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 Model 'CMR-CLIP' Raises Cardiac MRI Interpretation Accuracy
CMR-CLIP, a novel AI model, significantly improves cardiac MRI interpretation by learning from clinical reports instead of manual labels.
•EurekAlert
AI Stretchable Computing Patch Enables Real-Time On-Body Health Analysis
University of Chicago engineers introduce a stretchable skin patch that applies AI to instantly analyze health data on the body.
•EurekAlert
MD Anderson Names Albert Koong, MD, PhD, as Chief Scientific Officer
Albert Koong, MD, PhD, becomes the new Chief Scientific Officer at UT MD Anderson Cancer Center.