Robust breast cancer detection by utilising the multi-resolution features

Abstract

Breast Cancer can be said as a malignant growth of cells in the breast which can affect other parts of the body if left untreated. The use of Computer Assisted Diagnosis is that it provides the pathologist more accurate diagnosis information and helps to reduce the limitations of human observations. Our method proposed to create an accurate technique for automated diagnosis of breast cancerous cells on histopathology images. The dataset used for our purpose is BreaKHis_v1. The method consists of pre-processing, K-means segmentation, post-processing, feature vector extraction and classification. The texture and intensity feature vectors of the histopathology image is extracted and is combined and tested with multi resolution features such as wavelet, contourlet transform and wave atom features. Further for classification, several classifiers are tested .The result showed that wave atom feature produced superior result and the best classifier is ensemble classifier providing an overall accuracy of 94.5%.