A Comprehensive Survey on Different Machine Learning Approaches for Breast Cancer Prediction based on Medical Imaging Modalities and Microarray Gene Expression.

Abstract

Cancer is a complex global health problem that causes a high death rate. Breast cancer (BC) is the second most common death-causing disease in women worldwide. BC develops in the cells of the ducts or lobules of the glandular tissue when breast cells become uncontrollably proliferative. It can be controlled if diagnosed early enough. There are many techniques used to diagnose or classify BC. Machine learning (ML) has a significant effect on BC classification. This article provides a comparative study of different ML approaches for BC prediction based on medical imaging and microarray gene expression (MGE) data. DT, KNN, RF, SVM, Naïve Bayes, ANN, etc. perform much better in their respective fields. Another method named ensemble, incorporates more than one single classifier to solve the same problem. The study shows how ML with supervised, unsupervised, and ensemble learning might help with BC prognosis. This paper observes ensemble methods provide better performance than a single classifier. Finally, a comprehensive review of various imaging modalities and microarray gene expression, different datasets, performance metrics and outcomes, challenges, and prospective research directions are provided for the new researchers in this fast-growing field.