Detection of Lung Cancer and Prediction of Life Expectancy Post Thoracic Surgery

Lung Cancer is a disease characterized by the uncontrolled cell growth in tissues of the lungs. It is one of the dangerous and life taking disease in the world. Early detection of lung cancer helps in identification of the treatment to be given which in turn increases the chances of survival of the lung cancer infected patient. This paper presents an approach which utilizes Convolution Neural network (CNN) to classify the CT lung images as cancerous or non-cancerous. The accuracy obtained by means of CNN is 95% which is more efficient when compared to accuracy obtained by the traditional neural network systems. Once the cancer is detected the paper also presents an approach to predict the life expectancy of the lung cancer infected patient post thoracic surgery. The prediction part is implemented using Machine Learning techniques. Linear Discriminant Analysis gave an accuracy of 83.76% with a F-measure of 0.83 which is more compared to other machine learning algorithms used.