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

Wei C, Eze C, Klaar R, Thorwarth D, Warda C, Taugner J, Hörner-Rieber J, Regnery S, Jäkel O, Weykamp F, Palacios M, Marschner SN, Corradini S, Belka C, Kurz C, Landry G, Rabe M (2025)

Publication Type: Journal article

Publication year: 2025

Journal

Physics in Medicine and Biology IOP Publishing

Book Volume: 70

Article Number: 145018

Journal Issue: 14

DOI: 10.1088/1361-6560/ade8d0

Abstract

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.

Involved external institutions

Klinikum der Universität München (LMU Klinikum) DE Germany (DE) Universitätsklinikum Tübingen DE Germany (DE) Universitätsklinikum Düsseldorf DE Germany (DE) Universitätsklinikum Heidelberg DE Germany (DE) Nationales Zentrum für Strahlenforschung in der Onkologie / National Center for Radiation Research in Oncology (NCRO- OncoRay) DE Germany (DE) Amsterdam University Medical Centers (Amsterdam UMC) / Amsterdam Universitair Medische Centra NL Netherlands (NL)

How to cite

APA:

Wei, C., Eze, C., Klaar, R., Thorwarth, D., Warda, C., Taugner, J.,... Rabe, M. (2025). Deep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patients. Physics in Medicine and Biology, 70(14). https://doi.org/10.1088/1361-6560/ade8d0

MLA:

Wei, Chengtao, et al. "Deep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patients." Physics in Medicine and Biology 70.14 (2025).

BibTeX: Download