Atheromatic™: Symptomatic vs. asymptomatic classification of carotid ultrasound plaque using a combination of HOS, DWT & texture

Quantitative characterization of carotid atherosclerosis and classification into either symptomatic or asymptomatic is crucial in terms of diagnosis and treatment planning for a range of cardiovascular diseases. This paper presents a computer-aided diagnosis (CAD) system (Atheromatic™, patented technology from Biomedical Technologies, Inc., CA, USA) which analyzes ultrasound images and classifies them into symptomatic and asymptomatic. The classification result is based on a combination of discrete wavelet transform, higher order spectra and textural features. In this study, we compare support vector machine (SVM) classifiers with different kernels. The classifier with a radial basis function (RBF) kernel achieved an accuracy of 91.7% as well as a sensitivity of 97%, and specificity of 80%. Encouraged by this result, we feel that these features can be used to identify the plaque tissue type. Therefore, we propose an integrated index, a unique number called symptomatic asymptomatic carotid index (SACI) to discriminate symptomatic and asymptomatic carotid ultrasound images. We hope this SACI can be used as an adjunct tool by the vascular surgeons for daily screening.

1. Introduction

HEART disease and stroke are mainly due to occlusion due to atherosclerosis and high blood pressure [1]. Stroke remains the third most common cause of death in most industrialized countries. Atherosclerosis is a condition of thickening of artery due to deposition of multiple plaques [2]. It has been shown that surgical removal of plaques reduced the risk of ipsilateral stroke [3]. Since not all carotid plaques are necessarily harmful and as carotid surgery carries a considerable risk for the patient, optimized diagnosis and patient selection is of paramount importance. For both surgery and treatment, an early detection of carotid atherosclerosis plaque and the classification of the same into symptomatic [4] or asymptomatic [5] are crucial. Invasive methods like intravascular ultrasound [6], [7] carry risks. Non-invasive carotid artery ultrasound is also well established but the correlation between ultrasonographic features and the histological evaluation of carotid plaques is often poor [8], [9]. Improving the ultrasound image quality with adequate preprocessing as well as extracting discriminate features will increase the correlation between automated classification results and histological results of carotid plaques. In this paper, we present an effective texture derived atherosclerotic tissue characterization algorithm which can be used in CAD systems. We call the system as Atheromatic ™ (Patented Technology from Global Biomedical Technologies, Inc., California, USA). The block diagram, in Fig. 1, shows the structure of the algorithm. Fig 1. Block diagram of the proposed system