Fully Automated Active Contour Model Based Approach for Segmentation of Common Carotid Artery Using Ultrasound Images

摘要

In this paper, we have proposed an automated approach to segment common carotid artery from longitudinal carotid B-mode ultrasound images and calculate the carotid intima media thickness. The proposed approach extracts the contours in the ultrasound images using gradient vector flow snakes with an improved snake initialization process. The seed points for this improved snake initialization process are extracted using selected edges returned by the candidate line-selection algorithm. Intima media thickness is calculated from the extracted contours. The proposed approach is tested and clinically validated on a data set of 100 longitudinal ultrasound images of the carotid artery. There is no significant difference between intima media thickness measurements obtained using the proposed approach and the manual measurements. The intra-observer error of 0.088, a coefficient of variation of 12.99 %, Bland-Altman plots with small differences between experts (0.01 and 0.03 for Experfl and Expert2, respectively) and figure of merit of 98.5 % are obtained. The proposed approach can be used successfully for carotid intima media thickness measurement, which can further be used for risk estimation of cardiovascular diseases and ischemic stroke. The proposed approach makes the segmentation process automated and yet reduces the risk of subjectivity and operator variability for intima media thickness measurement.