Breast cancer image classification using the convolution neural network

Abstract

Breast cancer is a type of tumour and the disease with the second-leading cause of death among women. Physicians diagnose the disease through tumour classification and decide whether it is malignant or benign. However, to accurately perform the classification is not an easy task, even by experts. Thus, diagnostic system automation is required to assist physicians in accurately diagnosing malignant tumours as cancer in the early stages. This paper attempts to improve the accuracy of breast cancer detection by utilising the deep learning convolution neural network (CNN). Experiments were conducted using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. Compared to existing techniques, the use of CNN shows a better result and achieves 99.66% in terms of accuracy.