Title: Automatic stenosis grading system for diagnosing coronary artery disease using coronary angiogram
Authors: A.H. Nandhu Kishore; VE. Jayanthi
Addresses: Department of Computer Science and Engineering, PSNA College of Engineering and Technology, Kothandaraman Nagar, Dindigul, 624 622, Tamil Nadu, India ' Department of Electronics and Communication Engineering, PSNA College of Engineering and Technology, Kothandaraman Nagar, Dindigul, 624 622, Tamil Nadu, India
Abstract: The coronary angiogram is considered as the golden standard for diagnosing the coronary artery disease. The paper proposes a system that helps to describe the level of stenosis in coronary angiogram image by using mathematical morphology and thresholding technique. A novel method is introduced to determine the percentage of stenosis and its grading. Based on the diagnostic results, myocardial infarction (MI) is treated well-in-advance. A real time clinical dataset consisting of 25 conventional coronary angiographies with 865 frames is used to evaluate the performance of the proposed system. The execution of the proposed system is inspected by a cardiologist and confirmed the system has produced excellent segmentation and stenosis grading automatically. Sensitivity, specificity, accuracy and precision of the system are 94.74%, 83.33%, 92% and 94.74%, respectively with an average computational time of 0.84 sec. Kappa value also shows perfect system agreement for stenosis grading.
Keywords: coronary artery disease; CAD; coronary angiogram; coronary artery segmentation; stenosis detection; stenosis grading.
International Journal of Biomedical Engineering and Technology, 2019 Vol.31 No.3, pp.260 - 277
Received: 11 Jan 2017
Accepted: 23 Mar 2017
Published online: 14 Oct 2019 *