Kyle Lafata

Overview:

Kyle Lafata is an Assistant Professor of Radiology, Radiation Oncology, and Electrical & Computer Engineering at Duke University. As an imaging physicist and data scientist, Dr. Lafata’s research interests are in image-based phenotyping and computational biomarkers. His dissertation work focused on nature-inspired computational methods and soft-computing paradigms, including the applied analysis of stochastic differential equations, self-organization, and quantum machine learning (i.e., an emerging branch of research that explores the methodological and structural similarities between quantum systems and learning systems). He has broad expertise in imaging science, digital pathology, computer vision, feature engineering, and applied mathematics.


The Lafata Laboratory focuses on multi-scale imaging biomarkers. They study the imaging phenotype across multiple physical length-scales, including radiological (i.e., ~10-3 m), pathological (i.e., ~10-6 m), and molecular (i.e., ~10-9 m) domains. To accomplish this, the lab develops mathematical methods, computational imaging techniques, and measurement tools to characterize and quantify the appearance and behavior of disease. This technology is applied to interrogate underlying biology, characterize tissue microenvironments, diagnose disease, predict disease progression, quantify treatment response, and enable personalized therapy.

Positions:

Assistant Professor of Radiation Oncology

Radiation Oncology
School of Medicine

Assistant Professor in Radiology

Radiology
School of Medicine

Assistant Professor in the Department of Electrical and Computer Engineering

Electrical and Computer Engineering
Pratt School of Engineering

Member of the Duke Cancer Institute

Duke Cancer Institute
School of Medicine

Education:

Ph.D. 2018

Duke University

C. 2018

Duke University

Postdoctoral Associate, Radiation Oncology/Radiation Physics Division

Duke University School of Medicine

Grants:

Targeting the B Cell Response to Treat Antibody-Mediated Rejection

Administered By
Surgery, Abdominal Transplant Surgery
Awarded By
National Institutes of Health
Role
Co Investigator
Start Date
End Date

Computational Pathology of Proteinuric Diseases

Administered By
Medicine, Nephrology
Awarded By
National Institutes of Health
Role
Co Investigator
Start Date
End Date

Publications:

Effect of Lung SBRT Fractionation On Feature Variability of Longitudinal Cone-Beam CT Radiomics

Authors
Geng, R; Lafata, K; Yin, F
MLA Citation
Geng, R., et al. “Effect of Lung SBRT Fractionation On Feature Variability of Longitudinal Cone-Beam CT Radiomics.” Medical Physics, vol. 45, no. 6, 2018, pp. E411–E411.
URI
https://scholars.duke.edu/individual/pub1450058
Source
wos-lite
Published In
Medical Physics
Volume
45
Published Date
Start Page
E411
End Page
E411

Biologically Guided Deep Learning for Post-Radiation PET Image Outcome Prediction: A Feasibility Study of Oropharyngeal Cancer Application

Authors
Wang, C; Ji, H; Bertozzi, A; Brizel, D; Mowery, Y; Yin, F; Lafata, K
URI
https://scholars.duke.edu/individual/pub1495088
Source
wos-lite
Published In
Medical Physics
Volume
48
Published Date

Sensitivity of Radiomic Features to Acquisition Noise and Respiratory Motion

MLA Citation
Lafata, K., et al. “Sensitivity of Radiomic Features to Acquisition Noise and Respiratory Motion.” International Journal of Radiation Oncology*Biology*Physics, vol. 99, no. 2, Elsevier BV, 2017, pp. S93–94. Crossref, doi:10.1016/j.ijrobp.2017.06.226.
URI
https://scholars.duke.edu/individual/pub1284602
Source
crossref
Published In
International Journal of Radiation Oncology, Biology, Physics
Volume
99
Published Date
Start Page
S93
End Page
S94
DOI
10.1016/j.ijrobp.2017.06.226

A Radiomics-Boosted Deep Learning Model for COVID-19 and Non-COVID-19 Pneumonia Detection Using Chest X-Ray Image

MLA Citation
URI
https://scholars.duke.edu/individual/pub1495104
Source
wos-lite
Published In
Medical Physics
Volume
48
Published Date

Sensitivity of Radiomic Features to Image Noise and Respiratory Motion

Authors
MLA Citation
Lafata, K., et al. “Sensitivity of Radiomic Features to Image Noise and Respiratory Motion.” Medical Physics, vol. 44, no. 6, WILEY, 2017.
URI
https://scholars.duke.edu/individual/pub1308078
Source
wos
Published In
Medical Physics
Volume
44
Published Date