A review on breast cancer detection using machine learning techniques

Abstract

One of the major diseases that has a high mortality rate in women is breast cancer. As the death rate of women has been increasing every year, it is necessary to decrease this number to detect the cancerous cells accurately by employing various methods. This paper presents a review of various works on the detection of breast cancer using various machine learning techniques such as decision tree, random forest, K-nearest neighbour, support vector machine, logistic regression and Naïve Bayes classifier. In addition, the paper also covers various deep neural network techniques and the comparison of various works. It follows various steps, namely pre-processing of breast image, mass detection, feature selection and image segmentation, feature extraction and classification. These steps are applied on various datasets namely, Wisconsin dataset, ImageNet, BreakHis, histopathological images and MIAS. The performance of various models has been examined and made a comparative study by considering accuracy, sensitivity and specificity metrics. Authors of this paper presented an overview of the current developments in cancer research by leveraging machine learning, deep learning and transformer models. Further, the authors also proposed the future scope of the work.

Topics & Concepts