Deep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patients.
Authors
Affiliations (14)
Affiliations (14)
- LMU Hospital Department of Radiotherapy and Radiation Oncology, Marchioninistr. 15, 81377 Munich, Germany, Munich, 81377, GERMANY.
- Department of Radiation Oncology, LMU Hospital Department of Radiotherapy and Radiation Oncology, Marchioninistr. 15, 81377 Munich, Germany, Munich, BY, 81377, GERMANY.
- Department of Radiology, LMU University Hospital, LMU Munich, Marchioninistr. 15, Munich, 81377, GERMANY.
- Section for Biomedical Physics, Department of Radiation Oncology, University Hospital Tübingen, Hoppe-Seyler-Str 3, Tübingen, BW, 72076, GERMANY.
- Department of Radiation Oncology, University Hospital Tübingen, Hoppe-Seyler-Straße 3, Tübingen, 72076, GERMANY.
- Department of Radiation Oncology, University Hospital of Düsseldorf, Moorenstraße 5, Düsseldorf, NRW, 40225, GERMANY.
- Department of Radiation Oncology, Heidelberg University Hospital, Im Neuenheimer Feld 400, Heidelberg, 69120, GERMANY.
- Division for Medical Physics in Radiotherapy (E040), Deutsches Krebsforschungszentrum, Im Neuenheimer Feld 280, 69120 Heidelberg, Heidelberg, 69120, GERMANY.
- Department of Radiation Oncology, Amsterdam UMC, De Boelelaan 1118, Amsterdam, 1081, NETHERLANDS.
- Department of Radiation Oncology, LMU University Hospital, Marchioninistr. 15, LMU Munich, 81377, GERMANY.
- Radiation Oncology, University Hospital Munich Campus Grosshadern, Marchioninistr. 15, Munchen, 81377, GERMANY.
- Department of Radiation Oncology, University Hospital of Ludwig-Maximilians-University Munich, Marchioninistr. 15, Munich, 81377, GERMANY.
- Radiation Oncology, University Hospital Munich, Marchioninistr. 15, Munich, Bavaria, 81377, GERMANY.
- Department of Radiation Oncology, LMU Hospital Department of Radiotherapy and Radiation Oncology, Marchioninistr. 15, Munich, BY, 81377, GERMANY.
Abstract
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.
Approach: Data from 140 stage 1-2 lung cancer patients treated at a 0.35T MR-Linac were split into 102/17/21 for training/validation/testing. Additionally, 18 central lung tumor patients, treated at a 0.35T MR-Linac externally, and 14 stage 3 lung cancer patients from a phase 1 clinical trial, treated at 0.35T or 1.5T 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_{MSE+Dice}) or MSE and regularization losses (TM_{MSE}) 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.
Main results: TM_{MSE+Dice} and TM_{MSE} achieved 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, TM_{MSE+Dice} achieved 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. TM_{MSE+Dice} and TM_{MSE} had significantly higher geometric accuracy than other methods on external data. No significant difference between TM_{MSE+Dice} and TM_{MSE} was found.
Significance: TransMorph models achieved time-efficient segmentation of fraction MRIs with high geometrical accuracy and accurately segmented images obtained at different field strengths.