Clinical Applications of Artificial Intelligence in Cardiac CT: From Coronary CT Angiography to CT-Derived Fractional Flow Reserve and Myocardial Perfusion Imaging.
Authors
Affiliations (2)
Affiliations (2)
- Department of Radiology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- Faculty of Medical Imaging Technology, College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China. [email protected].
Abstract
Artificial intelligence (AI) has rapidly transformed cardiac CT, extending its clinical utility from coronary CT angiography (CCTA) to CT myocardial perfusion imaging (CT-MPI). This review outlines the current advances in and future perspectives on AI-aided cardiac CT across anatomical, functional, and prognostic dimensions. In CCTA, AI can automate calcium scoring, vessel segmentation, and plaque characterization, markedly improving workflow efficiency and reproducibility. Deep-learning models can allow accurate detection of coronary stenosis and plaque quantification, achieving diagnostic and prognostic performances comparable to those of invasive reference standards. Beyond anatomical assessment, machine learning-based CT-derived fractional flow reserve measurements can provide lesion-specific functional evaluation directly from routine CCTA scans, substantially improving computational efficiency over conventional fluid dynamics while maintaining diagnostic accuracy. In functional imaging, AI can facilitate automated quantification of myocardial blood flow and ischemic myocardial volume, showing excellent agreement with manual measurements and strong performance for ischemia detection and risk stratification. Emerging approaches for virtual perfusion modeling and deep-learning-based denoising have further expanded the noninvasive assessment of myocardial physiology and tissue characterization. Despite these advances, challenges in aligning AI development with clinical requirements, acquiring diverse and high-quality datasets, and translating algorithms into validated tools remain unresolved. Furthermore, the current evidence is limited by retrospective designs, selected validation cohorts, and insufficient external and prospective testing in complex real-world settings. Addressing these challenges through multidisciplinary collaboration, standardized protocols, and robust validation frameworks is critical for responsible integration of AI into routine cardiovascular imaging and for realizing its full potential in precision cardiovascular care.