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

Häntze H, Xu L, Mertens CJ, Dorfner FJ, Donle L, Busch F, Kader A, Ziegelmayer S, Bayerl N, Navab N, Rueckert D, Schnabel J, Aerts HJ, Truhn D, Bamberg F, Weiss J, Schlett CL, Ringhof S, Niendorf T, Pischon T, Kauczor HU, Nonnenmacher T, Kröncke T, Völzke H, Schulz-Menger J, Maier-Hein K, Hering A, Prokop M, van Ginneken B, Makowski MR, Adams LC, Bressem KK (2025)

Publication Type: Journal article

Publication year: 2025

Journal

Radiology: Artificial Intelligence Radiological Society of North America

Book Volume: 7

Article Number: e240777

Journal Issue: 6

DOI: 10.1148/ryai.240777

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 human-in-the-loop annotation workflow used 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 the Multi-Modality Abdominal Multi-Organ Segmentation Challenge 2022 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 means ± SDs reporting and two-sided t tests for demographic effects. Results: One-hundred thirty-nine participants were evaluated; demographic information was available for 70 (mean age, 52.7 years ± 14.0 [SD], 36 female participants). 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 or 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-weighted half-Fourier acquisition single-shot turbo spin echo to 0.91 ± 0.05 for in-phase sequences. The model generalized well to CT, achieving a mean DSC of 0.84 ± 0.12 on abdominal multiorgan segmentation CT data. Conclusion: MRSegmentator accurately segmented 40 anatomic structures on MRI and generalized to CT, outperforming existing open-source tools.

Authors with CRIS profile

Nadine Bayerl Institute of Radiology

Involved external institutions

Max-Delbrück-Centrum für Molekulare Medizin in der Helmholtz-Gemeinschaft / Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC) DE Germany (DE) Universitätsklinikum Heidelberg DE Germany (DE) Universitätsmedizin Greifswald / Universitätsklinikum Greifswald DE Germany (DE) Radboud University Nijmegen Medical Centre / Radboudumc of voluit Radboud Universitair Medisch Centrum (UMC) NL Netherlands (NL) Deutsches Krebsforschungszentrum (DKFZ) DE Germany (DE) Klinikum rechts der Isar DE Germany (DE) Humboldt-Universität zu Berlin DE Germany (DE) Universitätsklinikum Freiburg DE Germany (DE) Harvard University US United States (USA) (US) Universitätsklinikum Aachen (UKA) DE Germany (DE) Universitätsklinikum Augsburg DE Germany (DE) Technische Universität München (TUM) DE Germany (DE)

How to cite

APA:

Häntze, H., Xu, L., Mertens, C.J., Dorfner, F.J., Donle, L., Busch, F.,... Bressem, K.K. (2025). Segmenting Whole-Body MRI and CT for Multiorgan Anatomic Structure Delineation. Radiology: Artificial Intelligence, 7(6). https://doi.org/10.1148/ryai.240777

MLA:

Häntze, Hartmut, et al. "Segmenting Whole-Body MRI and CT for Multiorgan Anatomic Structure Delineation." Radiology: Artificial Intelligence 7.6 (2025).

BibTeX: Download