Automated characterization and classification of coronary atherosclerotic plaques for intravascular optical coherence tomography

This study aimed to propose a novel plaque characterization algorithm to automatically characterize and classify the atherosclerotic plaques (fibrous, calcific, and lipid-rich). First, nongeometric features such as Fisher vector, principal component analysis, histogram of the oriented gradient, and local binary pattern were investigated and adapted to two geometric features (basic feature and texture feature) to characterize the plaques. Second, for automated classification of the plaques, a hard example mining strategy was introduced to train support vector machine classifier and improve the effectiveness of training data. Third, to demonstrate the relationship between the selected features and the plaque classification accuracy, different feature compositions and comparisons were presented. The contribution of key features to the final classification was revealed. Datasets from 20 OCT pullbacks of 9 patients were used in the training and testing using the proposed algorithm. The overall classification accuracy reached 96.8%, and that of fibrous, calcific, and lipid-rich plaques was 94%, 97.2%, and 99.2%, respectively.
Source: Biocybernetics and Biomedical Engineering - Category: Biomedical Engineering Source Type: research