A Probabilistic Approach to Computerized Tracking of Arterial Walls in Ultrasound Image Sequences

Table 1

A selection of specific solutions reported to date applicable to the problem of tracking the vascular walls in B-mode ultrasound image sequences.

Reference	Basis of technique	Applications	Limitations
[3]	Cost function minimization	Intima-media thickness (IMT) and arterial lumen diameter measurement.	Extensive manual corrections were reported to be required
[5]	Greyscale intensity and gradient thresholding	Endothelium-dependent dilation of the brachial artery.	Dependence on vessel orientation, curvature, and appearance
[2]	Edge detection	Carotid artery diameter and intima-media thickness (IMT) measurement.	Operator intervention is frequently needed during the systolic expansion of the artery when the arterial wall moves a relatively large distance between frames
[6]	Active contours	Detection of the intima-media complex of the far wall of the common carotid artery.	Long processing times
[7]	Artificial neural networks	Detection of the near and far walls of the artery in the longitudinal plane.	Relatively horizontal and straight vessel assumed
[1]	Region tracking/block matching	Estimation of carotid artery wall motion.	Limited number of points can be tracked due to computational cost and speckle decorrelation
[8]	Fast marching algorithm	Segmentation of intravascular ultrasound images in 3D.	Required manual delineation of initial contours close to the arterial lumen boundaries
[9]	Hough transform	Extraction of carotid artery surface in the longitudinal and transverse planes.	Longitudinal and transverse arterial sections approximated as straight lines and circles
[10]	Polar representation, grey-level histograms, cost function minimization, and probabilistic considerations	Delineation of lumen boundaries in intravascular ultrasound (IVUS) images.	Specific to IVUS, modeled the lumen surface as a mixture of Gaussians placing limitations on the type of contour that can be traced
[11]	Edge detection and mathematical morphology	Delineate vessel lumen boundaries in transverse cross-sections of the common carotid artery.	Whether the method is also expected to work for longitudinal cross sections of arteries is not known. Also, edge detection techniques have an inherent vulnerability to image noise