Segmentation of Carotid Artery using Wavelets for the Analysis of Cardiovascular Diseases

K.B. Jayanthi (India), M.S. Kumar (USA), and R.S.D.W. Banu (India)


Image segmentation, wavelet transform, Fuzzy c-mean clustering, multiresolution analysis, ultrasound, carotid artery.


Diameter of the carotid artery is measured from ultrasound B-mode images as a step towards analysis of cardiac diseases. Reduction in the diameter is related to the plaque formation and other deposits in the artery walls. This is measured from the boundary extracted using image segmentation. The boundary of the carotid artery defines the shape of the vessel wall. This boundary extraction is mainly based on the multiresolution analysis technique. This technique decomposes the input image into a multiresolution space using two dimensional wavelet transform. The system builds feature vector for each pixel that contains information about the gray level and other texture information. This feature vector forms the input for Fuzzy C- Mean clustering method which results in a segmented image whose regions are distinct from each other according to texture characteristic content. An adaptive center weighted median filter is used to enhance ultrasound image before wavelet decomposition.

Important Links:

Go Back