Automatic Segmentation of Lumen Intima Layer in Longitudinal Mode Ultrasound Images

We propose an automated method for the segmentation of lumen intima layer of the common carotid artery in longitudinal mode ultrasound images. The method is hybrid, in the sense that a coarse segmentation is first achieved by optimizing a locally defined contrast function of an active oblong considering its five degrees-of-freedom, and subsequently the fine segmentation and delineation of the carotid artery are achieved by post-processing the portion of the ultrasound image spanned by the annulus region of the optimally fitted active oblong. The post-processing includes median filtering and Canny edge detection to retain the lumen intima representative points followed by a smooth curve fitting technique to delineate the lumen intima boundary. The algorithm has been validated on 84 longitudinal mode carotid artery ultrasound images provided by the Signal Processing laboratory, Brno university. The proposed technique results in an average accuracy and Dice similarity index of 98.9% and 95.2%, respectively.