A review of ultrasound common carotid artery image and video segmentation techniques

Abstract

The determination of the wall thickness [intima-media thickness (IMT)], the delineation of the atherosclerotic carotid plaque, the measurement of the diameter in the common carotid artery (CCA), as well as the grading of its stenosis are important for the evaluation of the atherosclerosis disease. All these measurements are also considered to be significant markers for the clinical evaluation of the risk of stroke. A number of CCA segmentation techniques have been proposed in the last few years either for the segmentation of the intima-media complex (IMC), the lumen of the CCA, or for the atherosclerotic carotid plaque from ultrasound images or videos of the CCA. The present review study proposes and discusses the methods and systems introduced so far in the literature for performing automated or semi-automated segmentation in ultrasound images or videos of the CCA. These are based on edge detection, active contours, level sets, dynamic programming, local statistics, Hough transform, statistical modeling, neural networks, and an integration of the above methods. Furthermore, the performance of these systems is evaluated and discussed based on various evaluation metrics. We finally propose the best performing method that can be used for the segmentation of the IMC and the atherosclerotic carotid plaque in ultrasound images and videos. We end the present review study with a discussion of the different image and video CCA segmentation techniques, future perspectives, and further extension of these techniques to ultrasound video segmentation and wall tracking of the CCA. Future work on the segmentation of the CCA will be focused on the development of integrated segmentation systems for the complete segmentation of the CCA as well as the segmentation and motion analysis of the plaque and or the IMC from ultrasound video sequences of the CCA. These systems will improve the evaluation, follow up, and treatment of patients affected by advanced atherosclerosis disease conditions.

An integrated system for the complete segmentation of the common carotid artery bifurcation in ultrasound images

“…Rocha et al also reported a sensitivity of 95% by segmenting the atherosclerotic carotid plaque using dynamic programming [14] . A number of other studies investigated segmentation of the CCA plaque [16] , and their results are comparable with those found in this study. We can thus conclude that the SA measurements performed in this study are as much reliable and accurate as the M measurements performed by the neurovascular expert and therefore the system might be used in the clinical praxis.…”

“…[7,13,[15][16][17][18] by also taking into consideration the follow up of the patients as well as take into account additional variables, such as age, sex, weight, blood pressure and others for better evaluating the risk of stroke in this group of patients. Acoustic shadowing, speckle noise [6,7,13,17] , as well as extensive echolucency, calcification and the positioning of the initial snake contour as it was discussed in Ref.…”

“…The segmentations were based on the Williams & Shah [37] snake segmentation method, which was used to deform the snake and segment the IMC, the atherosclerotic carotid plaque and the near carotid wall borders in each image. The snake v(s), adapts itself by a dynamic process that minimizes an energy function ( ( , ) snake E v s ) defined as [37] : [7,13,[15][16][17][18] .…”

“…We may ob ntation system egmentations in troke in the ag and (f)): Male n edical Engineerin x (CSI) [10,36] : the lumen diam n Ref. [7,13,[15][16][17][18] of Table 2 illustrates the M and the SA mean, SD and median segmentation measurements in millimeters for the IMT and D. These were performed on 200 subjects (100 normal + 100 diseased). We also present the percentage of ICA stenosis.…”

“…It diameter (D) ( he atherosclero are routinely as re performed m mated (SA) seg rease the accur ) (bands Z5 and en diameter, D walls on the men stenosis. Fi literature either -and intima-l d in the literatu y, a review [6] o cent study [16] Figure 1, otic carotid plaq ssessed with hig manually by e gmentation sys racy of the segm d Z6), the athe (band Z4), and image, which igure is reprodu r for the segme ayers [15] , from ture, where a c of different au a review on im ion system was ima-and the m filtering [17] . [1,3 ted through the leading echo b que, the D, as w gh resolution u experts and su stems are there mentation [6][7][8][9][10][11][12] rotid plaque, at ear walls of the d from a 69 ye f. [15] © IEEE T IMC [6][7][8][9] , the D images of the mentation of the A techniques f segmentation s hereas in Ref.…”