Breast cancer detection using non-invasive method for real time dataset

Abstract

Breast Cancer is one of the most horrible and dangerous diseases that affect women health. This paper aims to detect the breast cancer in a non-invasive manner with the help of mammograms and enables advanced characterization of the lesion using following steps: mammogram enhancement using adaptive median filter, cancer area detection using seed value based segmentation, extraction of CSLBP and GLDM features and finally, classification of cancer using RBF-SVM. The Algorithm is evaluated on real time mammogram breast dataset consisting of 249 images and for the considered dataset, accuracy is found to be 95.18%.