Validating a computer-aided diagnosis system for identifying carotid atherosclerosis

The degree of carotid stenosis is up to now considered one of the most important features for determining the risk of stroke. Ultrasound (US) is a non-invasive technique, relatively inexpensive, portable, which has an excellent temporal resolution. Computer-Aided Diagnosis (CAD) has became one of the major research field in medical imaging and diagnostic radiology. This work presents a CAD system, an automatic prototype software used for carotid plaque detection. We studied US images of 44 subjects, 22 with and 22 subjects without carotid artery stenosis. The CAD system automatically performed the following processing steps: registration of images, detection of lesions by a segmentation method using Watershed algorithm, extraction of dynamic and morphologic features, and classification of plaques through Cluster Analysis. Investigations has been carried out on 287 suspect regions including 61 plaques and 226 non-plaques cases. The area under the ROC curve was 0.89. The experimental results also show that the proposed methods is feasible, and have a good agreement with the expert neurologist. Without the need of any user-interaction, the proposed method generates a detection out-put that may be useful in second opinion.