Peer-Reviewed Publication
Commun Med (Lond)2026;6(1)August 29, 2026Journal Article

Pooled two-cohort MRI body composition phenotyping with open-source deep learning.

Christian J Mertens1, Hartmut Häntze1,2, Sebastian Ziegelmayer1, Jakob Nikolas Kather3,4,5, Daniel Truhn6, Su Hwan Kim1, Felix Busch1, Dominik Weller1, Benedikt Wiestler7, Markus Graf1, Fabian Bamberg8, Christopher L Schlett8, Jakob B Weiss8, Steffen Ringhof8, Elif Can8, Jeanette Schulz-Menger9,10,11,12, Thoralf Niendorf13,14, Jacqueline Lammert15, Isabel Molwitz16, Avan Kader1, Alessa Hering2, Aymen Meddeb17, Jawed Nawabi17, Matthias B Schulze18,19, Thomas Keil20, Stefan N Willich20, Lilian Krist20, Martin Hadamitzky21, Anke Hannemann22, Florian Bassermann23,24, Daniel Rueckert25,26,27, Tobias Pischon28,29,30, Alexander Hapfelmeier31, Marcus R Makowski1, Keno K Bressem1,21, Lisa C Adams32
1Institute for Diagnostic and Interventional Radiology, School of Medicine and Health, TUM Klinikum, Technical University of Munich (TUM), Munich, Germany.
2Diagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands.
3Else Kroener Fresenius Center for Digital Health, Dresden University of Technology, Dresden, Germany.
4Department of Medicine I, University Hospital Dresden, Dresden, Germany.
5Medical Oncology, National Center for Tumour Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany.
6Department for Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany.
7Department of Diagnostic and Interventional Neuroradiology, School of Medicine and Health, TUM Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany.
8Department of Diagnostic and Interventional Radiology, Medical Center, University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg im Breisgau, Germany.
9Charité, Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, ECRC Experimental and Clinical Research Center, Berlin, Germany.
10Working Group on CMR, Experimental and Clinical Research Center, a Joint Cooperation Between the Max-Delbrück-Center for Molecular Medicine and the Charité, Universitätsmedizin Berlin, Berlin, Germany.
11DZHK (German Centre for Cardiovascular Research), Berlin, Germany.
12Department of Cardiology and Nephrology, Helios Hospital Berlin-Buch, Berlin, Germany.
13Max-Delbrück-Center for Molecular Medicine in the Helmholtz Association (MDC), Berlin Ultrahigh Field Facility (B.U.F.F.), Berlin, Germany.
14Experimental and Clinical Research Center (ECRC), Charité-Universitätsmedizin Berlin, A Joint Cooperation Between the Charité Medical Faculty and the Max-Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany.
15Department of Gynecology and Center for Hereditary Breast and Ovarian Cancer, Technical University of Munich (TUM), School of Medicine and Health, Klinikum rechts der Isar, TUM University Hospital, Munich, Germany.
16Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.
17Department of Neuroradiology, Charité Universitätsmedizin Berlin, Berlin, Germany.
18Department of Molecular Epidemiology, German Institute of Human Nutrition Potsdam-Rehbrücke, Nuthetal, Germany.
19Institute of Nutrition Science, University of Potsdam, Nuthetal, Germany.
20Institute of Social Medicine, Epidemiology and Health Economics, Charité, Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.
21Department of Cardiovascular Radiology and Nuclear Medicine, German Heart Center Munich, TUM University Hospital, Munich, Germany.
22Institute of Clinical Chemistry and Laboratory Medicine, University Medicine Greifswald, Greifswald, Germany.
23Department of Medicine III, Technical University of Munich, TUM School of Medicine and Health, Munich, Germany.
24Center for Translational Cancer Research (TranslaTUM), Technical University of Munich, TUM School of Medicine and Health, Munich, Germany.
25Munich Center for Machine Learning (MCML), Munich, Germany.
26Chair of AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany.
27Department of Computing, Imperial College London, London, UK.
28Molecular Epidemiology Research Group, Max-Delbrück-Center for Molecular Medicine in the Helmholtz Association (MDC), Berlin, Germany.
29Max-Delbrück-Center for Molecular Medicine in the Helmholtz Association (MDC), Biobank Technology Platform, Berlin, Germany.
30Charité, Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.
31Technische Universität of Munich, School of Medicine and Health, TUM University Hospital Rechts der Isar, Institute of AI and Informatics in Medicine and Institute of General Practice and Health Services Research, Munich, Germany.
32Institute for Diagnostic and Interventional Radiology, School of Medicine and Health, TUM Klinikum, Technical University of Munich (TUM), Munich, Germany. lisa.adams@tum.de.

Abstract

BACKGROUND: Body mass index fails to capture variation in fat and muscle distribution that determines metabolic health and disease risk. MRI enables radiation-free quantification of regional body composition, yet scalable open-source tools applied in pooled cohorts with differing acquisition protocols have been lacking. METHODS: MRSegmentator, an open-source nnU-Net-based pipeline, was applied to…

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.