Abstract

Info

Title:: Stein-Weiss analytic function combined with back-propagation neural network for blood vessel segmentation

Author(s):: WU Mingzhu1; CHEN Ying1; LI Xingmin2; 3; 1. School of Information Engineering, Guangzhou Institute of Technology, Guangzhou 510075, China 2. School of Computer, South China Normal University, Guangzhou 510631, China 3. Zhujiang Hospital of Southern Medical University, Guangzhou 510280, China

Keywords:: Keywords: blood vessel segmentation Stein-Weiss analytic function back-propagation neural network

Abstract:: Abstract: For solving the problem of traditional back-propagation (BP) neural network for blood vessel segmentation, such as time consuming and low recognition rate, a BP neural network based on Stein-Weiss analytic function is proposed for blood vessel segmentation. After Stein-Weiss function is constructed for each voxel, 16 eigenvalues of the corresponding voxel are calculated according to the analytic properties of Stein-Weiss analytic function. The calculated eigenvalues are taken as the input data of BP neural network, and then the data are classified and learned through the self-learning ability of BP neural network. Finally, the edge of blood vessel is obtained by the generalization ability of BP neural network. The experimental results of hepatic vessel segmentation show that compared with traditional BP neural network algorithms, the proposed algorithm can be used to not only obtain the edge of blood vessel with high recognition rate and rich details, but also improve the efficiency of segmentation.