Deep Neural Network Based Classifier Model for Lung Cancer Diagnosis and Prediction System in Healthcare Informatics

Abstract

Lung cancer is a most important deadly disease which results to mortality of people because of the cells growth in unmanageable way. This problem leads to increased significance among physicians as well as academicians to develop efficient diagnosis models. Therefore, a novel method for automated identification of lung nodule becomes essential and it forms the motivation of this study. This paper presents a new deep learning classification model for lung cancer diagnosis. The presented model involves four main steps namely preprocessing, feature extraction, segmentation and classification. A particle swarm optimization (PSO) algorithm is sued for segmentation and deep neural network (DNN) is applied for classification. The presented PSO-DNN model is tested against a set of sample lung images and the results verified the goodness of the projected model on all the applied images.