GVF-Snake Based Method for Liver Region Segmentation

Abstract

In this paper, we present a GVF-Snake based method for liver region segmentation on CT images. Firstly, the CT images are enhanced using a method of histogram equalization and anisotropic diffusion filter. Then, a region based method is applied to complement rough segmentation. Finally, an improved generalized gradient vector flow snake model (GVF-Snake) is adopted for the refinement of the rough segmentation. Experiment results show that the proposed method can precisely extract the liver region.