A Machine Learning-Based Method for Intracoronary OCT Segmentation and Vulnerable Coronary Plaque Cap Thickness Quantification

Abstract

Accurate cap thickness quantification is of fundamental importance for vulnerable plaque detection in cardiovascular research. A segmentation method for intracoronary optical coherence tomography (OCT) image based on least squares support vector machine (LS-SVM) was performed to characterize plaque component borders and quantify fibrous cap thickness. Manual segmentation of OCT images were performed by experts based on combination of virtual-histology intravascular ultrasound (VH-IVUS) and OCT images and used as gold standard. The segmentation methods based on LS-SVM provided accurate plaque cap thickness (an 8.6% error by LS-SVM vs. 71% error by IVUS50) serving as solid basis for plaque modeling and assessment.