A novel graph cuts based liver segmentation method

This paper presents a novel liver segmentation method based on the fast marching and graph cuts methods. The algorithm is composed of three main steps: first, rough edge of the liver is extracted from the CT image by fast marching method. Second, hard constrain of the foreground and background which is used for initial calculation of graph cut is obtained by mathematical morphology method. Third, based on the former calculation, the graph cuts are utilized to refine the segmentation boundary of the liver. The developed method greatly reduces the complexity of the commonly used graph cuts methods, which can obtain the hard constrains automatically. Also, the developed method reduces the dependence of empirical parameters of the fast marching based method. Experimental results show that the developed method is very effective for the segmentation of liver from CT images.