An Integration Strategy based on Fuzzy Clustering and Level Set Method for Cell Image Segmentation

Abstract

In this study a new image segmentation framework which combines the Fuzzy c means clustering and the level set method is presented. Using this framework, the well-known Chan and Vese's level set technique and classical Bayes classifier are employed to obtain a prior membership value for each pixel based on region information. Next, a novel clustering model based on fuzzy c-mean clustering assisted by prior membership values is used to obtain the final segmentation. Experiments performed on high-throughput fluorescence microscopy colon cancer cell images, which are commonly utilized for the study of many normal and neoplastic procedures, indicate a significant improvement in accuracy when compared to several existing techniques.