Carotid Artery recognition system(CARS): A comparison of three automated paradigms for ultrasound images

Abstract

The development of completely automated techniques for arterial wall segmentation and intima-media thickness measurement requires the recognition of the artery in the image frame. Conceptually, automated techniques can be thought of as the combination of two cascades stages: artery recognition and wall segmentation. In this chapter we show three carotid artery recognition systems (CARS) that are fully automated. CARS is a generalized framework for carotid artery recognition in ultrasound images, which can be easily adapted to almost any B-Mode ultrasound vascular image. The first technique is based on first-order derivative Gaussian edge analysis (CARSgd). The second method is based on an integrated approach (CARSia) that combines image feature extractions, fitting, and classification. The third strategy is based on signal analysis (CARSsa). The output of all the three paradigms provides tracing of the far adventitial (ADF). The complete CARS system (consisting of the three strategies named CARSgd, CARSia, and CARSsa) was on a dataset of 365 longitudinal B-Mode carotid images, acquired by different sonographers. Performance evaluation of the carotid recognition process was done in three ways: (1) visual inspection by experts; (2) by measuring the Hausdorff Distance (HD) between far adventitial (ADF) and the manually traced ADF, and (3) by measuring the HD between ADF and the lumen-intima (GTLI) and media-adventitia (GTMA) borders of the arterial walls. The results showed the CARS accuracy in locating the artery in the ultrasound image. The average HD between ADF and the manual ADF was 0.76∈±∈0.73 mm for CARSgd, 1.02∈±∈2.03 mm for CARSia, and 2.18∈±∈3.10 mm for CARSsa. The average HD between GTLI and ADF for CARSgd, CARSia, and CARSsa was 2.16∈±∈1.16 mm, 2.71∈±∈2.89 mm, and 2.66∈±∈1.52 mm, respectively. The average HD between ADF and GTMA for CARSgd, CARSia, and CARSsa was 1.54∈±∈1.19 mm, 1.86∈±∈2.66 mm, and 1.95∈±∈1.64 mm, respectively. Considering a maximum distance of 50 pixels (about 3 mm), CARSgd showed an identification accuracy of 100%, CARSia of 92%, and CARSsa of 96%. These identification accuracies were confirmed by visual inspection. All the three systems work on MATLAB, Windows OS, and on a PC-based cross-platform medical application written in Java called AtheroEdge™ with 1 s per image. CARSgd showed very accurate ADF profiles coupled with a low computational burden and without the need for specific tuning. It can be thought of as a reference technique for carotid localization, to be used in automated intima-media thickness measurement strategies.