Deep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patients.

Fast and accurate organ-at-risk (OAR) and gross tumor volume (GTV) contour propagation methods are needed to improve the efficiency of magnetic resonance (MR) imaging-guided radiotherapy. We trained deformable image registration networks to accurately propagate contours from planning to fraction MR images.Data from 140 stage 1-2 lung cancer patients treated at a 0.35 T MR-Linac were split into 102/17/21 for training/validation/testing. Additionally, 18 central lung tumor patients, treated at a 0.35 T MR-Linac externally, and 14 stage 3 lung cancer patients from a phase 1 clinical trial, treated at 0.35 T or 1.5 T MR-Linacs at three institutions, were used for external testing. Planning and fraction images were paired (490 pairs) for training. Two hybrid transformer-convolutional neural network TransMorph models with mean squared error (MSE), Dice similarity coefficient (DSC), and regularization losses (TM) or MSE and regularization losses (TM) were trained to deformably register planning to fraction images. The TransMorph models predicted diffeomorphic dense displacement fields. Multi-label images including seven thoracic OARs and the GTV were propagated to generate fraction segmentations. Model predictions were compared with contours obtained through B-spline, vendor registration and the auto-segmentation method nnUNet. Evaluation metrics included the DSC and Hausdorff distance percentiles (50th and 95th) against clinical contours.TMand TMachieved mean OARs/GTV DSCs of 0.90/0.82 and 0.90/0.79 for the internal and 0.84/0.77 and 0.85/0.76 for the central lung tumor external test data. On stage 3 data, TMachieved mean OARs/GTV DSCs of 0.87/0.79 and 0.83/0.78 for the 0.35 T MR-Linac datasets, and 0.87/0.75 for the 1.5 T MR-Linac dataset. TMand TMhad significantly higher geometric accuracy than other methods on external data. No significant difference between TMand TMwas found.TransMorph models achieved time-efficient segmentation of fraction MRIs with high geometrical accuracy and accurately segmented images obtained at different field strengths.