Table 1: Overview of recent CCA IMC segmentation techniques for ultrasound imaging.

year, and
ref. no.
Common carotid artery IMT segmentation techniqueAdvantages & limitations of the methodsSelection method of ROI
Performance metricProcessing
IMT error

Ilea et al., 2013
Model-based approach, video tracking procedure: spatially coherent algorithmAdvantages: Method can deal with inconsistencies in the appearance of the IMC over the cardiac cycle. Robustness with respect to data captured under different imaging conditions.FAMAD80 sec
(8 sec in 1st frame & 72 sec in tracking 28 frames)
(−0.007) ± 0.17640*
Xu et al.,
Hough transform and dual snake modelAdvantages: It is less likely to be affected by noise, compensates the holes or missing boundaries, and can estimate the missing LI interface boundary.
Limitations: The method would work fine for early thickening of IMC but fails for irregular boundaries in the presence of plaques and eliminates minor details.
SAMAD0.465 sec0.02 ± 0.0350
Molinari et al.,
Multiresolution edge snapperAdvantages: Complete automation, robustness to noise, and real-time computation.
Limitations: Robustness with respect to noise, but the LI/MA representation is less accurate.
FAMADLess than 15 sec0.078 ± 0.112365
Destrempes et al.,
Nakagami distributions, Bayesian modelAdvantages: Robust to a reasonable variability in the initialization, lowest tracing error for LI & MA, method is not sensitive to the degree of stenosis or calcification.
Limitations: Depends on initial segmentation
38 sec8988
Petroudi et al., 2011, [24]Active contours & active contours without edgesAdvantages: Fully automated, fast, does not require any user interaction, and works well for noisy images.FAMAD0.09 ± 0.1030
Destrempes et al.,
Nakagami distributions, stochastic optimizationAdvantages: Reasonable average computation time, robust to the estimation procedures.
Limitations: Method suitable for healthy arteries, extensive tuning & training, so computational cost is high, for different scanner requires retraining & retuning.
24 sec7283
Faita et al.,
2008, [26]
First-order absolute moment edge operatorAdvantages: Suited for fast real-time implementation, operator can have immediate feedback on the quality of the images.
Limitations: Depends on ROI selection.
SAMAD0.001 ± 0.035150
Liang et al.,
Multiscale dynamic programmingAdvantages: No initial human setting, capable of processing images of different quality, ambiguous cases user can intervene, and reduced interobserver variability.
Limitations: Training required, for different scanner retraining needed, searched LI & MA interfaces may cross each other.
FAMAD0.7 min0.042 ± 0.0250
Gustavsson et al., 1994,
Dynamic programmingAdvantages: Fully automated, low computational complexity; suitable for clinical purposes, human correction allowed.
Limitations: Initial human setting & training required, fails for slanting IMC with weak boundary.
SAMAD0.03 ± 0.03222

: number of images/cases, SA: semiautomated, FA: fully automated, SD: standard deviation, HD: Hausdorff distance, MAD: mean absolute distance, *video sequences, : average processing time/frame or image.