Carotid Artery Identification in Ultrasound Images

The carotid arteries are arteries that supply the head and neck with oxygenated blood. Carotid artery recognition is a fully automated, fast, and reliable way to facilitate the low-level task of arterial delineation. Automatic segmentation of the carotid artery from ultrasound images is a critical test in clinical diagnosis. A real-time, user-independent algorithm is introduced for carotid artery localization in 2D (B-Mode) ultrasound images. The proposed algorithm was systematically compared with another algorithm for common carotid artery (CCA) recognition in 2D scans. The data used included 500 images from 50 subjects taken from 5 different institutions and covering a wide range of possible lumen tissue representation. Using the resulting values, the carotid artery was recognized in all the processed images. Thus, the proposed technique will further reinforce automatic segmentation in longitudinal 2D ultrasound images.