Classification of Common Carotid Artery Images Using Segmentation and Rule Mining

Increase in Intima-media Thickness (IMT) of common carotid artery leads to atherosclerosis and stroke. Manual method for finding the interfaces between the intima and media layer is not accurate and it depends on the experience of the external observer. An improved dynamic programming (DP) segmentation technique for detecting the intima-media layer of the far wall of the common carotid artery (CCA) images using optimal search technique is proposed. The algorithm is developed considering the normalization and smoothing for estimating the intima media thickness (IMT) of the normal and abnormal subjects. The magnitudes of the IMT values have been used to explore the rate of prediction of blockage existing in the cerebrovascular and cardiovascular pathologies, and also hypertension and atherosclerosis. Retrieving images from large databases becomes a difficult task. Here after finding out the IMT by segmentation, the results are entered into transaction database. Association rule mining is done in order to retrieve the images related to the query image i.e. to find out images related to the given patients image.