Chapter 9 - An intelligent deep learning approach for colon cancer diagnosis

Abstract

Colon cancer is caused by the uncontrollable growth of abnormal cells in the colon and can cause death of patient if not treated effectively. Detecting cancer accurately in the people and finding the related factors is essential and a challenge for physicians and researchers. The prediction model is built using machine learning approaches to detect and classify colon cancer patients. In this chapter, we proposed a Deep Neural Network trained by a Genetic Algorithm (DNN-GA) to identify colon cancer patients. The proposed method has been experimented on a microarray dataset that consists of symptoms of cancer patients. The performance of the proposed model is compared with that of other machine learning approaches such as K-nearest neighbor, Stochastic Gradient Descent, Decision Tree, Random Forest, Multi-Layer Perceptron, and Deep Neural Network. After experimenting and validating with several performance parameters, the proposed method is found to be superior to others and signifies a robust in classifying the colon cancer.