Breast Cancer Malignancy Prediction Using Deep Learning Neural Networks

Cancer is a disease that instils fear in many people across the globe because of its fatal nature. But in most cases, cancer can be cured if diagnosed in an early stage followed up with proper medical attention. Computer aided diagnosis is gaining popularity nowadays as it can be effectively used as a primary screening test for many diseases and especially in case of cancer. Deep learning is an artificial intelligence technique where the machine is equipped with intelligence by trying to mimic the thought process of a human brain. This paper focuses on building a deep neural network that can predict the malignancy of the breast cancer. The data is obtained from the Wisconsin breast cancer dataset provided by UCI. The neural network model is optimized against over fitting using the early stopping mechanism and dropout layers and attains a F1 score of over 98.