Researchers used AI to analyze over 66,000 whole-body MRI scans, creating a detailed body composition reference map linked to health risks.
Key Details
- 1Study analyzed MRI scans from 66,608 participants (mean age 57.7) in the UK Biobank and German National Cohort.
- 2AI created sex-, age-, and height-adjusted body composition metrics for fat and muscle distribution.
- 3Findings show high visceral fat increases diabetes risk by 2.26x, high intramuscular fat raises major cardiovascular risk by 1.54x, and low skeletal muscle ups all-cause mortality by 1.44x.
- 4Results indicate muscle quality and amount are independent health risk predictors, outperforming BMI.
- 5Researchers released an open-source web tool for calculating and comparing body composition z-scores.
- 6Routine scans (MRI/CT) can opportunistically provide these metrics without dedicated imaging.
Why It Matters
This research establishes AI-powered analysis of routine radiology exams as a powerful tool for quantifying body composition, enhancing risk stratification for cardiometabolic and oncologic diseases beyond conventional measures like BMI. The open-source reference curves and web-based calculator could drive broader clinical adoption of body composition metrics in radiology workflows.
Source
EurekAlert
Related News
•EurekAlert
AI-Enhanced Imaging Breaks Barriers in Complex Media for Biomedical Use
Researchers developed a physics-based machine learning imaging system that enhances visibility through complex media, holding promise for biomedical imaging.
•EurekAlert
AI Model Accelerates Accurate Dose Prediction for CyberKnife Radiotherapy
A physics- and spatially informed diffusion model accelerates Monte Carlo–level dose estimation for CyberKnife radiotherapy using planning CT and anatomical data.
•EurekAlert
New G-AUDIT Tool Detects Hidden Bias in Medical AI Training Data
Johns Hopkins and FDA researchers unveil G-AUDIT, a tool to identify hidden biases in medical AI datasets before model training.