A Lightweight CNN Model for Breast Cancer Classification

Breast cancer is a dominant cancer worldwide and is increasing in developing countries where the majority of cases are diagnosed in later stage. Early detection of cancer helps to control it in the early stage itself and decrease the death rate. There were over 2 million new cases in 2021, making it a significant health problem in present days. Malignant is the cancer cells that invade and kill nearby tissue and spread into different parts of the body. Unlike Malignant, Benign does not invade to other parts of the body. The key challenge is to classify the tumor as malignant or benign. To cater to this problem, novel Convolutional Neural Network (CNN) architecture is introduced to identify and classify the tumor as either malignant or benign. The proposed CNN model is experimented on the Wisconsin Breast Cancer Dataset (WBCD) and it is able to achieve 99% of accuracy.