Multiscale morphological analysis of the atherosclerotic carotid plaque

The aim of this paper was to investigate the usefulness of multiscale morphological analysis in the assessment of atherosclerotic carotid plagues. Ultrasound images were recorded from 137 asymptomatic and 137 symptomatic plaques and were converted to binary images at low, middle and high intensity intervals based on structural morphology. Low images represent low intensity regions corresponding to blood, thrombus, lipid or hemorrhage, whereas high images describe the collagen and calcified components of the plaque. Middle image describe image regions that fall between low and high components. The morphological pattern spectra were computed and several classifiers like the K-Nearest Neighbor (KNN), the Probabilistic Neural Network (PNN), and the Support Vector Machine (SVM) were evaluated for classifying these spectra into two classes: asymptomatic or symptomatic. The highest diagnostic yield achieved was 67% that is slightly lower than texture analysis carried out on the same data set.