versus soft-copy display. MATERIALS AND METHODS: After being trained in interpretation of digital mammograms, eight radiologists interpreted 63 digital mammograms, all with old studies for comparison. All studies were interpreted by all readers in soft-copy and printed-film display, with interpretations of images in the same cases at least 1 month apart. Mammograms were interpreted in cases that included six biopsy-proved cancers and 20 biopsy-proved benign lesions, 20 cases of probably benign findings in patients who underwent 6-month follow-up, and 17 cases without apparent findings. Area under the receiver operating characteristic curve (A(z)), sensitivity, and specificity were calculated for soft-copy and printed-film display. RESULTS: There was no significant difference in the speed of interpretation, but interpretations with soft-copy display were slightly faster. The differences in A(z), sensitivity, and specificity were not significantly different; A(z) and sensitivity were slightly better for interpretations with printed film, and specificity was slightly better for interpretations with soft copy. CONCLUSION: Interpretation with soft-copy display is likely to be useful with digital mammography and is unlikely to significantly change accuracy or speed.

Authors
Pisano, ED; Cole, EB; Kistner, EO; Muller, KE; Hemminger, BM; Brown, ML; Johnston, RE; Kuzmiak, CM; Braeuning, MP; Freimanis, RI; Soo, MS; Baker, JA; Walsh, R
MLA Citation
Pisano, ED, Cole, EB, Kistner, EO, Muller, KE, Hemminger, BM, Brown, ML, Johnston, RE, Kuzmiak, CM, Braeuning, MP, Freimanis, RI, Soo, MS, Baker, JA, and Walsh, R. "Interpretation of digital mammograms: comparison of speed and accuracy of soft-copy versus printed-film display." Radiology 223.2 (May 2002): 483-488.
PMID
11997557
Source
pubmed
Published In
Radiology
Volume
223
Issue
2
Publish Date
2002
Start Page
483
End Page
488
DOI
10.1148/radiol.2232010704

Malignant lesions initially subjected to short-term mammographic follow-up.

PURPOSE: To determine whether systematically evaluated criteria for probably benign lesions were actually applied to lesions placed into that category. MATERIALS AND METHODS: A search of the mammography database yielded 295 cases that were initially followed up with short-term interval mammography but eventually received a biopsy recommendation for the same breast. Of the 83 malignancies (81 patients) for which mammograms and pathology reports were available for review, 51 malignancies corresponded to the lesions for which short-term follow-up was recommended. Each case was retrospectively reviewed to determine whether the lesion followed up represented the subsequently diagnosed malignancy. Each lesion was characterized with appropriate Breast Imaging Reporting and Data System descriptors, based on the mammographic imaging available when short-term follow-up was first recommended. These characteristics were then used to determine if, in retrospect, the mammographic appearance met previously published criteria for probably benign lesions. RESULTS: Of the 51 malignancies, 23 (45%) appeared mammographically as microcalcifications, 12 (24%) as masses, four (8%) as architectural distortion, and 12 (24%) as developing densities. None fulfilled strict criteria for a probably benign lesion when reviewed in retrospect. Forty-seven (92%) of 51 lesions had already demonstrated progression at the time of follow-up recommendation. CONCLUSION: Short-term mammographic follow-up is often recommended for lesions that, in retrospect, do not fulfill established diagnostic criteria for probably benign lesions.

Authors
Rosen, EL; Baker, JA; Soo, MS
MLA Citation
Rosen, EL, Baker, JA, and Soo, MS. "Malignant lesions initially subjected to short-term mammographic follow-up." Radiology 223.1 (April 2002): 221-228.
PMID
11930070
Source
pubmed
Published In
Radiology
Volume
223
Issue
1
Publish Date
2002
Start Page
221
End Page
228
DOI
10.1148/radiol.2231011355

Sonographically guided biopsy of suspicious microcalcifications of the breast: a pilot study.

OBJECTIVE: The purpose of this study is to evaluate the use of sonographic guidance for biopsy of mammographically detected suspicious microcalcifications. SUBJECTS AND METHODS: Twenty-three patients with suspicious microcalcifications detected on mammography (15 associated with masses or distortion; eight with microcalcifications alone) underwent sonographically guided core biopsy (n = 18) or sonographically guided needle localization before excision (n = 5). Microcalcifications were targeted, and specimen radiographs were obtained for each lesion, with the success of the procedure based on identifying microcalcifications on the specimen radiograph. For core biopsies, the number of cores obtained was compared with that in 49 control patients who underwent sonographically guided core biopsy of noncalcified masses. RESULTS: All 23 lesions (100%) were successfully biopsied under sonographic guidance, with microcalcifications seen on specimen radiographs in each case. Of 18 core biopsies, a mean of 8.7 cores was obtained compared with a mean of 5.5 cores in the control group (p<0.0001). Of 13 lesions sampled with core biopsy that subsequently underwent surgical excision, three (23%) were upgraded from atypical ductal hyperplasia to ductal carcinoma in situ (n = 1) and from ductal carcinoma in situ to invasive carcinoma (n = 2). Mammographically, most lesions contained more than 15 pleomorphic microcalcifications. On sonography, echogenic foci corresponded to microcalcifications in all but two cases in which broader echogenic regions were seen. When no mass or distortion was visible on mammography, sonography showed a mass or dilated ducts with internal echogenic foci. CONCLUSION: Microcalcifications identifiable on sonography can be successfully biopsied under sonographic guidance. Further study is necessary to determine whether targeting microcalcifications seen sonographically in the mass or duct can improve the rate of underestimation of disease compared with stereotactic core biopsy.

Authors
Soo, MS; Baker, JA; Rosen, EL; Vo, TT
MLA Citation
Soo, MS, Baker, JA, Rosen, EL, and Vo, TT. "Sonographically guided biopsy of suspicious microcalcifications of the breast: a pilot study." AJR Am J Roentgenol 178.4 (April 2002): 1007-1015.
PMID
11906892
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
178
Issue
4
Publish Date
2002
Start Page
1007
End Page
1015
DOI
10.2214/ajr.178.4.1781007

Breast US: assessment of technical quality and image interpretation.

PURPOSE: To determine whether ultrasonography (US) of the breast performed at a wide range of clinical practices conforms to the American College of Radiology (ACR) standards for quality and to assess the interpretations of breast sonograms. MATERIALS AND METHODS: Static images from 152 breast US examinations performed at 86 institutions were evaluated for compliance with ACR guidelines for breast US hardware, technical factors, imaging protocol, and image annotation. Official interpretations submitted by the referring facilities were compared with static images submitted by the facility. Discrepancies were confirmed by two dedicated breast radiologists after repeat imaging, short-interval follow-up imaging, or biopsy. RESULTS: A total of 60.5% of cases did not comply with at least one ACR guideline on breast US and included 9.2% of cases with inadequate equipment, 14.7% of cases with inappropriate focal zone placement, at least 14% of cases with static images in only one imaging plane, and 25% of cases with incomplete patient identifiers. Clinically relevant interpretation errors and interpretation discrepancies were confirmed in 23 (15.1%) of 152 cases. CONCLUSION: The majority of breast US examinations did not comply with at least some of the standards for quality set forth by the ACR. Attention to these basic standards could substantially improve image quality.

Authors
Baker, JA; Soo, MS
MLA Citation
Baker, JA, and Soo, MS. "Breast US: assessment of technical quality and image interpretation." Radiology 223.1 (April 2002): 229-238.
PMID
11930071
Source
pubmed
Published In
Radiology
Volume
223
Issue
1
Publish Date
2002
Start Page
229
End Page
238
DOI
10.1148/radiol.2231011125

Cross-institutional evaluation of BI-RADS predictive model for mammographic diagnosis of breast cancer.

OBJECTIVE: Given a predictive model for identifying very likely benign breast lesions on the basis of Breast Imaging Reporting and Data System (BI-RADS) mammographic findings, this study evaluated the model's ability to generalize to a patient data set from a different institution. MATERIALS AND METHODS: The artificial neural network model underwent three trials: it was optimized over 500 biopsy-proven lesions from Duke University Medical Center or "Duke," evaluated on 1,000 similar cases from the University of Pennsylvania Health System or "Penn," and reoptimized for Penn. RESULTS: Trial A's Duke-only model yielded 98% sensitivity, 36% specificity, area index (A(z)) of 0.86, and partial A(z) of 0.51. The cross-institutional trial B yielded 96% sensitivity, 28% specificity, A(z) of 0.79, and partial A(z) of 0.28. The decreases were significant for both A(z) (p = 0.017) and partial A(z) (p < 0.001). In trial C, the model reoptimized for the Penn data yielded 96% sensitivity, 35% specificity, A(z) of 0.83, and partial A(z) of 0.32. There were no significant differences compared with trial B for specificity (p = 0.44) or partial A(z) (p = 0.46), suggesting that the Penn data were inherently more difficult to characterize. CONCLUSION: The BI-RADS lexicon facilitated the cross-institutional test of a breast cancer prediction model. The model generalized reasonably well, but there were significant performance decreases. The cross-institutional performance was encouraging because it was not significantly different from that of a reoptimized model using the second data set at high sensitivities. This study indicates the need for further work to collect more data and to improve the robustness of the model.

Authors
Lo, JY; Markey, MK; Baker, JA; Floyd, CE
MLA Citation
Lo, JY, Markey, MK, Baker, JA, and Floyd, CE. "Cross-institutional evaluation of BI-RADS predictive model for mammographic diagnosis of breast cancer." AJR Am J Roentgenol 178.2 (February 2002): 457-463.
PMID
11804918
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
178
Issue
2
Publish Date
2002
Start Page
457
End Page
463
DOI
10.2214/ajr.178.2.1780457

Negative predictivevalue of breast imaging in patients with palpable lesions [3] (multiple letters)

Authors
Hall, FM; Soo, MS; Rosen, EL; Baker, JA
MLA Citation
Hall, FM, Soo, MS, Rosen, EL, and Baker, JA. "Negative predictivevalue of breast imaging in patients with palpable lesions [3] (multiple letters)." American Journal of Roentgenology 179.4 (2002): 1073-1074.
PMID
12239070
Source
scival
Published In
American Journal of Roentgenology
Volume
179
Issue
4
Publish Date
2002
Start Page
1073
End Page
1074

Negative predictive value of sonography with mammography in patients with palpable breast lesions.

OBJECTIVE: This study was performed to determine the negative predictive value of sonography with mammography in evaluating palpable breast lesions. MATERIALS AND METHODS: Four hundred twenty patients with 455 palpable breast lesions were retrospectively identified from our mammography database as having negative mammographic and sonographic results. For patients diagnosed with breast cancer, images and medical records were reviewed to determine whether the palpable lesion evaluated on sonography and mammography corresponded to the patient's breast cancer. On the basis of the number of breast cancers that correlated to the palpable areas imaged, the negative predictive value of sonography with mammography was determined. RESULTS: Sixty-two of the 420 patients in the study group were already diagnosed with breast carcinoma, and eight new carcinomas were diagnosed during the study period. Only one of six ipsilateral cancers corresponded to a palpable lesion that had a negative imaging evaluation. This lesion was diagnosed as an invasive lobular cancer, hard and fixed at physical examination. Imaging and clinical follow-up of the remaining patients showed no abnormality at the sites of previously investigated palpable abnormalities. The mean imaging follow-up was 25 months. The negative predictive value of sonography and mammography in the setting of a palpable lesion was 99.8%. CONCLUSION: The negative predictive value of sonography with mammography is high, and together these imaging modalities can be reassuring if follow-up is planned when the physical examination is not highly suspicious. However, if the physical examination is suspicious, biopsy should not be delayed.

Authors
Soo, MS; Rosen, EL; Baker, JA; Vo, TT; Boyd, BA
MLA Citation
Soo, MS, Rosen, EL, Baker, JA, Vo, TT, and Boyd, BA. "Negative predictive value of sonography with mammography in patients with palpable breast lesions." AJR Am J Roentgenol 177.5 (November 2001): 1167-1170.
PMID
11641195
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
177
Issue
5
Publish Date
2001
Start Page
1167
End Page
1170
DOI
10.2214/ajr.177.5.1771167

Artifacts and pitfalls in sonographic imaging of the breast.

Authors
Baker, JA; Soo, MS; Rosen, EL
MLA Citation
Baker, JA, Soo, MS, and Rosen, EL. "Artifacts and pitfalls in sonographic imaging of the breast." AJR Am J Roentgenol 176.5 (May 2001): 1261-1266.
PMID
11312192
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
176
Issue
5
Publish Date
2001
Start Page
1261
End Page
1266
DOI
10.2214/ajr.176.5.1761261

The evolving role of sonography in evaluating solid breast masses.

Many investigators have attempted to use ultrasound imaging to differentiate benign from malignant solid breast masses. Studies have evaluated several generations of gray-scale imaging, Doppler, color Doppler, and power Doppler imaging, and several unconventional ultrasound techniques. Although various individual studies have shown promise, ultrasound criteria for avoiding biopsy of solid lesions have not been widely adopted. Considerable observer variability also remains an important obstacle. This article reviews the results, strengths, and weaknesses of some of the key studies addressing this issue. Fundamental criteria for a successful ultrasound model are also specified.

Authors
Baker, JA; Soo, MS
MLA Citation
Baker, JA, and Soo, MS. "The evolving role of sonography in evaluating solid breast masses." Semin Ultrasound CT MR 21.4 (August 2000): 286-296. (Review)
PMID
11014251
Source
pubmed
Published In
Seminars in Ultrasound, CT and MRI
Volume
21
Issue
4
Publish Date
2000
Start Page
286
End Page
296

Sonography of solid breast lesions: observer variability of lesion description and assessment.

OBJECTIVE: The purpose of this study was to measure the level of inter- and intraobserver agreement and to evaluate the causes of variability in radiologists' descriptions and assessments of sonograms of solid breast masses. MATERIALS AND METHODS: Sixty sonograms of solid masses were evaluated independently by five radiologists. Observers used the lexicon of a recently published benchmark report on sonographic appearances of breast masses to determine mass shape, margin, echogenicity, echo texture, presence of echogenic pseudocapsule, and acoustic transmission. Final diagnostic assessments were determined by applying the rule-based model of the same benchmark report to the radiologists' descriptions. In addition, one observer interpreted each case twice to evaluate intraobserver variability. Inter- and intraobserver variability were measured using Cohen's kappa statistic. We also investigated causes of variability in radiologists' descriptions. RESULTS: Interobserver agreement ranged from lowest for determining the presence of an echogenic pseudocapsule (kappa = .09) to highest for determining mass shape (kappa = .8). Intraobserver agreement was lowest for mass echo texture (kappa = .24) and greatest for mass shape (kappa = .79). Variability in descriptions of lesions contributed to interobserver (kappa = .51) and some intraobserver (kappa = .66) inconsistency in assessing the likelihood of malignancy. CONCLUSION: Lack of uniformity among observers' use of descriptive terms for solid breast masses resulted in inconsistent diagnoses. The need for improved definitions and additional illustrative examples could be addressed by developing a standardized lexicon similar to that of the Breast Imaging Reporting and Data System.

Authors
Baker, JA; Kornguth, PJ; Soo, MS; Walsh, R; Mengoni, P
MLA Citation
Baker, JA, Kornguth, PJ, Soo, MS, Walsh, R, and Mengoni, P. "Sonography of solid breast lesions: observer variability of lesion description and assessment." AJR Am J Roentgenol 172.6 (June 1999): 1621-1625.
PMID
10350302
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
172
Issue
6
Publish Date
1999
Start Page
1621
End Page
1625
DOI
10.2214/ajr.172.6.10350302

Sonographically guided percutaneous interventions of the breast using a steerable ultrasound beam.

Authors
Baker, JA; Soo, MS; Mengoni, P
MLA Citation
Baker, JA, Soo, MS, and Mengoni, P. "Sonographically guided percutaneous interventions of the breast using a steerable ultrasound beam." AJR Am J Roentgenol 172.1 (January 1999): 157-159.
PMID
9888759
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
172
Issue
1
Publish Date
1999
Start Page
157
End Page
159
DOI
10.2214/ajr.172.1.9888759

Effect of patient history data on the prediction of breast cancer from mammographic findings with artificial neural networks.

RATIONALE AND OBJECTIVES: The authors evaluated the contribution of medical history data to the prediction of breast cancer with artificial neural network (ANN) models based on mammographic findings. MATERIALS AND METHODS: Three ANNs were developed: The first used 10 Breast Imaging Reporting and Data System (BI-RADS) variables; the second, the BI-RADS variables plus patient age; the third, the BI-RADS variables, patient age, and seven other history variables, for a total of 18 inputs. Performance of the ANNs and the original radiologist's impression were evaluated with five metrics: receiver operating characteristic area index (Az); specificity at given sensitivities of 100%, 98%, and 95%; and positive predictive value. RESULTS: All three ANNs consistently outperformed the radiologist's impression over all five performance metrics. The patient-age variable was particularly valuable. Adding the age variable to the basic ANN model, which used only the BI-RADS findings, significantly improved Az (P = .028). In fact, replacing all history data with just the age variable resulted in virtually no changes for Az or specificity at 98% sensitivity (P = .324 and P = .410, respectively). CONCLUSION: Patient age was an important variable for the prediction of breast cancer from mammographic findings with the ANNs. For this data set, all history data could be replaced with age alone.

Authors
Lo, JY; Baker, JA; Kornguth, PJ; Floyd, CE
MLA Citation
Lo, JY, Baker, JA, Kornguth, PJ, and Floyd, CE. "Effect of patient history data on the prediction of breast cancer from mammographic findings with artificial neural networks." Acad Radiol 6.1 (January 1999): 10-15.
PMID
9891147
Source
pubmed
Published In
Academic Radiology
Volume
6
Issue
1
Publish Date
1999
Start Page
10
End Page
15

Prediction of breast biopsy outcomes from mammographic findings

Authors
Floyd, CE; Lo, JY; Baker, JA
MLA Citation
Floyd, CE, Lo, JY, and Baker, JA. "Prediction of breast biopsy outcomes from mammographic findings." COMPUTER-AIDED DIAGNOSIS IN MEDICAL IMAGING 1182 (1999): 193-200.
Source
wos-lite
Published In
International Congress Series
Volume
1182
Publish Date
1999
Start Page
193
End Page
200

Predictive model for the diagnosis of intraabdominal abscess.

RATIONALE AND OBJECTIVES: The authors investigated the use of an artificial neural network (ANN) to aid in the diagnosis of intraabdominal abscess. MATERIALS AND METHODS: An ANN was constructed based on data from 140 patients who underwent abdominal and pelvic computed tomography (CT) between January and December 1995. Input nodes included data from clinical history, physical examination, laboratory investigation, and radiographic study. The ANN was trained and tested on data from all 140 cases by using a round-robin method and was compared with linear discriminate analysis. A receiver operating characteristic curve was generated to evaluate both predictive models. RESULTS: CT examinations in 50 cases were positive for abscess. This finding was confirmed by means of laboratory culture of aspirations from CT-guided percutaneous drainage in 38 patients, ultrasound-guided percutaneous drainage in five patients, surgery in five patients, and characteristic appearance on CT scans without aspiration in two patients. CT scans in 90 cases were negative for abscess. The sensitivity and specificity of the ANN in predicting the presence of intraabdominal abscess were 90% and 51%, respectively. Receiver operating characteristic analysis showed no statistically significant difference in performance between the two predictive models. CONCLUSION: The ANN is a useful tool for determining whether an intraabdominal abscess is present. It can be used to set priorities for CT examinations in order to expedite treatment in patients believed to be more likely to have an abscess.

Authors
Freed, KS; Lo, JY; Baker, JA; Floyd, CE; Low, VH; Seabourn, JT; Nelson, RC
MLA Citation
Freed, KS, Lo, JY, Baker, JA, Floyd, CE, Low, VH, Seabourn, JT, and Nelson, RC. "Predictive model for the diagnosis of intraabdominal abscess." Acad Radiol 5.7 (July 1998): 473-479.
PMID
9653463
Source
pubmed
Published In
Academic Radiology
Volume
5
Issue
7
Publish Date
1998
Start Page
473
End Page
479

Predicting breast cancer invasion with artificial neural networks on the basis of mammographic features.

PURPOSE: To evaluate whether an artificial neural network (ANN) can predict breast cancer invasion on the basis of readily available medical findings (ie, mammographic findings classified according to the American College of Radiology Breast Imaging Reporting and Data System and patient age). MATERIALS AND METHODS: In 254 adult patients, 266 lesions that had been sampled at biopsy were randomly selected for the study. There were 96 malignant and 170 benign lesions. On the basis of nine mammographic findings and patient age, a three-layer backpropagation network was developed to predict whether the malignant lesions were in situ or invasive. RESULTS: The ANN predicted invasion among malignant lesions with an area under the receiver operating characteristic curve (Az) of .91 +/- .03. It correctly identified all 28 in situ cancers (specificity, 100%) and 48 of 68 invasive cancers (sensitivity, 71%). CONCLUSION: The ANN used mammographic features and patient age to accurately classify invasion among breast cancers, information that was previously available only by means of biopsy. This knowledge may assist in surgical planning and may help reduce the cost and morbidity of unnecessary biopsy.

Authors
Lo, JY; Baker, JA; Kornguth, PJ; Iglehart, JD; Floyd, CE
MLA Citation
Lo, JY, Baker, JA, Kornguth, PJ, Iglehart, JD, and Floyd, CE. "Predicting breast cancer invasion with artificial neural networks on the basis of mammographic features." Radiology 203.1 (April 1997): 159-163.
PMID
9122385
Source
pubmed
Published In
Radiology
Volume
203
Issue
1
Publish Date
1997
Start Page
159
End Page
163
DOI
10.1148/radiology.203.1.9122385

Fractal texture analysis in computer-aided diagnosis of solitary pulmonary nodules.

RATIONALE AND OBJECTIVES: The authors investigated the use of fractal texture characterization to improve the accuracy of solitary pulmonary nodule computer-aided diagnosis (CAD) systems. METHODS: Thirty chest radiographs were acquired from patients who had no pulmonary nodules. Thirty regions were selected that were considered remotely suspicious-looking for nodules. Artificial nodules of multiple shapes, sizes, and orientations were added at subtle levels of contrast to 30 non-suspicious-looking regions of the radiographs. Fractal dimensions of the 60 "nodule candidates" were calculated to quantify the texture of each region. Four radiologists also interpreted the images. RESULTS: The fractal dimension of each possible nodule provided statistically significant (P < .05) differentiation between regions that contained an artificial nodule and those that did not. The area under the receiver operating characteristic curve for the fractal analysis was significantly better (P < .05) than that for the radiologists. CONCLUSION: Fractal texture characterization provides useful information for the classification of potential solitary pulmonary nodules with CAD algorithms.

Authors
Vittitoe, NF; Baker, JA; Floyd, CE
MLA Citation
Vittitoe, NF, Baker, JA, and Floyd, CE. "Fractal texture analysis in computer-aided diagnosis of solitary pulmonary nodules." Acad Radiol 4.2 (February 1997): 96-101.
PMID
9061081
Source
pubmed
Published In
Academic Radiology
Volume
4
Issue
2
Publish Date
1997
Start Page
96
End Page
101

Breast imaging reporting and data system standardized mammography lexicon: observer variability in lesion description.

OBJECTIVE: The American College of Radiology has recommended the Breast Imaging Reporting and Data System (BI-RADS) as a standardized scheme for describing mammographic lesions. The objective of this study was to measure inter- and intraobserver variabilities of radiologists' descriptions of mammographic lesions with the BI-RADS standardized lexicon. MATERIALS AND METHODS: Sixty mammographic studies with abnormal findings were independently evaluated by five radiologists. Readers described each lesion by selecting a single term from the BI-RADS lexicon for each of eight morphologic categories: calcification distribution, number, and description; mass margin, shape, and density; associated findings; and special cases. Additionally, each reader assessed the significance of each lesion on a five-point scale. One observer read each case twice. Inter- and intraobserver variabilities for each description and interpretation category of the BI-RADS lexicon were determined with Cohen's kappa statistic. Radiologists' specific use of calcification descriptors was evaluated in detail. RESULTS: Substantial agreement was observed between readers for choosing terms to describe masses and calcifications (kappa value range, 0.50 +/- 0.02-0.77 +/- 0.03). Intraobserver agreement for these categories was similar (kappa value range, 0.57 +/- 0.07-0.84 +/- 0.09). Considerable inter- and intraobserver variabilities were noted for the "associated findings" and "special cases" categories (kappa value range, -0.02 +/- 0.14-0.38 +/- 0.12), a result that in part reflected the small number of cases to which these categories were assigned. Moderate interobserver variability and little intraobserver variability in the interpretation of lesion significance were noted when an assessment classification similar to that of BI-RADS was used. Use of terms to describe calcifications did not always conform to BI-RADS-defined levels of suspicion. CONCLUSION: BI-RADS is moderately successful in providing a standardized language for physicians to describe lesion morphology. Efforts to reevaluate specific terms and the diagnostic significance assigned to calcification descriptors may prove useful in maintaining the promise of improved quality with the BI-RADS standardized mammography lexicon.

Authors
Baker, JA; Kornguth, PJ; Floyd, CE
MLA Citation
Baker, JA, Kornguth, PJ, and Floyd, CE. "Breast imaging reporting and data system standardized mammography lexicon: observer variability in lesion description." AJR Am J Roentgenol 166.4 (April 1996): 773-778.
PMID
8610547
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
166
Issue
4
Publish Date
1996
Start Page
773
End Page
778
DOI
10.2214/ajr.166.4.8610547

Artificial neural network: improving the quality of breast biopsy recommendations.

PURPOSE: To evaluate the performance and inter- and intraobserver variability of an artificial neural network (ANN) for predicting breast biopsy outcome. MATERIALS AND METHODS: Five radiologists described 60 mammographically detected lesions with the American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) nomenclature. A previously programmed ANN used the BI-RADS descriptors and patient histories to predict biopsy results. ANN predictive performance was compared with the clinical decision to perform biopsy. Inter- and intraobserver variability of radiologists' interpretations and ANN predictions were evaluated with Cohen kappa analysis. RESULTS: The ANN maintained 100% sensitivity (23 of 23 cancers) while improving the positive predictive value of biopsy results from 38% (23 of 60 lesions) to between 58% (23 of 40 lesions) and 66% (23 of 35 lesions; P < .001). Interobserver variability for interpretation of the lesions was significantly reduced by the ANN (P < .001); there was no statistically significant effect on nearly perfect intraobserver reproducibility. CONCLUSION: Use of an ANN with radiologists' descriptions of abnormal findings may improve interpretation of mammographic abnormalities.

Authors
Baker, JA; Kornguth, PJ; Lo, JY; Floyd, CE
MLA Citation
Baker, JA, Kornguth, PJ, Lo, JY, and Floyd, CE. "Artificial neural network: improving the quality of breast biopsy recommendations." Radiology 198.1 (January 1996): 131-135.
PMID
8539365
Source
pubmed
Published In
Radiology
Volume
198
Issue
1
Publish Date
1996
Start Page
131
End Page
135
DOI
10.1148/radiology.198.1.8539365

Computer-aided diagnosis of mammography using an artificial neural network: Predicting the invasiveness of breast cancers from image features

The study aimed to develop an artificial neural network (ANN) for computer-aided diagnosis of mammography. Using 9 mammographic image features and patient age, the ANN predicted whether breast lesions were benign, invasive malignant, or noninvasive malignant. Given only 97 malignant patients, the 3-layer backpropagation ANN successfully predicted the invasiveness of those breast cancers, performing with Az of 0.88 ± 0.03. To determine more generalized clinical performance, a different ANN was developed using 266 consecutive patients (97 malignant, 169 benign). This ANN predicted whether those patients were benign or noninvasive malignant vs. invasive malignant with Az of 0.86 ± 0.03. This study is unique because it is the first to predict the invasiveness of breast cancers using mammographic features and age. This knowledge, which was previously available only through surgical biopsy, may assist in the planning of surgical procedures for patients with breast lesions, and may help reduce the cost and morbidity associated with unnecessary surgical biopsies.

Authors
Lo, JY; Kim, J; Baker, JA; Jr, CEF
MLA Citation
Lo, JY, Kim, J, Baker, JA, and Jr, CEF. "Computer-aided diagnosis of mammography using an artificial neural network: Predicting the invasiveness of breast cancers from image features." Proceedings of SPIE - The International Society for Optical Engineering 2710 (1996): 725-732.
Source
scival
Published In
Proceedings of SPIE - The International Society for Optical Engineering
Volume
2710
Publish Date
1996
Start Page
725
End Page
732
DOI
10.1117/12.237977

Use of genetic algorithms for computer-aided diagnosis of breast cancers from image features

Purpose: In this investigation we have explored genetic algorithms as a technique to train the weights in a feed forward neural network designed to predict breast cancer based on mammographic findings and patient history. Methods: Mammograms were obtained from 206 patients who obtained breast biopsies. Mammographic findings were recorded by radiologists for each patient. In addition, the outcome of the biopsy was recorded. Of the 206 cases, 73 were malignant while 133 were benign at the time of biopsy. A genetic algorithm (GA) was developed to adjust the weights of an artificial neural network (ANN) so that the ANN would output the outcome of the biopsy when the mammographic findings were given as inputs. The GA is a technique for function optimization that reflects biological genetic evolution. The ANN was a fully connected feed-forward network using a sigmoid activation with 11 inputs, one hidden layer with 10 nodes, and one output node (benign/malignant). The GA approach allows much flexibility in selecting the function to be optimized. In this work both mean-squared error (MSE) and receiver operating characteristic (ROC) curve area (Az) were explored as optimization criteria. The system was trained using a bootstrap sampling. Results: Optimizing for the two criteria result in different solutions. The "best" solution was obtained by minimizing a linear combination of MSE and (1-Az). ROC areas were 0.82 +/- 0.07, somewhat less than those obtained using backpropagation for ANN training: 0.90 +/- 0.05. New or breakthrough work: This is the first description of a genetic algorithm for breast cancer diagnosis. The novel advantage of this technique is the ability to optimize the system for maximizing ROC area rather than minimizing mean squared error. Conclusions: A new technique for computer-aided diagnosis of breast cancer has been explored. The flexibility of the GA approach allows optimization of cost functions that have relevance to breast cancer prediction.

Authors
Jr, CEF; Tourassi, GD; Baker, JA
MLA Citation
Jr, CEF, Tourassi, GD, and Baker, JA. "Use of genetic algorithms for computer-aided diagnosis of breast cancers from image features." Proceedings of SPIE - The International Society for Optical Engineering 2710 (1996): 51-58.
Source
scival
Published In
Proceedings of SPIE - The International Society for Optical Engineering
Volume
2710
Publish Date
1996
Start Page
51
End Page
58
DOI
10.1117/12.237973

Selenium-based digital radiography of the chest: radiologists' preference compared with film-screen radiographs.

OBJECTIVE: A new digital thoracic radiography system (Thoravision; Philips Medical Systems, Hamburg, Germany), which uses selenium as a detector material, was evaluated for observer preference. The system has been shown to have higher detection efficiency than conventional film-screen systems and thus could provide an image with reduced noise. The hypothesis tested in this study was that the selenium-based digital system would provide an image appearance for conventional thoracic imaging that would be equal or superior to that provided by a conventional film-screen system. MATERIALS AND METHODS: Fifty-three patient volunteers were imaged at 120 kV with both the selenium-based system and a thoracic film-screen combination system (InSight HC; Kodak, Rochester, NY). Posteroanterior and lateral images were acquired with both systems, for a total of 212 images. Both imaging systems included a stationary 12:1 antiscatter grid. Exposures were the same for both imaging systems, and the digital images were printed to film. Images for the same patient were compared by six observers--three specialized chest radiologists and three general radiologists. Images included both normal chest radiographs and radiographs with abnormal findings. Each pair of images was ranked on a scale from 1 to 5 for preference of technique, with a score of 3 indicating no preference. Eleven anatomic features were evaluated in the posteroanterior views, and six features were evaluated in the lateral views. Statistical significance of preference was evaluated with Student's t test. RESULTS: The chest radiologists had a statistically significant preference for the selenium-based system for all 17 features (p < .001). The general radiologists had a statistically significant preference for the selenium-based system for visualization of 10 of the 17 features (p < .05). Neither group had a statistically significant preference for the conventional images in any category. CONCLUSION: The selenium-based system provided an image appearance that was significantly preferred by all radiologists, more strongly by those specializing in chest radiography. This study demonstrates that a digital thoracic imaging system can routinely produce images that are perceived as equal or superior to conventional images.

Authors
Floyd, CE; Baker, JA; Chotas, HG; Delong, DM; Ravin, CE
MLA Citation
Floyd, CE, Baker, JA, Chotas, HG, Delong, DM, and Ravin, CE. "Selenium-based digital radiography of the chest: radiologists' preference compared with film-screen radiographs." AJR Am J Roentgenol 165.6 (December 1995): 1353-1358.
PMID
7484562
Source
pubmed
Published In
AJR. American journal of roentgenology
Volume
165
Issue
6
Publish Date
1995
Start Page
1353
End Page
1358
DOI
10.2214/ajr.165.6.7484562

Computer-aided diagnosis of breast cancer: artificial neural network approach for optimized merging of mammographic features.

RATIONALE AND OBJECTIVES: An artificial neural network (ANN) approach was developed for the computer-aided diagnosis of mammography using an optimally minimized number of input features. METHODS: A backpropagation ANN merged nine input features (age plus eight radiographic findings extracted by radiologists) to predict biopsy outcome as its output. The features were ranked, and more important ones were selected to produce an optimal subset of features. RESULTS: Given all nine features, the ANN performed with a receiver operator characteristic area under the curve (Az) of .95 +/- .01. Given only the four most important features, the ANN performed with an Az of .96 +/- .01. Although not significantly better than the ANN with all nine features, the ANN with the four optimized features was significantly better than expert radiologists' Az of .90 +/- .02 (p = .01). This four-feature ANN had a 95% sensitivity and an 81% specificity. For cases with calcifications, the radiologists' performance dropped to an Az of .85 +/- .04, whereas a specialized three-feature ANN performed significantly better with an Az of .95 +/- .02 (p = .02). CONCLUSION: Given only four input features, the ANN predicted biopsy outcome significantly better than did expert radiologists, who also had access to other radiographic and nonradiographic data. The reduced number of features would substantially decrease data entry efforts and potentially improve the ANN's general applicability.

Authors
Lo, JY; Baker, JA; Kornguth, PJ; Floyd, CE
MLA Citation
Lo, JY, Baker, JA, Kornguth, PJ, and Floyd, CE. "Computer-aided diagnosis of breast cancer: artificial neural network approach for optimized merging of mammographic features." Acad Radiol 2.10 (October 1995): 841-850.
PMID
9419649
Source
pubmed
Published In
Academic Radiology
Volume
2
Issue
10
Publish Date
1995
Start Page
841
End Page
850

Breast cancer: prediction with artificial neural network based on BI-RADS standardized lexicon.

PURPOSE: To determine if an artificial neural network (ANN) to categorize benign and malignant breast lesions can be standardized for use by all radiologists. MATERIALS AND METHODS: An ANN was constructed based on the standardized lexicon of the Breast Imaging Recording and Data System (BI-RADS) of the American College of Radiology. Eighteen inputs to the network included 10 BI-RADS lesion descriptors and eight input values from the patient's medical history. The network was trained and tested on 206 cases (133 benign, 73 malignant cases). Receiver operating characteristic curves for the network and radiologists were compared. RESULTS: At a specified output threshold, the ANN would have improved the positive predictive value (PPV) of biopsy from 35% to 61% with a relative sensitivity of 100%. At a fixed sensitivity of 95%, the specificity of the ANN (62%) was significantly greater than the specificity of radiologists (30%) (P < .01). CONCLUSION: The BI-RADS lexicon provides a standardized language between mammographers and an ANN that can improve the PPV of breast biopsy.

Authors
Baker, JA; Kornguth, PJ; Lo, JY; Williford, ME; Floyd, CE
MLA Citation
Baker, JA, Kornguth, PJ, Lo, JY, Williford, ME, and Floyd, CE. "Breast cancer: prediction with artificial neural network based on BI-RADS standardized lexicon." Radiology 196.3 (September 1995): 817-822.
PMID
7644649
Source
pubmed
Published In
Radiology
Volume
196
Issue
3
Publish Date
1995
Start Page
817
End Page
822
DOI
10.1148/radiology.196.3.7644649

The sonographic appearance of anomalous circumrenal vein mimicking perirenal fluid collection.

Authors
Baker, JA; Carroll, BA
MLA Citation
Baker, JA, and Carroll, BA. "The sonographic appearance of anomalous circumrenal vein mimicking perirenal fluid collection." J Ultrasound Med 14.3 (March 1995): 244-246.
PMID
7760470
Source
pubmed
Published In
Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine
Volume
14
Issue
3
Publish Date
1995
Start Page
244
End Page
246

Scatter compensation in digital chest radiography using the posterior beam stop technique.

A new scatter compensation technique for computed radiography based on posterior beam stop (PBS) sampled scatter measurements and the bicubic spline interpolation technique was proposed. Using only a single exposure, both the clinical image and an array of scatter measurements, which were interpolated into a smooth scatter-only image, were simultaneously acquired. The scatter was subtracted from the clinical image to generate the primary-only image. To gauge the accuracy of scatter estimation, both quantitative and interpolation errors were evaluated. The PBS measurements were compared against the standard beam stop method at 16 locations in an anatomical phantom, resulting in quantitative errors of 2.7% relative to the scatter or 6.8% relative to the primary. Also measured were the interpolation error over 64 interpolation sample locations and 64 midpoint sample locations in the anatomical phantom. The combined interpolation error was 1.9% relative to the scatter or 8.0% relative to the primary. At the interpolation sample locations, the errors were identical between the phantom radiograph and digital portable chest radiographs from five patients. By summing the quantitative and interpolation errors in quadrature, the overall error of the PBS SISTER (scatter interpolation-subtraction technique for radiography) method was 3.3% relative to the scatter or 10% relative to the primary, which was adequate for dual-energy imaging purposes (less than 10% error relative to the scatter or 20% relative to the primary). The change of image contrast, noise, and signal-to-noise ratio (SNR) at six locations in the anatomical phantom were quantitatively analyzed. Contrast and noise were equally enhanced in all anatomical regions, resulting in approximately the same SNR before and after compensation.(ABSTRACT TRUNCATED AT 250 WORDS)

Authors
Lo, JY; Floyd, CE; Baker, JA; Ravin, CE
MLA Citation
Lo, JY, Floyd, CE, Baker, JA, and Ravin, CE. "Scatter compensation in digital chest radiography using the posterior beam stop technique." Med Phys 21.3 (March 1994): 435-443.
PMID
8208219
Source
pubmed
Published In
Medical physics
Volume
21
Issue
3
Publish Date
1994
Start Page
435
End Page
443
DOI
10.1118/1.597388

Observer evaluation of scatter subtraction for digital portable chest radiographs.

RATIONALE AND OBJECTIVES: The authors compared standard digital portable chest radiographs (DPCXR) to scatter-subtracted DPCXR: METHODS: Thirty DPCXR were obtained using a photostimulable phosphor digital imaging system and a posterior beam stop (PBS) technique that allowed measurement of the scatter component of the DPCXR: The scatter component was subtracted from the clinical image to form a scatter-subtracted image. Six observers recorded preference for the standard image or scatter-subtracted image for identifying five radiographic landmarks and for image quality. RESULTS: A statistically significant preference was demonstrated for the scatter-subtracted images and for viewing the tracheo-bronchial tree, right paratracheal stripe, vertebral column, and support apparatus position. For unprocessed images, there was a statistically significant preference for viewing the pulmonary vasculature. No statistically significant preference was demonstrated for overall image quality. CONCLUSIONS: These results suggest that PBS scatter subtraction holds promise for improving visualization of structures in high-scatter regions of chest radiographs.

Authors
Baker, JA; Floyd, CE; Lo, JY; Ravin, CE
MLA Citation
Baker, JA, Floyd, CE, Lo, JY, and Ravin, CE. "Observer evaluation of scatter subtraction for digital portable chest radiographs." Invest Radiol 28.8 (August 1993): 667-670.
PMID
8375997
Source
pubmed
Published In
Investigative Radiology
Volume
28
Issue
8
Publish Date
1993
Start Page
667
End Page
670

An artificial neural network for estimating scatter exposures in portable chest radiography.

An adaptive linear element (Adaline) was developed to estimate the two-dimensional scatter exposure distribution in digital portable chest radiographs (DPCXR). DPCXRs and quantitative scatter exposure measurements at 64 locations throughout the chest were acquired for ten radiographically normal patients. The Adaline is an artificial neural network which has only a single node and linear thresholding. The Adaline was trained using DPCXR-scatter measurement pairs from five patients. The spatially invariant network would take a portion of the image as its input and estimate the scatter content as output. The trained network was applied to the other five images, and errors were evaluated between estimated and measured scatter values. Performance was compared against a convolution scatter estimation algorithm. The network was evaluated as a function of network size, initial values, and duration of training. Network performance was evaluated qualitatively by the correlation of network weights to physical models, and quantitatively by training and evaluation errors. Using DPCXRs as input, the network learned to describe known scatter exposures accurately (7% error) and estimate scatter in new images (< 8% error) slightly better than convolution methods. Regardless of size and initial shape, all networks adapted into radial exponentials with magnitude of 0.75, perhaps implying an ideal point spread function and average scatter fraction, respectively. To implement scatter compensation, the two-dimensional scatter distribution estimated by the neural network is subtracted from the original DPCXR.

Authors
Lo, JY; Floyd, CE; Baker, JA; Ravin, CE
MLA Citation
Lo, JY, Floyd, CE, Baker, JA, and Ravin, CE. "An artificial neural network for estimating scatter exposures in portable chest radiography." Med Phys 20.4 (July 1993): 965-973.
PMID
8413040
Source
pubmed
Published In
Medical physics
Volume
20
Issue
4
Publish Date
1993
Start Page
965
End Page
973
DOI
10.1118/1.596978

Human pathologic correlation with PET in ischemic and nonischemic cardiomyopathy.

To assess the correlation between myocardial perfusion, metabolism and histologic findings in patients with cardiomyopathy, we evaluated myocardial perfusion and metabolism using positron emission tomography (PET) with 13NH3 (ammonia) and 18FDG (fluoro-2-deoxy-glucose) in nine patients prior to undergoing orthotopic cardiac transplantation. Four patients had ischemic cardiomyopathy (ISCM) and five had nonischemic cardiomyopathy (NISCM). Normalized circumferential profile analyses of representative mid-ventricular perfusion and metabolism PET images were performed for each patient. A corresponding mid-ventricular transaxial slice was obtained from the formalin fixed explanted heart and processed for routine histology. Hematoxylin-eosin stained and Masson trichrome stained sections were evaluated and the percentage of the slice occupied by infarct was determined planimetrically at 10-degree intervals in a circumferential manner. A significant correlation was found between circumferential normalized PET count density profile of perfusion and metabolism in both the ischemic and nonischemic groups (ISCM range r = 0.65-0.75; NISCM range, r = 0.70-0.87). Furthermore, there was a correlation in the ISCM group between the extent of matched perfusion/metabolism defects and transmural infarct involvement (r = 0.66-0.88). PET perfusion and metabolic data closely correlate with pathologic infarction in human hearts of ischemic cardiomyopathy patients.

Authors
Berry, JJ; Hoffman, JM; Steenbergen, C; Baker, JA; Floyd, C; Van Trigt, P; Hanson, MW; Coleman, RE
MLA Citation
Berry, JJ, Hoffman, JM, Steenbergen, C, Baker, JA, Floyd, C, Van Trigt, P, Hanson, MW, and Coleman, RE. "Human pathologic correlation with PET in ischemic and nonischemic cardiomyopathy." J Nucl Med 34.1 (January 1993): 39-47.
PMID
8418269
Source
pubmed
Published In
Journal of nuclear medicine : official publication, Society of Nuclear Medicine
Volume
34
Issue
1
Publish Date
1993
Start Page
39
End Page
47

Measurement of scatter fractions in clinical bedside radiography.

The authors present measurements of scatter fraction (SF), the ratio of scattered to total imaged photons, from clinical bedside radiographs of 102 patients. These measurements were obtained by using a new posterior beam-stop technique that does not alter the diagnostic image but that simultaneously provides SF measurements at 224 locations in the image. The SF values in the lung were found to be consistent with previous measurements, while the SF values in the mediastinal and retrocardiac areas were larger than previously reported. SFs in diseased lung were significantly larger than SFs in normal lung. The range of SF values was large for all anatomic locations. For applications in which accurate scatter estimation is required, this wide range of values suggests that SFs should be measured in each individual image.

Authors
Floyd, CE; Baker, JA; Lo, JY; Ravin, CE
MLA Citation
Floyd, CE, Baker, JA, Lo, JY, and Ravin, CE. "Measurement of scatter fractions in clinical bedside radiography." Radiology 183.3 (June 1992): 857-861.
PMID
1584947
Source
pubmed
Published In
Radiology
Volume
183
Issue
3
Publish Date
1992
Start Page
857
End Page
861
DOI
10.1148/radiology.183.3.1584947

Posterior beam-stop method for scatter fraction measurement in digital radiography.

The authors presented a new posterior beam-stop (PBS) technique for measuring the ratio of scattered to total-detected photon flux (scatter fraction) in a radiographic examination while preserving the diagnostic quality of the image. The scatter measurement was made using a standard imaging geometry with both beam stops and an additional x-ray detector placed behind the standard imaging detector. This PBS geometry differs from the standard beam-stop (SBS) technique for scatter measurement. With SBS, a beam-stop shadow appears on the image. To evaluate the PBS technique, scatter fraction measurements were performed on an anatomic phantom using both the PBS and SBS techniques. When compared with the standard technique, PBS provided accurate estimation of scatter fractions. Since the measurement can be performed without degrading a standard clinical radiographic examination, the PBS technique allows simultaneous acquisition of scatter measurements from human patients in combination with a standard radiographic examination.

Authors
Floyd, CE; Baker, JA; Lo, JY; Ravin, CE
MLA Citation
Floyd, CE, Baker, JA, Lo, JY, and Ravin, CE. "Posterior beam-stop method for scatter fraction measurement in digital radiography." Invest Radiol 27.2 (February 1992): 119-123.
PMID
1601602
Source
pubmed
Published In
Investigative Radiology
Volume
27
Issue
2
Publish Date
1992
Start Page
119
End Page
123

The effect of metabolic milieu on cardiac PET imaging using fluorine-18-deoxyglucose and nitrogen-13-ammonia in normal volunteers.

Cardiac PET imaging using 13N-ammonia and 18FDG was performed on 17 normal volunteers in the glucose-loaded and fasted states. PET images (glucose-loaded and fasted) were subjected to qualitative visual analysis using the descriptors: image quality, FDG blood-pool activity, ammonia lung field activity, and clinical interpretability. Glucose-loaded studies had better image quality, diminished FDG blood-pool activity, and were more often clinically interpretable compared to fasted studies. Dietary state did not affect 13N-ammonia study parameters. Using a semi-quantitative region of interest method, 18FDG myocardial activity was homogeneous and significantly affected by dietary state (2.48 +/- 1.0 fold increase in myocardial-to-blood pool ratio in glucose-loaded versus fasted states). Serum glucose, insulin, and free-fatty acid concentrations responded physiologically to glucose loading and fasting but showed no correlation with myocardial 18FDG uptake. PET imaging using 13N-ammonia and 18FDG appears optimal in the glucose-loaded state.

Authors
Berry, JJ; Baker, JA; Pieper, KS; Hanson, MW; Hoffman, JM; Coleman, RE
MLA Citation
Berry, JJ, Baker, JA, Pieper, KS, Hanson, MW, Hoffman, JM, and Coleman, RE. "The effect of metabolic milieu on cardiac PET imaging using fluorine-18-deoxyglucose and nitrogen-13-ammonia in normal volunteers." J Nucl Med 32.8 (August 1991): 1518-1525.
PMID
1869972
Source
pubmed
Published In
Journal of nuclear medicine : official publication, Society of Nuclear Medicine
Volume
32
Issue
8
Publish Date
1991
Start Page
1518
End Page
1525
Show More