Early Detection and Prediction of Lung Cancer Survival using Neural Network Classifier

Early Detection and Prediction of Lung Cancer Survival using Neural Network Classifier

Abstract—A new computer-aided diagnosis (CAD) system for early lung cancer detection based on the analysis of sputum color images is proposed. A set of features is extracted from the nuclei of the sputum cells after applying a region detection process. For training and testing the system we used two classification techniques: artificial neural network (ANN) and support vector machine (SVM) to increase the accuracy of the CAD system. The performance of the system was analyzed based on different criteria such as sensitivity, precision, specificity and accuracy. < Final Year Project > The evaluation was done by using Receiver Operating Characteristic (ROC) curve. The experimental results demonstrate the efficiency of SVM classifier over the ANN classifier with 97% of sensitivity and accuracy as well as a significant reduction in the number of false positive and false negative rates.