Real-Time Explainable Detection of Stenosis in Coronary Angiography

Keith A Dufendach, Emma Erickson, Cecilia Morales, Robert Edman, David Kaczorowski, Artur Dubrawski

Abstract: Coronary angiography is the gold standard for evaluating coronary artery disease and determining the appropriate treatment strategy for a patient. The aim of this study is to use a machine learning (ML)-based object detection algorithm to identify images with clinically significant stenoses and provide explainable output by localizing the area of stenosis within each image.