BioCompNet: A Deep Learning Workflow Enabling Automated Body Composition Analysis toward Precision Management of Cardiometabolic Disorders

Jianyong Wei, Hongli Chen, Lijun Yao, Xuhong Hou, Rui Zhang, Liang Shi, J. F. Sun, Cheng Hu, Xiaoer Wei, Weiping JiaCyborg 2025 · DOI

TL;DR

This paper introduces BioCompNet, a novel deep learning workflow that automates the analysis of 15 body composition components from MRI scans, covering both abdominal and thigh regions. By integrating dual MRI sequences and a U-Net architecture, BioCompNet achieves high accuracy and significantly reduces analysis time, paving the way for more precise cardiometabolic risk assessment and clinical decision-making.

What Problem Does This Paper Address?

Cardiometabolic diseases (CMDs) like cardiovascular disease and type 2 diabetes are major global health burdens. Body composition (BC) – the proportions of bone, muscle, and fat – is increasingly recognized as a crucial biomarker for predicting CMD risk. However, traditional methods for quantifying BC from medical images are labor-intensive, time-consuming, and often lack comprehensive anatomical coverage. This creates a bottleneck for large-scale studies and routine clinical application, hindering the proactive identification and management of individuals at risk.

Methods

The core of BioCompNet is a deep learning workflow built upon a 2D U-Net architecture. Key methodological innovations include:

  • Dual-Parametric MRI Integration: The model leverages both fat- and water-sequence MRI images. The fat sequence excels at visualizing adipose tissue, while the water sequence provides better contrast for muscles, bones, and vessels. This dual-input approach enhances tissue differentiation and segmentation accuracy.
  • Hierarchical U-Net Architecture: A 2D U-Net is employed to handle the inherent anisotropy of MRI data (different resolutions in slice thickness vs. in-plane). This architecture allows for efficient feature extraction and segmentation across different spatial scales.
  • Comprehensive Anatomical Coverage: BioCompNet is designed to segment 15 distinct BC components across both the abdomen (vertebral bone, psoas muscle, core muscles, subcutaneous adipose tissue [SAT], visceral adipose tissue [VAT], etc.) and thigh regions (femur, muscle, SAT, IMAT, vessels). This is a significant expansion compared to previous studies that often focused only on abdominal fat.
  • Automated Post-processing: Beyond segmentation, the workflow includes automated post-processing steps to quantify morphological features (volume, circumference, area) and intermuscular adipose tissue (IMAT) using K-means clustering.
  • Semiautomated Annotation Strategy: To create high-quality ground truth data, an iterative model-assisted annotation process was used, combining initial manual segmentation with AI-driven refinement.

Datasets

  • Internal Dataset: The model was developed and internally validated using MRI data from 503 participants (aged 45-70) from a large-scale, community-based prospective cohort study investigating CMDs. This dataset was split into training (80%), internal validation (10%), and internal test (10%) sets.
  • External Dataset: For independent validation, 30 participants from a tertiary hospital underwent abdominal and/or thigh MRI. This dataset represents a different clinical population and potentially different scanning protocols.

Key Insights and Ideas

  • Dual-Sequence MRI is Crucial: Integrating both fat and water MRI sequences significantly improves segmentation performance compared to using either sequence alone, highlighting the complementary information they provide.
  • 2D U-Net Handles Anisotropy Well: The choice of a 2D U-Net architecture proved effective in managing the anisotropic nature of MRI data, outperforming 3D models in generalization to external datasets.
  • Comprehensive BC Analysis is Feasible and Valuable: BioCompNet demonstrates that it's possible to automate the quantification of a wide range of BC components across multiple body regions, offering a more holistic view of metabolic health.
  • Automation Dramatically Reduces Time: The most striking insight is the massive reduction in processing time, from over 2 hours manually to just over 7 seconds with BioCompNet, making large-scale analysis practical.

Key Results

  • High Segmentation Accuracy: BioCompNet achieved excellent average Dice Similarity Coefficients (DSCs): 0.944 for abdominal and 0.961 for thigh components on the internal test set, and 0.938 for abdominal and 0.936 for thigh on the external test set.
  • Robust Generalization: The model demonstrated strong performance on the independent external test set, outperforming benchmark models (2D and 3D nnU-Net) in generalization, particularly in the thigh region.
  • Excellent Agreement with Physicians: Interreader reliability (Intraclass Correlation Coefficient - ICC) for quantified features was excellent (≥ 0.881), and IMAT quantification showed a strong linear trend (Ptrend < 0.001) compared to physician ratings.
  • Massive Time Savings: The automated workflow reduced processing time from 128.8 ± 5.6 minutes per case to just 0.12 ± 0.001 minutes, a nearly 1000-fold speedup.

Limitations and Future Work

  • Low BMI Group Performance: Segmentation performance was slightly inferior in the low-BMI group (<18.5), likely due to underrepresentation in the training data and inherent challenges in visualizing adipose tissue in leaner individuals.
  • NAFLD Group Differences: Segmentation for VAT, IPAT, and RPAT was lower in the NAFLD group, suggesting that hepatic fat-related changes might affect imaging characteristics.
  • Vessel Segmentation Variability: Thigh vessel segmentation showed variability across subgroups, attributed to their small size and low pixel proportion.
  • Future Directions: The authors suggest expanding the training dataset with more diverse and balanced cohorts, exploring architectural modifications (e.g., multiscale feature extraction, attention mechanisms), and developing a user-friendly interface for clinicians to review and adjust outputs. Further research is needed to fully elucidate the clinical implications of these imaging-derived BC features for CMD risk stratification and treatment.

Summary updated

Abstract

Growing evidence highlights the importance of body composition (BC), including bone, muscle, and adipose tissue (AT), as a critical biomarker for cardiometabolic risk stratification. However, conventional methods for quantifying BC components using medical images are hindered by labor-intensive workflows and limited anatomical coverage. This study developed BioCompNet-an end-to-end deep learning workflow that integrates dual-parametric magnetic resonance imaging (MRI) sequences (water/fat) with a hierarchical U-Net architecture to enable fully automated quantification of 15 biomechanically critical BC components. BioCompNet targets 10 abdominal compartments (vertebral bone, psoas muscles, core muscles, subcutaneous AT [SAT], superficial SAT, deep SAT, intraperitoneal AT, retroperitoneal AT, visceral AT, and intermuscular AT [IMAT]) and 5 thigh compartments (femur, muscle, SAT, IMAT, and vessels). The workflow was developed on 8,048 MRI slices from a community-based cohort (<i>n</i> = 503) and independently validated on 240 MRI slices from a tertiary hospital (<i>n</i> = 30). The model's performance was benchmarked against expert annotations. On internal and external validation datasets, BioCompNet achieved average Dice similarity coefficients of 0.944 and 0.938 for abdominal compartments and 0.961 and 0.936 for thigh compartments, respectively. Excellent interreader reliability was observed (intraclass correlation coefficient ≥ 0.881) across all quantified features, and IMAT quantification showed a strong linear trend (<i>P</i> <sub>trend</sub> < 0.001) compared to physician-rated assessments. The workflow substantially reduced processing time from 128.8 ± 5.6 to 0.12 ± 0.001 min per case. By enabling rapid, accurate, and comprehensive volumetric analysis of BC components, BioCompNet establishes a scalable framework for precision cardiometabolic risk assessment and clinical decision support.
BibTeX
@inproceedings{wei2025biocompnet,
  author = {Jianyong Wei and Hongli Chen and Lijun Yao and Xuhong Hou and Rui Zhang and Liang Shi and J. F. Sun and Cheng Hu and Xiaoer Wei and Weiping Jia},
  title = {{BioCompNet: A Deep Learning Workflow Enabling Automated Body Composition Analysis toward Precision Management of Cardiometabolic Disorders}},
  booktitle = {Cyborg},
  year = {2025},
  doi = {10.34133/cbsystems.0381},
}
Figure