Related Experiment Video
Updated: Jun 2, 2026
13:35
Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos
Published on: March 21, 2021
Artificial Intelligence-Based Body Composition Analysis Reveals Sex-Specific Prognostic Markers and Their Clinical
Tianxiang Li1,2,3, Tingting Liu1,2,3, Qian Yang4
1Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
Summary
Multidimensional body composition, assessed using AI, reveals sex-specific prognostic factors in gastric cancer (GC). These findings suggest body composition can aid in risk stratification for GC patients.
Area of Science:
- Oncology
- Medical Imaging
- Bioinformatics
Background:
- Conventional body composition assessment lacks multidimensional complexity in gastric cancer (GC).
- Understanding detailed body composition is crucial for GC patient prognosis.
Purpose of the Study:
- To systematically evaluate multidimensional body composition in GC.
- To determine the clinical relevance and prognostic value of body composition in GC patients.
Main Methods:
- Retrospective enrollment of 1196 GC patients and 983 healthy controls.
- AI-driven segmentation (nnU-Net) for body composition analysis.
- Development and external validation of sex-specific prognostic models using TCGA data.
Main Results:
- AI-derived body composition parameters showed sex-specific survival associations in GC.
- Higher muscle/fat indices and lower fat density correlated with better survival in surgical patients.
- Subcutaneous fat area improved survival in ICI-treated females; associations with tumor microenvironment noted.
Conclusions:
- Multidimensional body composition is significantly associated with GC prognosis.
- AI-assessed body composition may serve as a complementary biomarker for GC risk stratification.
