Automated Muscle and Fat Segmentation in Computed Tomography for Comprehensive Body Composition Analysis

2025-02-13

AI Summary

Current CT-based body composition analysis lacks publicly available, standardized, and generalizable automated tools across diverse clinical settings. To address this, we propose the first open-source, end-to-end CT body composition analysis system covering thoracic, abdominal, and pelvic regions. Our method employs an anatomy-guided multi-scale U-Net architecture, robust to vendor-specific CT intensity distributions, enabling accurate segmentation of skeletal muscle, subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), and—novelly—muscle fat infiltration (MFI), with experimental validation. On internal and external datasets, Dice scores exceed 89% for muscle, SAT, and VAT—outperforming public benchmarks by 2.40% and 10.26%, respectively. Key 2D/3D quantitative metrics—including skeletal muscle index (SMI), VAT/SAT ratio, and muscle density—achieve mean relative absolute error <10%. The system is designed for broad clinical deployment in cardiology, metabolism, oncology, nutrition, and critical care.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Evaluation and Analysis
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Large-scale security measurements

Abstract

Body composition assessment using CT images can potentially be used for a number of clinical applications, including the prognostication of cardiovascular outcomes, evaluation of metabolic health, monitoring of disease progression, assessment of nutritional status, prediction of treatment response in oncology, and risk stratification for surgical and critical care outcomes. While multiple groups have developed in-house segmentation tools for this analysis, there are very limited publicly available tools that could be consistently used across different applications. To mitigate this gap, we present a publicly accessible, end-to-end segmentation and feature calculation model specifically for CT body composition analysis. Our model performs segmentation of skeletal muscle, subcutaneous adipose tissue (SAT), and visceral adipose tissue (VAT) across the chest, abdomen, and pelvis area in axial CT images. It also provides various body composition metrics, including muscle density, visceral-to-subcutaneous fat (VAT/SAT) ratio, muscle area/volume, and skeletal muscle index (SMI), supporting both 2D and 3D assessments. The model is shared for public use. To evaluate the model, the segmentation was applied to both internal and external datasets, with body composition metrics analyzed across different age, sex, and race groups. The model achieved high dice coefficients on both internal and external datasets, exceeding 89% for skeletal muscle, SAT, and VAT segmentation. The model outperforms the benchmark by 2.40% on skeletal muscle and 10.26% on SAT compared to the manual annotations given by the publicly available dataset. Body composition metrics show mean relative absolute errors (MRAEs) under 10% for all measures. Furthermore, the model provided muscular fat segmentation with a Dice coefficient of 56.27%, which can be utilized for additional analyses as needed.

Problem

• Automated segmentation of muscle and fat in CT images
• Publicly accessible model for body composition analysis
• High accuracy in skeletal muscle and fat segmentation

Innovation

• Publicly accessible end-to-end segmentation model
• Comprehensive muscle and fat segmentation
• High accuracy across diverse datasets