Enhancing Precision in Cardiac Segmentation for Magnetic Resonance-Guided Radiation Therapy Through Deep Learning

Purpose: Cardiac substructure dose metrics are more strongly linked to late cardiac morbidities than to whole-heart metrics. Magnetic resonance (MR)-guided - guided radiation therapy (MRgRT) enables substructure visualization during daily localization, allowing potential for enhanced cardiac sparing. We extend a publicly available state-of-the-art deep learning framework, " No New" U-Net, to incorporate self-distillation (nnU-Net.wSD) for substructure segmentation for MRgRT. Methods and Materials: Eighteen (institute A) patients who underwent thoracic or abdominal radiation therapy on a 0.35 T MR-guided linear accelerator were retrospectively evaluated. On each image, 1 of 2 radiation oncologists delineated reference contours of 12 cardiac substructures (chambers, great vessels, and coronary arteries) used to train (n = 10), validate (n = 3), and test (n = 5) nnU-Net.wSD by leveraging a teacher-student network and comparing it to standard 3-dimensional U-Net. The impact of using simulation data or including 3 to 4 daily images for augmentation during training was evaluated for nnU-Net.wSD. Geometric metrics (Dice similarity coefficient, fi cient, mean distance to agreement, and 95% Hausdorff distance), visual inspection, and clinical dose-volume histograms were evaluated. To determine generalizability, institute A's ' s model was tested on an unlabeled data set from institute B (n = 22) and evaluated via consensus scoring and volume comparisons. Results: nnU-Net.wSD yielded a Dice similarity coefficient (reported mean f SD) of 0.65 f 0.25 across the 12 substructures (chambers, 0.85 f 0.05; great vessels, 0.67 f 0.19; and coronary arteries, 0.33 f 0.16; mean distance to agreement, < 3 mm; mean 95% Hausdorff distance, < 9 mm) while outperforming the 3-dimensional U-Net (0.583 f 0.28; P < .01). Leveraging fractionated data for augmentation improved over a single MR simulation time point (0.579 <section> 0.29; P < .01). Predicted contours yielded dose-volume histograms that closely matched those of the clinical treatment plans where mean and maximum (ie, dose to 0.03 cc) doses deviated by 0.32 <section> 0.5 Gy and 1.42 2.6 Gy, respectively. There were no statistically significant fi cant differences between institute A and B volumes (P > .05) for 11 of 12 substructures, with larger volumes requiring minor changes and coronary arteries exhibiting more variability. Conclusions: This work is a critical step toward rapid and reliable cardiac substructure segmentation to improve cardiac sparing in low-field fi eld MRgRT. (c) 2024 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.