000302286 001__ 302286
000302286 005__ 20250731092256.0
000302286 0247_ $$2doi$$a10.1088/1361-6560/ade8d0
000302286 0247_ $$2pmid$$apmid:40570891
000302286 0247_ $$2ISSN$$a0031-9155
000302286 0247_ $$2ISSN$$a1361-6560
000302286 037__ $$aDKFZ-2025-01305
000302286 041__ $$aEnglish
000302286 082__ $$a530
000302286 1001_ $$00009-0003-7846-1800$$aWei, Chengtao$$b0
000302286 245__ $$aDeep learning-based contour propagation in magnetic resonance imaging-guided radiotherapy of lung cancer patients.
000302286 260__ $$aBristol$$bIOP Publ.$$c2025
000302286 3367_ $$2DRIVER$$aarticle
000302286 3367_ $$2DataCite$$aOutput Types/Journal article
000302286 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1753946504_19397
000302286 3367_ $$2BibTeX$$aARTICLE
000302286 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000302286 3367_ $$00$$2EndNote$$aJournal Article
000302286 500__ $$aMed. Biol. 70 145018
000302286 520__ $$aFast 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.
000302286 536__ $$0G:(DE-HGF)POF4-315$$a315 - Bildgebung und Radioonkologie (POF4-315)$$cPOF4-315$$fPOF IV$$x0
000302286 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
000302286 650_7 $$2Other$$aMR-linac
000302286 650_7 $$2Other$$aMRgRT
000302286 650_7 $$2Other$$aPUMA
000302286 650_7 $$2Other$$aTransMorph
000302286 650_7 $$2Other$$adeep learning
000302286 650_7 $$2Other$$aimage registration
000302286 650_7 $$2Other$$alung cancer
000302286 7001_ $$aEze, Chukwuka$$b1
000302286 7001_ $$00009-0006-9739-2865$$aKlaar, Rabea$$b2
000302286 7001_ $$aThorwarth, Daniela$$b3
000302286 7001_ $$aWarda, Cora$$b4
000302286 7001_ $$aTaugner, Julian$$b5
000302286 7001_ $$aHörner-Rieber, Juliane$$b6
000302286 7001_ $$aRegnery, Sebastian$$b7
000302286 7001_ $$0P:(DE-He78)440a3f62ea9ea5c63375308976fc4c44$$aJäkel, Oliver$$b8$$udkfz
000302286 7001_ $$0P:(DE-He78)c7f6680647a8e992f04c9e075784f775$$aWeykamp, Fabian$$b9$$udkfz
000302286 7001_ $$aPalacios, Miguel A$$b10
000302286 7001_ $$aMarschner, Sebastian$$b11
000302286 7001_ $$aCorradini, Stefanie$$b12
000302286 7001_ $$0P:(DE-HGF)0$$aBelka, Claus$$b13
000302286 7001_ $$aKurz, Christopher$$b14
000302286 7001_ $$00000-0003-1707-4068$$aLandry, Guillaume$$b15
000302286 7001_ $$00000-0002-7085-4066$$aRabe, Moritz$$b16
000302286 773__ $$0PERI:(DE-600)1473501-5$$a10.1088/1361-6560/ade8d0$$p145018$$tPhysics in medicine and biology$$v70$$x0031-9155$$y2025
000302286 909CO $$ooai:inrepo02.dkfz.de:302286$$pVDB
000302286 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)440a3f62ea9ea5c63375308976fc4c44$$aDeutsches Krebsforschungszentrum$$b8$$kDKFZ
000302286 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)c7f6680647a8e992f04c9e075784f775$$aDeutsches Krebsforschungszentrum$$b9$$kDKFZ
000302286 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b13$$kDKFZ
000302286 9131_ $$0G:(DE-HGF)POF4-315$$1G:(DE-HGF)POF4-310$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lKrebsforschung$$vBildgebung und Radioonkologie$$x0
000302286 9141_ $$y2025
000302286 915__ $$0StatID:(DE-HGF)0430$$2StatID$$aNational-Konsortium$$d2024-12-27$$wger
000302286 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bPHYS MED BIOL : 2022$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2024-12-27
000302286 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2024-12-27
000302286 9201_ $$0I:(DE-He78)E040-20160331$$kE040$$lE040 Med. Physik in der Strahlentherapie$$x0
000302286 9201_ $$0I:(DE-He78)MU01-20160331$$kMU01$$lDKTK Koordinierungsstelle München$$x1
000302286 9201_ $$0I:(DE-He78)E050-20160331$$kE050$$lE050 KKE Strahlentherapie$$x2
000302286 980__ $$ajournal
000302286 980__ $$aVDB
000302286 980__ $$aI:(DE-He78)E040-20160331
000302286 980__ $$aI:(DE-He78)MU01-20160331
000302286 980__ $$aI:(DE-He78)E050-20160331
000302286 980__ $$aUNRESTRICTED