CT Image Segmentation based on Clustering and Graph-Cuts

Abstract

In order to complete the auto-segmentation of cardiac dual-source CT image and extract the structure of heart accurately, this paper proposes a hybrid segmentation method based on k clustering and Graph-Cuts. This method identifies the initial label of pixels, on the basis of it, then creates the energy function on the label with the knowledge of anatomic construction of heart and constructs the network diagram, finally minimizes the energy function by the method of max-flow/min-cut theorem and picks up region of interest. The experiment results indicate that the robust, accurate segmentation of the cardiac DSCT image can be realized by combining Graph-Cut and k clustering algorithm