Breast Cancer Prediction Using Machine Learning Techniques

Abstract

The most frequent cancer found in both sexes is breast cancer and second most common type of a cancer leading cause of death from cancer found in women worldwide. Treatment for breast cancer can be highly effective when the disease is diagnosed at an early stage; it will not only prevent the growth of the cancer but will also increase the survival rate by 90% or higher (https://www.who.int/news-room/fact-sheets/detail/breast-cancer ). Therefore, in order to predict and treat such type of cancer, development of intelligent techniques is needed. Machine learning (ML) techniques can be used as an effective tool to help design an efficient, faster, and cheaper alternative systems. In this research, we have done an analysis of supervised learning techniques and deep learning techniques of ML on Wisconsin Breast Cancer dataset (WBCD) (https://archive.ics.uci.edu/ml/datasets/Breast + Cancer + Wisconsin + (Diagnostic)) and MIAS mammography dataset (https://www.kaggle.com/kmader/mias-mammography ) to analyze which technique can the most efficient and accurate. DNN and CNN gave us the highest accuracy of 99% for WBCD and MIAS mammography dataset, respectively.