TotalVibeSegmentator: Full Body MRI Segmentation for the NAKO and UK Biobank

2024-05-31

AI Summary

This study addresses the challenge of voxel-wise fine-grained segmentation of whole-body MRI (VIBE sequence) from two large epidemiological cohorts—NAKO and UK Biobank—by proposing the first end-to-end deep learning framework specifically designed for torso-wide segmentation. Methodologically, it builds upon the nnUNet architecture, integrating knowledge from TotalSegmentator, spinal anatomical priors, and body composition segmentation, and employs multi-stage iterative retraining for optimization. It achieves, for the first time on publicly available data, fine-grained, boundary-sensitive segmentation of 71 organs and 22 vertebral bodies. On an independent test set, the model attains a mean Dice score of 0.89 ± 0.07; abdominal organ Dice scores all exceed 0.90 (pancreas: 0.70). The fully open-source model supports batch inference at scale (≥1,000 subjects), providing a reproducible, high-accuracy, standardized segmentation tool for large-scale imaging epidemiology studies.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Objectives: To present a publicly available torso segmentation network for large epidemiology datasets on volumetric interpolated breath-hold examination (VIBE) images. Materials&Methods: We extracted preliminary segmentations from TotalSegmentator, spine, and body composition networks for VIBE images, then improved them iteratively and retrained a nnUNet network. Using subsets of NAKO (85 subjects) and UK Biobank (16 subjects), we evaluated with Dice-score on a holdout set (12 subjects) and existing organ segmentation approach (1000 subjects), generating 71 semantic segmentation types for VIBE images. We provide an additional network for the vertebra segments 22 individual vertebra types. Results: We achieved an average Dice score of 0.89 +- 0.07 overall 71 segmentation labels. We scored>0.90 Dice-score on the abdominal organs except for the pancreas with a Dice of 0.70. Conclusion: Our work offers a detailed and refined publicly available full torso segmentation on VIBE images.

Problem

• Develops a deep learning model for full torso MRI and CT segmentation
• Provides comprehensive voxel-wise coverage of anatomical structures
• Creates publicly available segmentation tool for large biomedical studies

Innovation

• Iteratively improved nnUNet model for torso segmentation
• Trained on multi-source data including NAKO and UK Biobank
• Segments 71-72 anatomical structures with comprehensive coverage