Abstract
In this paper, we present a system for segmenting the 3D liver region from CT images and reconstructing its 3D model. The segmentation is accomplished in 3-D space which is extended from the user controlled 2-D random walker technique and implemented by a slice-section method. After obtaining the 3D liver segmentation result, we apply the surface reconstruction algorithm based on bipartite polar classification to build the 3-D liver surface model. In the experimental results, we apply the proposed algorithm to ten test CT datasets to evaluate its accuracy and we demonstrate the good accuracy compared with the human labeled results. © 2012 IEEE.