Segmentation of carotid ultrasound images

Abstract

This chapter surveys methodologies for the segmentation of carotid ultrasound images and describes a method for the semiautomatic detection of the lumen-intima and the media-adventitia interfaces of the near and far common carotid wall. The approach is based on feature extraction, fitting of cubic splines, dynamic programming, smooth intensity thresholding surfaces, and geometric snakes. A set of 47 B-mode images of the common carotid were used to assess the performance of the method. The detection errors are similar to the ones observed in manual segmentations for 95% of the far wall interfaces and 73% of the near wall interfaces.