Dense Convolutional Neural Network Based Deep Learning Framework for the Diagnosis of Breast Cancer

Breast Cancer is second most deadly disease prevailing among women after lung cancer. Females affected with breast cancer are vulnerable to grave health-related issues with a very high mortality rate. Therefore, it has become a matter of concern among medical experts. But early and timely intervention using modern prognosis process to detect and diagnose such complications can enhance the chances of survival of cancer patients. For this purpose, computer-aided detection methods using machine learning and deep learning models are employed to detect breast cancer which provide high accuracy in detecting abnormalities in cells. In this research work, a novel dense Convolutional Neural Network (CNN) based deep learning model is proposed to accurately detect benign and malignant tumour classes using Wisconsin Breast Cancer dataset. The performance metrics such as accuracy, sensitivity, precision, F1-score, area under ROC curve (AUC) were computed using five-fold cross validation. It is concluded that the proposed CNN model shows good accuracy of 98.2% in detecting breast cancer abnormalities.