WITHDRAWN: A new proposal for the segmentation of breast lesion in mammogram images using optimized kernel fuzzy clustering algorithm

Abstract

Abstract Breast Cancer is one of the fatal diseases which is caused due to the un natural development of the tissues in the breasts which are abnormal. The level of sarcoma or the stage of the cancer is mostly relied upon the doctor’s analysis. In order to provide a technical contribution which supports the doctor to take decision, this paper is intended to develop a framework which can help in determining the stage in which the cancer is at present. The major issues in the prediction of breast cancer through mammograms are the diverged artifacts, similar breast tissues and lower contrast on the boundary between skin and air. To overcome these issues, Optimized Kernel Fuzzy Clustering Algorithm is developed (OKFCA) and to determine the cancer portions in mammogram images. The OKFCA algorithm has described to identify the segmented regions in Mammogram Image Analysis Society (MIAS) database. The proposed segmentation algorithm is carried out with pre-processed mammogram images, noise free image that was obtained by using Hybrid Denoising Filter (HDF) algorithm and the proposed OKFCA is a significant approach to find out the cancer segment of mammogram image. Data clustering facilitates to place data of similar types in one group and of dissimilar types in different group. The results from the experiments which were carried on the MIAS data confirms the efficiency of the proposed system in terms of accuracy when compared to that of the famous K-Means, OKFCA and Otsu methods.