000303405 001__ 303405
000303405 005__ 20250810022010.0
000303405 0247_ $$2doi$$a10.1148/ryai.240777
000303405 0247_ $$2pmid$$apmid:40767616
000303405 0247_ $$2altmetric$$aaltmetric:180077116
000303405 037__ $$aDKFZ-2025-01641
000303405 041__ $$aEnglish
000303405 082__ $$a610
000303405 1001_ $$00000-0002-6204-571X$$aHäntze, Hartmut$$b0
000303405 245__ $$aSegmenting Whole-Body MRI and CT for Multiorgan Anatomic Structure Delineation.
000303405 260__ $$aOak Brook, IL$$bRSNA$$c2025
000303405 3367_ $$2DRIVER$$aarticle
000303405 3367_ $$2DataCite$$aOutput Types/Journal article
000303405 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1754571617_25076
000303405 3367_ $$2BibTeX$$aARTICLE
000303405 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000303405 3367_ $$00$$2EndNote$$aJournal Article
000303405 500__ $$aepub
000303405 520__ $$a'Just Accepted' papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop and validate MRSegmentator, a retrospective cross-modality deep learning model for multiorgan segmentation of MRI scans. Materials and Methods This retrospective study trained MRSegmentator on 1,200 manually annotated UK Biobank Dixon MRI sequences (50 participants), 221 in-house abdominal MRI sequences (177 patients), and 1228 CT scans from the TotalSegmentator-CT dataset. A human-in-the-loop annotation workflow leveraged cross-modality transfer learning from an existing CT segmentation model to segment 40 anatomic structures. The model's performance was evaluated on 900 MRI sequences from 50 participants in the German National Cohort (NAKO), 60 MRI sequences from AMOS22 dataset, and 29 MRI sequences from TotalSegmentator-MRI. Reference standard manual annotations were used for comparison. Metrics to assess segmentation quality included Dice Similarity Coefficient (DSC). Statistical analyses included organ-and sequence-specific mean ± SD reporting and two-sided t tests for demographic effects. Results 139 participants were evaluated; demographic information was available for 70 (mean age 52.7 years ± 14.0 [SD], 36 female). Across all test datasets, MRSegmentator demonstrated high class wise DSC for well-defined organs (lungs: 0.81-0.96, heart: 0.81-0.94) and organs with anatomic variability (liver: 0.82-0.96, kidneys: 0.77-0.95). Smaller structures showed lower DSC (portal/splenic veins: 0.64-0.78, adrenal glands: 0.56-0.69). The average DSC on the external testing using NAKO data, ranged from 0.85 ± 0.08 for T2-HASTE to 0.91 ± 0.05 for in-phase sequences. The model generalized well to CT, achieving mean DSC of 0.84 ± 0.12 on AMOS CT data. Conclusion MRSegmentator accurately segmented 40 anatomic structures on MRI and generalized to CT; outperforming existing open-source tools. Published under a CC BY 4.0 license.
000303405 536__ $$0G:(DE-HGF)POF4-315$$a315 - Bildgebung und Radioonkologie (POF4-315)$$cPOF4-315$$fPOF IV$$x0
000303405 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
000303405 7001_ $$00009-0007-4119-1033$$aXu, Lina$$b1
000303405 7001_ $$00000-0001-7303-2650$$aMertens, Christian J$$b2
000303405 7001_ $$00009-0003-5914-3233$$aDorfner, Felix J$$b3
000303405 7001_ $$aDonle, Leonhard$$b4
000303405 7001_ $$00000-0001-9770-8555$$aBusch, Felix$$b5
000303405 7001_ $$aKader, Avan$$b6
000303405 7001_ $$00000-0001-8724-4718$$aZiegelmayer, Sebastian$$b7
000303405 7001_ $$00000-0002-8530-6783$$aBayerl, Nadine$$b8
000303405 7001_ $$aNavab, Nassir$$b9
000303405 7001_ $$00000-0002-5683-5889$$aRueckert, Daniel$$b10
000303405 7001_ $$00000-0001-6107-3009$$aSchnabel, Julia$$b11
000303405 7001_ $$00000-0002-2122-2003$$aAerts, Hugo J W L$$b12
000303405 7001_ $$00000-0002-9605-0728$$aTruhn, Daniel$$b13
000303405 7001_ $$00000-0002-7460-3942$$aBamberg, Fabian$$b14
000303405 7001_ $$aWeiss, Jakob$$b15
000303405 7001_ $$00000-0002-1576-1481$$aSchlett, Christopher L$$b16
000303405 7001_ $$00000-0003-1823-1037$$aRinghof, Steffen$$b17
000303405 7001_ $$00000-0001-7584-6527$$aNiendorf, Thoralf$$b18
000303405 7001_ $$00000-0003-1568-767X$$aPischon, Tobias$$b19
000303405 7001_ $$aKauczor, Hans-Ulrich$$b20
000303405 7001_ $$aNonnenmacher, Tobias$$b21
000303405 7001_ $$00000-0003-4889-1036$$aKröncke, Thomas$$b22
000303405 7001_ $$aVölzke, Henry$$b23
000303405 7001_ $$00000-0003-3100-1092$$aSchulz-Menger, Jeanette$$b24
000303405 7001_ $$0P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aMaier-Hein, Klaus$$b25$$udkfz
000303405 7001_ $$aHering, Alessa$$b26
000303405 7001_ $$00000-0001-8157-8055$$aProkop, Mathias$$b27
000303405 7001_ $$00000-0003-2028-8972$$avan Ginneken, Bram$$b28
000303405 7001_ $$00000-0002-1922-0826$$aMakowski, Marcus R$$b29
000303405 7001_ $$aAdams, Lisa C$$b30
000303405 7001_ $$00000-0001-9249-8624$$aBressem, Keno K$$b31
000303405 773__ $$0PERI:(DE-600)2960483-7$$a10.1148/ryai.240777$$gp. e240777$$pnn$$tRadiology: artificial intelligence$$vnn$$x2638-6100$$y2025
000303405 909CO $$ooai:inrepo02.dkfz.de:303405$$pVDB
000303405 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aDeutsches Krebsforschungszentrum$$b25$$kDKFZ
000303405 9131_ $$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$$x0
000303405 9141_ $$y2025
000303405 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-02
000303405 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-02
000303405 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-02
000303405 915__ $$0StatID:(DE-HGF)0112$$2StatID$$aWoS$$bEmerging Sources Citation Index$$d2025-01-02
000303405 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-02
000303405 9201_ $$0I:(DE-He78)E230-20160331$$kE230$$lE230 Medizinische Bildverarbeitung$$x0
000303405 980__ $$ajournal
000303405 980__ $$aVDB
000303405 980__ $$aI:(DE-He78)E230-20160331
000303405 980__ $$aUNRESTRICTED