Detection of the Intimal and Adventitial Layers of the Carotid Artery based on Snakes

Abstract

The segmentation and analysis of the carotid artery is useful for the diagnosis of serious cardiovascular disease. Several methods have been presented for the segmentation of ultrasound carotid artery images, but almost all need a certain degree of user interaction. In this paper, we present an automatic segmentation method for detecting the intimal and adventitial layers. The method firstly uses the blood flow image to determine the position of the carotid artery, and then the identification of the region of interest (ROI) will be performed. We use the Fuzzy c-means cluster algorithm to distinguish the initial intimal and adventitial layers of the carotid artery. Finally, the energy definition of active contour model is used. The internal force and external force in the snake model are modified to be suitable for our approach. The carotid artery intimal-medial thickness is considered and adjusted to the energy of the active contour model.