Survey of machine learning algorithms for breast cancer detection using mammogram images

Breast cancer is the primary cause of death in most cancer affected women. Mammography is one of the most dependable strategies for early detection and diagnosis of breast cancer and reduces the death rate. Mammograms are radiographic images of the breast which are utilized to identify the early symptoms of breast cancer. These radiographic images reduce human errors in detecting cysts and reduce the diagnosing time and also increase the diagnosis accuracy. An overview of the machine learning techniques for breast cancer detection and classification has been presented in this paper, which can be divided into three main stages: pre-processing, extraction of features, and classification. This article discusses about the effects of several Machine learning techniques for automation of mammogram image classification are investigated. This investigation assembles agent works that show how Machine learning technique is applied to the result of different issues identified with various analytic science examinations. This study portrays the impacts of pre-taken care of mammogram images before entering the classifier, which brings about higher effective classification. The detection stage is trailed by segmentation of the tumor region in a mammogram image. This study is an attempt to gather and compare the various screening techniques, classifiers, and their performance in terms of sensitivity, specificity and exactness for breast cancer diagnosis. (C) 2020 Elsevier Ltd. All rights reserved.