Comparison of texture analysis methods for the characterization of coronary plaques in intravascular ultrasound images

Intravascular Ultrasound (IVUS) is a diagnostic imaging technique that prov ides tomographic visualization of coronary arteries. The aim of this study was to evaluate five texture analysis techniques and determine their abilit y to distinguish between plaque lesions of different composition. Using his tological correlation, regions of calcified, fibrous, and necrotic core pla que were chosen from 27 coronary plaques. First-order statistics, Haralick' s method, Laws' texture energy method, the neighborhood gray-tone differenc e matrix method, and texture spectrum features were examined using discrimi nant analysis. Self-validation indicated that Haralick's method yielded the most accurate results, with resubstitution and cross-validation error rate s of 0.00 and 14.76%, respectively. Further optimization gave error rates o f 6.67%, using only two discriminating features, IDM and entropy. (C) 2000 Elsevier Science Ltd. All rights reserved.