A Framework for Cross-Domain Generalization in Coronary Artery Calcium Scoring Across Gated and Non-Gated Computed Tomography.
Authors
Affiliations (4)
Affiliations (4)
- Center for Applied AI, University of Kentucky, Lexington, KY.
- Department of Medicine, Division of Cardiovascular Medicine and the Gill Heart and Vascular Institute, University of Kentucky, Lexington, KY.
- Department of Radiology, College of Medicine, University of Kentucky, Lexington, KY.
- EduceLab, University of Kentucky, Lexington, KY.
Abstract
Coronary artery calcium (CAC) scoring is a key predictor of cardiovascular risk, but relies on ECG-gated CT scans, restricting its use to specialized cardiac imaging settings. We introduce an automated framework for CAC detection and lesion-specific Agatston scoring that works across gated and non-gated CT scans. At its core is <b>CARD-ViT</b>, a self-supervised Vision Transformer trained exclusively on gated CT data using DINO. Without any non-gated training data, our framework achieves 0.707 accuracy and Cohen's κ of 0.528 on the publicly available Stanford non-gated dataset, matching models trained directly on non-gated scans. On gated test sets, the framework achieves 0.910 accuracy with Cohen's κ scores of 0.871 and 0.874 across independent datasets, demonstrating risk stratification. Results demonstrate the feasibility of cross-domain CAC scoring from gated to non-gated domains, supporting scalable cardiovascular screening in routine chest imaging without additional scans or annotations.