Chunhao Wang

Objective. Deep learning (DL) models for fluence map prediction (FMP) have great potential to reduce treatment planning time in intensity-modulated radiation therapy (IMRT) by avoiding the lengthy inverse optimization process. This study aims to improve the rigor of input feature design in a DL-FMP model by examining how different designs of input features influence model prediction performance.Approach. This study included 231 head-and-neck intensity-modulated radiation therapy patients. Three input feature designs were investigated. The first design (D1) assumed that information of all critical structures from all beam angles should be combined to predict fluence maps. The second design (D2) assumed that local anatomical information was sufficient for predicting radiation intensity of a beamlet at a respective beam angle. The third design (D3) assumed the need for both local anatomical information and inter-beam modulation to predict radiation intensity values of the beamlets that intersect at a voxel. For each input design, we tailored the DL model accordingly. All models were trained using the same set of ground truth plans (GT plans). The plans generated by DL models (DL plans) were analyzed using key dose-volume metrics. One-way ANOVA with multiple comparisons correction (Bonferroni method) was performed (significance level = 0.05).Main results. For PTV-related metrics, all DL plans had significantly higher maximum dose (p < 0.001), conformity index (p < 0.001), and heterogeneity index (p < 0.001) compared to GT plans, with D2 being the worst performer. Meanwhile, except for cord+5 mm (p < 0.001), DL plans of all designs resulted in OAR dose metrics that are comparable to those of GT plans.Significance. Local anatomical information contains most of the information that DL models need to predict fluence maps for clinically acceptable OAR sparing. Input features from beam angles are needed to achieve the best PTV coverage. These results provide valuable insights for further improvement of DL-FMP models and DL models in general.

<h4>Purpose/objective(s)</h4>To compare dosimetric results of two beam arrangement strategies and their robustness to setup uncertainties in fractionated thoracic spine Stereotactic Body Radiotherapy (SBRT) MATERIALS/METHODS: Fifteen patients who received fractionated thoracic spine SBRT were retrospectively studied. All patients received simulation CT scans in body vacuum bag immobilization and multiparametric MRI exams. Clinical target volumes (CTVs) included single vertebral bodies with possible paraspinal space inclusion. Planning target volumes (PTVs) were expanded from CTVs with a 2mm margin but were cropped from spinal cord defined by MRI with a 2mm margin. Two different beam arrangement strategies of volumetric modulated arc therapy planning were studied: 1) 5 full arcs (FA) (360° each arc) with different collimator angles; and 2) 6 partial arcs (PA) (90° each arc) divided into two groups (3 arcs in each group) covering patient left-posterior-oblique (LPO) and right-posterior-oblique (RPO) regions, respectively, with orthogonal collimator angles. Both plans (Plan_FA and Plan_PA) were calculated as 24 Gy in 3 fractions using 6xFFF photon energy and a high-definition MLC model. During the inverse optimization of each plan for same patient, a same set of dose-volume constraints and optimization settings was used to exhaust parameter space search. Key dosimetric results of PTV as well as dose-volume parameters of relevant organs-at-risk (OARs) including spinal cord, esophagus, heart, lung and liver were evaluated. Dosimetric impact of on-board patient setup uncertainties to both plans were also simulated. All comparison results were analyzed by Wilcoxon signed-rank tests when the statistical power was sufficient.<h4>Results</h4>Both Plan_FA and Plan_PA achieved satisfactory spatial dose distribution. After PTV coverage normalization, Plan_PA had better PTV dose uniformity (P = 0.026) and Plan_FA had better dose fall-off gradient outside PTV. Plan_PA had slightly better (18.1 ± 0.8 Gy vs 18.3 ± 0.9 Gy) cord max dose (D_0.035cc) results (P = 0.213) and better cord low dose sparing V12 Gy (P = 0.013) results. Plan_PA also achieved lower max dose (D_0.035cc) of esophagus (P = 0.003) and heart, and improved low dose sparing (V5 Gy) of lung (P = 0.002) and liver. In plan parameter comparisons, Plan_FA demonstrated stronger beam modulation effect (P < 0.001) but Plan_PA had smaller MLC apertures (P < 0.001). In the simulated on-board scenarios with setup uncertainties, while both Plan_FA and Plan_PA had similar cord max dose increases with simulated pitch and/or roll in setup (< 0.1 Gy differences), Plan_PA had minimal cord max dose increase (P < 0.001) with simulated anterior body weight loss.<h4>Conclusion</h4>For thoracic spine SBRT plans, the beam arrangement in Plan_PA might be favored dosimetrically with better OAR sparing results and could be less sensitive to certain patient uncertainties, while the Plan_FA could be acceptable with satisfactory dosimetry results.<h4>Author disclosure</h4>C. Wang: None. Y. Xie: None. Z. Hu: None. F. Yin: Research Grant; Varian Medical Systems. Teaching and mentoring graduate students. Administration of graduate program activities; Duke Kunshan University. Board of Directors Member at Large Members; AAPM. organize activities of the SANTRO; SANTRO.Z. Reitman: None. Y. Cui: None.

PURPOSE: To develop a radiomics filtering technique for characterizing spatial-encoded regional pulmonary ventilation information on lung computed tomography (CT). METHODS: The lung volume was segmented on 46 CT images, and a 3D sliding window kernel was implemented across the lung volume to capture the spatial-encoded image information. Fifty-three radiomic features were extracted within the kernel, resulting in a fourth-order tensor object. As such, each voxel coordinate of the original lung was represented as a 53-dimensional feature vector, such that radiomic features could be viewed as feature maps within the lungs. To test the technique as a potential pulmonary ventilation biomarker, the radiomic feature maps were compared to paired functional images (Galligas PET or DTPA-SPECT) based on the Spearman correlation (ρ) analysis. RESULTS: The radiomic feature maps GLRLM-based Run-Length Non-Uniformity and GLCOM-based Sum Average are found to be highly correlated with the functional imaging. The achieved ρ (median [range]) for the two features are 0.46 [0.05, 0.67] and 0.45 [0.21, 0.65] across 46 patients and 2 functional imaging modalities, respectively. CONCLUSIONS: The results provide evidence that local regions of sparsely encoded heterogeneous lung parenchyma on CT are associated with diminished radiotracer uptake and measured lung ventilation defects on PET/SPECT imaging. These findings demonstrate the potential of radiomics to serve as a complementary tool to the current lung quantification techniques and provide hypothesis-generating data for future studies.

PURPOSE: To develop a method of biologically guided deep learning for post-radiation 18FDG-PET image outcome prediction based on pre-radiation images and radiotherapy dose information. METHODS: Based on the classic reaction-diffusion mechanism, a novel biological model was proposed using a partial differential equation that incorporates spatial radiation dose distribution as a patient-specific treatment information variable. A 7-layer encoder-decoder-based convolutional neural network (CNN) was designed and trained to learn the proposed biological model. As such, the model could generate post-radiation 18FDG-PET image outcome predictions with breakdown biological components for enhanced explainability. The proposed method was developed using 64 oropharyngeal patients with paired 18FDG-PET studies before and after 20-Gy delivery (2 Gy/day fraction) by intensity-modulated radiotherapy (IMRT). In a two-branch deep learning execution, the proposed CNN learns specific terms in the biological model from paired 18FDG-PET images and spatial dose distribution in one branch, and the biological model generates post-20-Gy 18FDG-PET image prediction in the other branch. As in 2D execution, 718/233/230 axial slices from 38/13/13 patients were used for training/validation/independent test. The prediction image results in test cases were compared with the ground-truth results quantitatively. RESULTS: The proposed method successfully generated post-20-Gy 18FDG-PET image outcome prediction with breakdown illustrations of biological model components. Standardized uptake value (SUV) mean values in 18FDG high-uptake regions of predicted images (2.45 ± 0.25) were similar to ground-truth results (2.51 ± 0.33). In 2D-based Gamma analysis, the median/mean Gamma Index (<1) passing rate of test images was 96.5%/92.8% using the 5%/5 mm criterion; such result was improved to 99.9%/99.6% when 10%/10 mm was adopted. CONCLUSION: The developed biologically guided deep learning method achieved post-20-Gy 18FDG-PET image outcome predictions in good agreement with ground-truth results. With the breakdown biological modeling components, the outcome image predictions could be used in adaptive radiotherapy decision-making to optimize personalized plans for the best outcome in the future.

Purpose.We have previously reported an artificial intelligence (AI) agent that automatically generates intensity-modulated radiation therapy (IMRT) plans via fluence map prediction, by-passing inverse planning. This AI agent achieved clinically comparable quality for prostate cases, but its performance on head-and-neck patients leaves room for improvement. This study aims to collect insights of the deep-learning-based (DL-based) fluence map prediction model by systematically analyzing its prediction errors.Methods.From the modeling perspective, the DL model's output is the fluence maps of IMRT plans. However, from the clinical planning perspective, the plan quality evaluation should be based on the clinical dosimetric criteria such as dose-volume histograms. To account for the complex and non-intuitive relationships between fluence map prediction errors and the corresponding dose distribution changes, we propose a novel error analysis approach that systematically examines plan dosimetric changes that are induced by varying amounts of fluence prediction errors. We investigated four decomposition modes of model prediction errors. The two spatial domain decompositions are based on fluence intensity and fluence gradient. The two frequency domain decompositions are based on Fourier-space banded frequency rings and Fourier-space truncated low-frequency disks. The decomposed error was analyzed for its impact on the resulting plans' dosimetric metrics. The analysis was conducted on 15 test cases spared from the 200 training and 16 validation cases used to train the model.Results.Most planning target volume metrics were significantly correlated with most error decompositions. The Fourier space disk radii had the largest Spearman's coefficients. The low-frequency region within a disk of ∼20% Fourier space contained most of errors that impact overall plan quality.Conclusions.This study demonstrates the feasibility of using fluence map prediction error analysis to understand the AI agent's performance. Such insights will help fine-tune the DL models in architecture design and loss function selection.