Artificial Intelligence-Based CT-Derived Fractional Flow Reserve (CT-FFR)

Abstract

Coronary computed tomography angiography (cCTA) is an evolving, noninvasive first-line strategy for the evaluation of suspected coronary artery disease (CAD). A technique named computed tomography angiography-derived fractional flow reserve (CT-FFR) is an alternative method for detecting hemodynamically significant coronary stenosis, based in coronary geometries extracted from conventional CT images. Recent studies have shown that CT-FFR can be interpreted in the same way as the invasive FFR, which is the gold standard of coronary hemodynamics assessment. In recent years, artificial intelligence (AI) and, in particular, the application of machine learning (ML) algorithms have been developed as a technical approach of CT-FFR for improved decision pathways, risk stratification, and outcome prediction in a more objective, reproducible, and rational manner. AI is based on computer science and mathematics depending on big data, high performance computational infrastructure, and applied algorithms. The application of ML in daily routine clinical practice may hold potential to improve imaging workflow and to promote better outcome prediction and more effective decision-making in patient management, like improved therapeutic guidance to efficiently justify the management of patients with suspected coronary artery disease.KeywordsCoronary computed tomography angiographyFractional flow reserveCT-derived fractional flow reserveMachine learningArtificial intelligenceCoronary artery disease