基于Graph-Based和四叉树的肝脏自动提取

In this paper, we present an algorithm based on Graph Theory for automatic liver segmentation of CT scans, combining with quad-tree. Firstly the isotropic nonlinear diffusion filter is used to filter the image data, and then the quad-tree algorithm is employed to segment the liver and the initial segmented regions are acquired. Finally we take these regions for the nodes of a graph, and segment the objects from the background by the theory of graph. Experimental results show the good performance of proposed algorithm.