Robust kernel FCM in segmentation of breast medical images

Abstract

This paper presents an automatic effective fuzzy c-means segmentation method for segmenting breast cancer MRI based on standard fuzzy c-means. To introduce a new effective segmentation method, this paper introduced a novel objective function by replacing original Euclidean distance on feature space using new hyper tangent function. This paper obtains the new hyper tangent function from exited hyper tangent function to perform effectively with large number of data from more noised medical images and to have strong clusters. It derives an effective method to construct the membership matrix for objects, and it derives a robust method for updating centers from proposed novel objective function. Experiments will be done with an artificially generated data set to show how effectively the new fuzzy c-means obtain clusters, and then this work implements the proposed methods to segment the breast medical images into different regions, each corresponding to a different tissue, based on the signal enhancement-time information. This paper compares the results with results of standard fuzzy c-means algorithm. The correct classification rate of proposed fuzzy c-means segmentation method is obtained using silhouette method.