Back to all news
AI Enables Rapid Body Composition Analysis on Routine MRI to Predict Cardiometabolic Risk
An open-source AI tool can quickly and accurately assess body composition from routine MRI, helping identify patients at elevated cardiometabolic risk.
Key Details
- 1Study analyzed 33,539 UK Biobank participants without prior diabetes, MI, or stroke using whole-body MRI.
- 2Open-source AI model estimated subcutaneous/visceral adipose tissue, skeletal muscle volume, and fat fraction in under 3 minutes per scan.
- 3AI-derived visceral fat and skeletal muscle fat fraction were independently associated with incident diabetes and major cardiovascular events over median 4.8 years follow-up.
- 4Associations were adjusted for traditional risk factors, BMI, and waist circumference.
- 5Visceral adipose tissue, but not subcutaneous fat, was a key predictor of future risk, corroborating previous findings.
Why It Matters
This work demonstrates the clinical utility and technical feasibility of using AI to extract prognostic body composition data from existing routine MRI scans, potentially enabling radiologists to flag high-risk patients for early intervention without workflow disruption.
Source
EurekAlert
Related News
•EurekAlert
NIH-Backed AI Model Predicts Cancer Survival Using Single-Cell Data
Researchers have developed scSurvival, a machine learning tool that uses single-cell tumor data to accurately predict cancer patient survival and identify high-risk cell populations.
•EurekAlert
Deep Learning Pathomics Platform Improves Immunotherapy Prediction in Lung Cancer
A deep learning pathomics platform accurately predicts immunotherapy response in metastatic NSCLC using routine pathology slides.
•EurekAlert
AI Pathology Model Outperforms PD-L1 in Predicting NSCLC Immunotherapy Response
MD Anderson's Path-IO machine learning platform accurately predicts immunotherapy responses in metastatic non-small cell lung cancer, surpassing current biomarker standards.