Multiscale geometric texture analysis of ultrasound images of carotid atherosclerosis

In this paper two wavelet extension methods, the ridgelet (DRT) and the fast discrete curvelet (FDCT) transforms, were used in an attempt to characterize carotid atherosclerotic plaque from B-mode ultrasound and discriminate between symptomatic and asymptomatic cases. The mean and standard deviation of the detail subimages produced for each decomposition scheme were used as texture features. Feature selection included ranking the features in terms of their divergence values. The selected features were subsequently input to a classifier using support vector machines. Both transforms produced an 82.5% overall classification performance (75% and 85% for systole and 90% and 80% for diastole for DRT and FDCT, respectively). Those preliminary results in a somewhat limited sample population showed that, in terms of classification accuracy of ultrasound images of the carotid artery, ridgelet and curvelet transforms are equivalent. The faster and most sensitive FDCT algorithm might be a reasonable choice.