Integrating Spatial Fuzzy Clustering with Level Set Methods for Liver Segmentation from Computed Tomography Scans

This article presents a fully automatic segmentation method of liver CT scans using fuzzy cmean clustering and level set. First, the difference of unique image is improved to make boundaries clearer; second, a spatial fuzzy c-mean clustering combining with anatomical previous information is engaged to extract liver area automatically Thirdly, a distance regularized level set is used for modification; finally, morphological operations are used as postprocessing. The experiment result shows that the method can achieve high accuracy (0.9986) and specificity (0.9989). Comparing with standard level set method, our method is more successful in dealing with over-segmentation difficulty.