TY - JOUR
T1 - Segmenting Whole-Body MRI and CT for Multiorgan Anatomic Structure Delineation
AU - Häntze, Hartmut
AU - Xu, Lina
AU - Mertens, Christian J
AU - Dorfner, Felix J
AU - Donle, Leonhard
AU - Busch, Felix
AU - Kader, Avan
AU - Ziegelmayer, Sebastian
AU - Bayerl, Nadine
AU - Navab, Nassir
AU - Rueckert, Daniel
AU - Schnabel, Julia
AU - Aerts, Hugo J W L
AU - Truhn, Daniel
AU - Bamberg, Fabian
AU - Weiss, Jakob
AU - Schlett, Christopher L
AU - Ringhof, Steffen
AU - Niendorf, Thoralf
AU - Pischon, Tobias
AU - Kauczor, Hans-Ulrich
AU - Nonnenmacher, Tobias
AU - Kröncke, Thomas
AU - Völzke, Henry
AU - Schulz-Menger, Jeanette
AU - Maier-Hein, Klaus
AU - Hering, Alessa
AU - Prokop, Mathias
AU - van Ginneken, Bram
AU - Makowski, Marcus R
AU - Adams, Lisa C
AU - Bressem, Keno K
PY - 2025/11
Y1 - 2025/11
N2 - 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.
AB - 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.
U2 - 10.1148/ryai.240777
DO - 10.1148/ryai.240777
M3 - Article
SN - 2638-6100
VL - 7
JO - Radiology: Artificial Intelligence
JF - Radiology: Artificial Intelligence
IS - 6
M1 - e240777
ER -