PCA-based Polling Strategy in Machine Learning Framework for Coronary Artery Disease Risk Assessment in Intravascular Ultrasound: A Link between Carotid and Coronary Grayscale Plaque Morphology

• Published in: Computer methods and programs in biomedicine 2016-05, Vol.128, p.137-158
• Main Authors: Araki, Tadashi, MD, Ikeda, Nobutaka, MD, Shukla, Devarshi, BTech, Jain, Pankaj K., B.E, Londhe, Narendra D., PhD, Shrivastava, Vimal K., M.Tech, Banchhor, Sumit K., MTech, Saba, Luca, MD, Nicolaides, Andrew, PhD, Shafique, Shoaib, MD, Laird, John R., MD, Suri, Jasjit S., PhD, MBA, Fellow AIMBE
• Format: Article
• Language: English
• Subjects: Adult; Aged; Aged, 80 and over; Algorithms; Carotid Arteries - diagnostic imaging; Carotid IMT; Carotid Intima-Media Thickness; Computational Biology - methods; Computer-Aided Design; Coronary artery; Coronary artery disease; Coronary Artery Disease - diagnostic imaging; Coronary Vessels - diagnostic imaging; Female; Humans; Internal Medicine; IVUS; Machine Learning; Male; Middle Aged; Morphology; Other; PCA; Plaque, Atherosclerotic - diagnostic imaging; Principal Component Analysis - methods; Reproducibility of Results; Retrospective Studies; Risk assessment; Risk Assessment - methods; Stability; Strategy; Stratification; Support Vector Machine; Support vector machines; Ultrasonography
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2016.02.004

Highlights • Coronary artery disease risk assessment in intravascular ultrasound. • A link between carotid and coronary grayscale plaque morphology. • Principal component analysis (PCA) for dominant feature selection. • Classification accuracy of 98.43% and reliability index of 97.32%.