Multiscale active contour model for vessel segmentation.

Abstract

This paper presents a novel multiscale active contour model for vessel segmentation. The model is based on accurate analysis of the vessel structure in the image. According to different scale response of the eigenvalues of local second order derivative (Hessian matrix), a new vessel region information function, which shows a valid estimation of the vesselness measure, is defined. We introduce the posteriori probability estimation into the active contours framework and design a new objective function. The defined objective function is minimized using the variational method, and a new region-based external force is obtained, which is more accurate to the vessel structure and not sensitive to the initial condition. This active contour model combines the obtained region-based and conventional boundary-based force, which aims at finding more accurate vessel edges even when the vessel branches are low contrast or blurry. Furthermore, the proposed model is implemented by an implicit method of level set framework, the solution of which is steady and suitable for various topology changes. Moreover, two new speed functions for vessel segmentation in the level set method are presented, one for fast marching and the other for a narrow-band algorithm. The vessel segmentation experiments compared with previous geometric active contour models are shown on several medical images. The experimental results demonstrate the performance of our approach.

DOI: 10.1080/03091900600700798

6 Figures and Tables

Statistics

010020020102011201220132014201520162017
Citations per Year

143 Citations

Semantic Scholar estimates that this publication has 143 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Yu2008MultiscaleAC, title={Multiscale active contour model for vessel segmentation.}, author={Guang-yan Yu and Peijun Liu and Yi Miao and Zheng-zhong Bian}, journal={Journal of medical engineering & technology}, year={2008}, volume={32 1}, pages={1-9} }