Peer-Reviewed Publication
Radiol Artif Intell2025;7(6):e240777.November 1, 2025Journal Article

Segmenting Whole-Body MRI and CT for Multiorgan Anatomic Structure Delineation.

Hartmut Häntze1,2, Lina Xu1, Christian J Mertens3, Felix J Dorfner1,4, Leonhard Donle1, Felix Busch3, Avan Kader3, Sebastian Ziegelmayer3, Nadine Bayerl5, Nassir Navab6, Daniel Rueckert7,8,9, Julia Schnabel9, Hugo J W L Aerts10,11,12, Daniel Truhn13, Fabian Bamberg14, Jakob Weiss14, Christopher L Schlett14, Steffen Ringhof14, Thoralf Niendorf15, Tobias Pischon15, Hans-Ulrich Kauczor16, Tobias Nonnenmacher16, Thomas Kröncke17, Henry Völzke18, Jeanette Schulz-Menger19, Klaus Maier-Hein20, Alessa Hering2, Mathias Prokop2, Bram van Ginneken2, Marcus R Makowski3, Lisa C Adams3, Keno K Bressem3,21
1Department of Radiology, Charité - Universitätsmedizin Berlin corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany.
2Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, the Netherlands.
3Department of Diagnostic and Interventional Radiology, School of Medicine and Health, Klinikum rechts der Isar, TUM University Hospital, Technical University of Munich, Munich, Germany.
4Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School, Charlestown, Mass.
5Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany.
6Laboratory for Computer Aided Medical Procedures, Technical University of Munich, Munich, Germany.
7Chair for AI in Medicine and Healthcare, Klinikum rechts der Isar, Technical University Munich, Munich, Germany.
8Department of Computing, Imperial College London, London, UK.
9Institute for Advanced Study, Technical University Munich, Munich, Germany.
10Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, Mass.
11Departments of Radiation Oncology and Radiology, Dana-Farber Cancer Institute and Brigham and Women's Hospital, Boston, Mass.
12Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, the Netherlands.
13Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany.
14Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany.
15Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany.
16Clinic for Diagnostic and Interventional Radiology, Heidelberg University Hospital, Heidelberg, Germany.
17Department of Diagnostic and Interventional Radiology and Neuroradiology, Universitätsklinikum Augsburg, Augsburg, Germany.
18Institute for Community Medicine, University Medicine Greifswald, Greifswald, Germany.
19Experimental Clinical Research Center, Charité - Universitätsmedizin Berlin corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany.
20Division of Medical Image Computing, German Cancer Research Center, Heidelberg, Germany.
21Department of Cardiovascular Radiology and Nuclear Medicine, School of Medicine and Health, German Heart Center, TUM University Hospital, Technical University of Munich, Lazarettstr 36, 80636 Munich, Germany.

Abstract

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 1200 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 hum…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.