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
Brain-Inspired Training Enhances AI Reliability and Uncertainty Recognition
KAIST researchers developed a brain-inspired AI training method that reduces overconfidence and improves the recognition of unfamiliar data.
•EurekAlert
AI and PS-OCT Enhance Early Keratoconus Detection
AI combined with polarization-sensitive OCT enables earlier and more accurate detection of subclinical keratoconus compared to standard tomography.
•EurekAlert
Retrieval-Augmented AI Enhances Reliability in Cancer Care Applications
Retrieval-augmented generation AI models offer increased accuracy and transparency for oncology applications, including imaging support, compared to standard AI tools.