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 |
MARC
| LEADER | 00000naa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1942571933 | ||
| 003 | DE-627 | ||
| 005 | 20251126101456.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 251126s2025 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1088/1361-6560/ade8d0 |2 doi | |
| 035 | |a (DE-627)1942571933 | ||
| 035 | |a (DE-599)KXP1942571933 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Wei, Chengtao |e VerfasserIn |0 (DE-588)1382674813 |0 (DE-627)1942572409 |4 aut | |
| 245 | 1 | 0 | |a Deep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patients |c 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 |
| 264 | 1 | |c 15 July 2025 | |
| 300 | |b Illustrationen | ||
| 300 | |a 17 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Veröffentlicht: 15. Juli 2025 | ||
| 500 | |a Gesehen am 26.11.2025 | ||
| 520 | |a 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. | ||
| 700 | 1 | |a Eze, Chukwuka |e VerfasserIn |4 aut | |
| 700 | 1 | |a Klaar, Rabea |e VerfasserIn |4 aut | |
| 700 | 1 | |a Thorwarth, Daniela |e VerfasserIn |4 aut | |
| 700 | 1 | |a Warda, Cora |e VerfasserIn |4 aut | |
| 700 | 1 | |a Taugner, Julian |e VerfasserIn |4 aut | |
| 700 | 1 | |a Hörner-Rieber, Juliane |d 1985- |e VerfasserIn |0 (DE-588)1025307631 |0 (DE-627)722020511 |0 (DE-576)370188039 |4 aut | |
| 700 | 1 | |a Regnery, Sebastian |e VerfasserIn |0 (DE-588)1182554776 |0 (DE-627)1662804199 |4 aut | |
| 700 | 1 | |a Jäkel, Oliver |d 1964- |e VerfasserIn |0 (DE-588)1050056302 |0 (DE-627)783260709 |0 (DE-576)404358705 |4 aut | |
| 700 | 1 | |a Weykamp, Fabian |d 1987- |e VerfasserIn |0 (DE-588)1072433036 |0 (DE-627)827655096 |0 (DE-576)43385992X |4 aut | |
| 700 | 1 | |a Palacios, Miguel |e VerfasserIn |4 aut | |
| 700 | 1 | |a Marschner, Sebastian N |e VerfasserIn |4 aut | |
| 700 | 1 | |a Corradini, Stefanie |e VerfasserIn |4 aut | |
| 700 | 1 | |a Belka, Claus |e VerfasserIn |4 aut | |
| 700 | 1 | |a Kurz, Christopher |e VerfasserIn |4 aut | |
| 700 | 1 | |a Landry, Guillaume |e VerfasserIn |4 aut | |
| 700 | 1 | |a Rabe, Moritz |e VerfasserIn |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Physics in medicine and biology |d Bristol : IOP Publ., 1956 |g 70(2025), 14, Artikel-ID 145018, Seite 1-17 |h Online-Ressource |w (DE-627)269016163 |w (DE-600)1473501-5 |w (DE-576)088704130 |x 1361-6560 |7 nnas |a Deep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patients |
| 773 | 1 | 8 | |g volume:70 |g year:2025 |g number:14 |g elocationid:145018 |g pages:1-17 |g extent:17 |a Deep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patients |
| 856 | 4 | 0 | |u https://doi.org/10.1088/1361-6560/ade8d0 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20251126 | ||
| 993 | |a Article | ||
| 994 | |a 2025 | ||
| 998 | |g 1072433036 |a Weykamp, Fabian |m 1072433036:Weykamp, Fabian |d 910000 |d 911400 |d 50000 |e 910000PW1072433036 |e 911400PW1072433036 |e 50000PW1072433036 |k 0/910000/ |k 1/910000/911400/ |k 0/50000/ |p 10 | ||
| 998 | |g 1050056302 |a Jäkel, Oliver |m 1050056302:Jäkel, Oliver |p 9 | ||
| 998 | |g 1182554776 |a Regnery, Sebastian |m 1182554776:Regnery, Sebastian |d 910000 |d 911400 |e 910000PR1182554776 |e 911400PR1182554776 |k 0/910000/ |k 1/910000/911400/ |p 8 | ||
| 998 | |g 1025307631 |a Hörner-Rieber, Juliane |m 1025307631:Hörner-Rieber, Juliane |d 50000 |e 50000PH1025307631 |k 0/50000/ |p 7 | ||
| 999 | |a KXP-PPN1942571933 |e 481408269X | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"origin":[{"dateIssuedDisp":"15 July 2025","dateIssuedKey":"2025"}],"person":[{"family":"Wei","role":"aut","given":"Chengtao","display":"Wei, Chengtao"},{"display":"Eze, Chukwuka","family":"Eze","given":"Chukwuka","role":"aut"},{"given":"Rabea","role":"aut","family":"Klaar","display":"Klaar, Rabea"},{"display":"Thorwarth, Daniela","given":"Daniela","role":"aut","family":"Thorwarth"},{"display":"Warda, Cora","family":"Warda","role":"aut","given":"Cora"},{"given":"Julian","role":"aut","family":"Taugner","display":"Taugner, Julian"},{"family":"Hörner-Rieber","given":"Juliane","role":"aut","display":"Hörner-Rieber, Juliane"},{"display":"Regnery, Sebastian","family":"Regnery","role":"aut","given":"Sebastian"},{"display":"Jäkel, Oliver","role":"aut","given":"Oliver","family":"Jäkel"},{"display":"Weykamp, Fabian","family":"Weykamp","role":"aut","given":"Fabian"},{"display":"Palacios, Miguel","role":"aut","given":"Miguel","family":"Palacios"},{"display":"Marschner, Sebastian N","family":"Marschner","given":"Sebastian N","role":"aut"},{"family":"Corradini","given":"Stefanie","role":"aut","display":"Corradini, Stefanie"},{"family":"Belka","given":"Claus","role":"aut","display":"Belka, Claus"},{"given":"Christopher","role":"aut","family":"Kurz","display":"Kurz, Christopher"},{"given":"Guillaume","role":"aut","family":"Landry","display":"Landry, Guillaume"},{"display":"Rabe, Moritz","family":"Rabe","given":"Moritz","role":"aut"}],"relHost":[{"physDesc":[{"extent":"Online-Ressource"}],"recId":"269016163","disp":"Deep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patientsPhysics in medicine and biology","origin":[{"dateIssuedKey":"1956","dateIssuedDisp":"1956-","publisherPlace":"Bristol","publisher":"IOP Publ."}],"pubHistory":["1.1956 -"],"language":["eng"],"type":{"bibl":"periodical","media":"Online-Ressource"},"note":["Gesehen am 28.01.2019","Fortsetzung der Druck-Ausgabe"],"id":{"eki":["269016163"],"issn":["1361-6560"],"zdb":["1473501-5"]},"title":[{"subtitle":"an official journal of the Institute of Physics and Engineering in Medicine","title":"Physics in medicine and biology","title_sort":"Physics in medicine and biology"}],"part":{"year":"2025","volume":"70","pages":"1-17","text":"70(2025), 14, Artikel-ID 145018, Seite 1-17","extent":"17","issue":"14"}}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"language":["eng"],"note":["Veröffentlicht: 15. Juli 2025","Gesehen am 26.11.2025"],"title":[{"title_sort":"Deep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patients","title":"Deep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patients"}],"physDesc":[{"noteIll":"Illustrationen","extent":"17 S."}],"recId":"1942571933","name":{"displayForm":["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"]},"id":{"eki":["1942571933"],"doi":["10.1088/1361-6560/ade8d0"]}} | ||
| SRT | |a WEICHENGTADEEPLEARNI1520 | ||