Health AI Central
Peer-Reviewed Publication
Eur Radiol2026;36(4):2548-2562.April 1, 2026Journal Article

VIBESegmentator: full body MRI segmentation for the NAKO and UK Biobank.

Robert Graf1,2, Paul Platzek3, Evamaria Olga Riedel3, Constanze Ramschütz3, Sophie Starck4, Hendrik K Möller3,4, Matan Atad3,4, Henry Völzke5, Robin Bülow6, Carsten Oliver Schmidt5, Julia Rüdebusch5, Matthias Jung7, Marco Reisert7, Jakob Weiss7, Maximilian T Löffler3,7, Fabian Bamberg7, Benedikt Wiestler3, Johannes C Paetzold8, Daniel Rueckert4,9, Jan Stefan Kirschke3
1Department of Diagnostic and Interventional Neuroradiology, School of Medicine, TUM University Hospital Neuro-Kopf-Zentrum Ismaninger Str. 22, 81675, München, Germany. robert.graf@tum.de.
2Institut für KI und Informatik in der Medizin, TUM University Hospital Technical University of Munich Ismaninger Str. 22, 81675, München, Germany. robert.graf@tum.de.
3Department of Diagnostic and Interventional Neuroradiology, School of Medicine, TUM University Hospital Neuro-Kopf-Zentrum Ismaninger Str. 22, 81675, München, Germany.
4Institut für KI und Informatik in der Medizin, TUM University Hospital Technical University of Munich Ismaninger Str. 22, 81675, München, Germany.
5Institut für Community Medicine, Abteilung SHIP-KEF, University Medicine Greifswald, Walter Rathenau Str. 48, 5. Etage, 17475, Greifswald, Germany.
6Institute for Diagnostic Radiology and Neuroradiology, University Medicine Greifswald, Ferdinand-Sauerbruch-Straße, 17475, Greifswald, Germany.
7Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg Hugstetter Str. 55, 79106, Freiburg, Germany.
8Department of Radiology, Weill Cornell Medicine, 1300 York Avenue, New York, NY, 10065, USA.
9Department of Computing, Imperial College London, Room 568, Huxley Building, 180 Queen's Gate, London, SW7 2AZ, UK.
PubMed PMC DOI PDF

Abstract

OBJECTIVES: To present a publicly available deep learning-based torso segmentation model that provides comprehensive voxel-wise coverage, including delineations that extend to the boundaries of anatomical compartments. MATERIALS AND METHODS: We extracted preliminary segmentations from TotalSegmentator, spine, and body composition models for magnetic resonance tomography (MR) images, then improved…

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.

Create Free AccountSign In

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.