Least square support vector machine and minumum redundacy maximum relavance for diagnosis of breast cancer from breast microscopic images

Abstract

In these days, there are many various diseases, whose diagnosis is very hardly. Breast cancer is one of these type diseases. In this study, the aim is to determine cancerous lesions taken from light microscopic. Here, totally 180 that be 3x60 breast microscopic images set are taken from Firat University Medicine Faculty Pathalogy Laboratuary. In this study, 23 features are used. These features are totally obtained 92 (23x4) features by rotating for variety angles (i.e., 0 degrees,46 degrees, 90 degrees,186 degrees) breast microscopic images. In this paper, new method is found. This method are called as Minimum Redundancy Maximum Relavance_Least Square Support Vector Machine (mRMR_LSSVM). In this study, the structure of this method composes from three steps. These are feature select step, classification step and testing stage. In feature select step have found optimal feature subset using minimum redundancy and maximum relevance via mutual information (mRMR). In classification step is used LSSVM. For validation of the proposed method is found the accuracy rate. This accuracy rate, with (mRMR_LSSVM). was obtained % 100 in breast microscopic images. (C) 2015 The Authors. Published by Elsevier Ltd.