Lung Cancer Detection and Classification using 2D Convolutional Neural Network

The deaths caused by cancer is increasing day by day and one of the major reasons is lung cancer. Detecting lung cancer at initial stages greatly lessens the number of patients dying and dramatically increases the likelihood that the patient will be saved. Lung cancer does not show any symptoms at early stages which makes it difficult to get treated at early stage which eventually reduces the survival rate. The traditional method of lung cancer detection such as Histopathological assessment of tissue is time consuming. An automated tool which can detect the lung cancer nodule using the CT images reduces a lot of work, saves time and also reduces the errors. The speedy detection of the lung cancer nodule can be advantageous and reduce the risk of patient's survival as well as helps the pathologists. Therefore, the role of automated tool would become significant. This paper aims to classify malignant and non-malignant cells development in the lungs using the 2D Convolutional Neural Network (CNN) algorithm to classify the tumors found in lung as malignant or benign. This method was evaluated on Kaggle CT scans, experimental results show that our method achieves 88.76% accuracy in identifying lung nodules from CT images, which is more efficient as compared to accuracy obtained by the traditional neural network systems.