Deep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patients
Objective. 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 f...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
15 July 2025
|
| In: |
Physics in medicine and biology
Year: 2025, Volume: 70, Issue: 14, Pages: 1-17 |
| ISSN: | 1361-6560 |
| DOI: | 10.1088/1361-6560/ade8d0 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.1088/1361-6560/ade8d0
|
| Author Notes: | Chengtao Wei, Chukwuka Eze, Rabea Klaar, Daniela Thorwarth, Cora Warda, Julian Taugner, Juliane Hörner-Rieber, Sebastian Regnery, Oliver Jäkel, Fabian Weykamp, Miguel Palacios, Sebastian N Marschner, Stefanie Corradini, Claus Belka, Christopher Kurz, Guillaume Landry and Moritz Rabe |
| Summary: | Objective. 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 0.35 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 (TMMSE+Dice) or MSE and regularization losses (TMMSE) 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. TMMSE+Dice and TMMSE 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, TMMSE+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. TMMSE+Dice and TMMSE had significantly higher geometric accuracy than other methods on external data. No significant difference between TMMSE+Dice and TMMSE 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. |
|---|---|
| Item Description: | Veröffentlicht: 15. Juli 2025 Gesehen am 26.11.2025 |
| Physical Description: | Online Resource |
| ISSN: | 1361-6560 |
| DOI: | 10.1088/1361-6560/ade8d0 |