Automated Breast Cancer Detection and Classification Techniques – A survey

Abstract

Breast cancer (BC) is the world's second leading cause of death for women. Because the cause of the disease is unknown, early detection and diagnosis are critical for BC control, as they can improve treatment success, save lives, and lower costs. Gene mutation, changes in size, and breast skin texture are indicators of BC. Symptoms must be carefully investigated to offer appropriate care to patients and an automatic prediction system that can classify tumors as benign or malignant is required. The majority of data generated in today's internet world is collected on social media or healthcare websites. Using data mining (DM) techniques, symptoms can be extracted from this massive amount of data, which will be helpful in the identification and classification of BC. The main contributions in this study are to investigate major problems that faces BC diagnosis and classification methods, as well as to present an overview of recent research studies that used to identify and classify BC.