Title: Ultrasound carotid artery image segmentation using shape prior technique

Authors: N. Santhiyakumari, M. Madheswaran

Addresses: Department of ECE, K.S. Rangasamy College of Technology, Tiruchengode-637215, India. ' Centre for Advanced Research, Department of Electronics and Communication Engineering, Muthayammal Engineering College, Rasipuram-637 408, Tamilnadu, India

Abstract: Carotid artery ultrasound image segmentation with shape prior algorithm is proposed in this paper. Automatic segmentation of the artery image is a difficult task due to the presence of speckle noise and lack of information in the acquired image. Curve evolution has been proposed using image information with shape priors, in such a way that the final image position corresponds to the shape. It is an iterative two step algorithm composed of an image and shape correction steps. Shape prior represents the mean shape of the portion in the algorithm and its values have been calculated using Karcher mean. The measured mean minimises the sum of squared geodesic distances from the mean shape to each of the shapes in the shape space. The proposed work is used for the automatic segmentation of anatomical structures that incorporates the prior information about shape in order to limit the space of possible solutions. The segmented outputs have been used to detect layers of ultrasound carotid artery image.

Keywords: ultrasound imaging; carotid artery images; shape prior; image processing; automatic segmentation; image segmentation.

DOI: 10.1504/IJMEI.2010.036308

International Journal of Medical Engineering and Informatics, 2010 Vol.2 No.4, pp.364 - 375

Published online: 01 Nov 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article