Automatic liver segmentation from CT scans based on a statistical shape model

Xing Zhang; Jie Tian; Kexin Deng; Yongfang Wu; Xiuli Li

doi:10.1109/IEMBS.2010.5626470

Automatic liver segmentation from CT scans based on a statistical shape model

Annu Int Conf IEEE Eng Med Biol Soc. 2010:2010:5351-4. doi: 10.1109/IEMBS.2010.5626470.

Authors

Xing Zhang¹, Jie Tian, Kexin Deng, Yongfang Wu, Xiuli Li

Affiliation

¹ Medical Image Processing Group, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.

PMID: 21096258
DOI: 10.1109/IEMBS.2010.5626470

Abstract

In this paper, we present an algorithm for automatic liver segmentation from CT scans which is based on a statistical shape model. The proposed method is a hybrid method that combines three steps: 1) Localization of the average liver shape model in a test CT volume via 3D generalized Hough transform; 2) Subspace initialization of the statistical shape model; 3) Deformation of the shape model to adapt to liver contour through an optimal surface detection approach based on graph theory. The proposed method is evaluated on MICCAI 2007 liver segmentation challenge datasets. The experiment results demonstrate availability of the proposed method.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms
Automation
Diffusion
Humans
Imaging, Three-Dimensional
Liver / anatomy & histology*
Liver / diagnostic imaging*
Models, Statistical*
Nonlinear Dynamics
Radiographic Image Interpretation, Computer-Assisted / methods*
Tomography, X-Ray Computed / methods*