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

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. Keywords: MR-Imaging, Segmentation, Vision, Application Domain, Supervised Learning, Type of Machine Learning © The Author(s) 2025. Published by the Radiological Society of North America under a CC BY 4.0 license. See also commentary by Tao in this issue.