Automated Deep Learning Segmentation and Quantification of Epicardial Adipose Tissue from Coronary Computed Tomography Angiography: Validation and Clinical Implications.
Automated AI measurement of abdominal fat from routine heart CT scans enables routine cardiovascular risk assessment without extra analysis time.
This automated deep learning EAT quantification tool validated on CCTA demonstrates that epicardial adipose tissue—a biomarker increasingly recognized as a cardiovascular risk predictor—can be reliably measured without time-consuming manual expert segmentation. The automation enables scalable integration of EAT measurement into routine cardiac CT workflows, supporting its clinical adoption as a cardiometabolic risk biomarker.
What the study was
- Study design
- Automated segmentation algorithm validation study against manual expert measurement
- Population
- Cardiac CT angiography patients requiring epicardial adipose tissue quantification
- Category
- Diagnostics
- Maturity
- Validated
- Journal
- Journal of imaging informatics in medicine
Why it surfaced
Validated automated EAT segmentation from CCTA reduces a major barrier to clinical adoption of this emerging cardiovascular risk biomarker; directly applicable to existing cardiac CT workflows.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.