Comparison Of AI-based Coronary CTA Interpretation And QCA For Coronary Stenosis Evaluation

Introduction: Coronary CT angiography (CCTA) has become an established tool in the diagnostic work-up of patients with suspected coronary artery disease (CAD). Despite the high diagnostic performance, clinical CCTA interpretation has variability between readers with different degrees of correlation to invasive coronary angiography (ICA). AI-workflows could provide context to better interpret CCTA and overcome these limitations. We sought to evaluate the performance of a new AI-based tool by comparing the quantified stenosis severity with a gold-standard reference derived from invasive quantitative coronary angiography (QCA).