ISSN / eISSN: 0033-8362 / 1826-6983
Karen M. O’Donnell¹, Saif A. Mehdi², Luciana P. Moretti²
1-Department of Cardiothoracic Imaging, Northshore Metropolitan University
2-Institute for Biomedical Informatics, Northshore Metropolitan University
Purpose: To validate an AI-based automated coronary artery calcium (CAC) scoring system applied to non-gated chest CT compared with dedicated ECG-gated cardiac CT.
Methods: In 432 patients undergoing both scan types, automated CAC scores from non-gated CT were compared with Agatston scores from cardiac CT. Agreement was analyzed using Bland–Altman plots and risk category classification.
Results: Automated non-gated scoring demonstrated strong correlation (r = 0.92) with cardiac CT. Risk categories matched in 84% of cases. Minor underestimation occurred at high CAC values (>400).
Conclusion: Automated CAC scoring on routine chest CT is a reliable alternative to dedicated cardiac CT for risk stratification, enabling opportunistic cardiovascular screening.
Keywords: coronary calcium scoring, AI in radiology, non-gated CT, cardiac imaging, cardiovascular risk
Please fill in the details below to request access to this article or subscribe for updates. Our team will contact you shortly.