Classification and Stage Prediction of Lung Cancer using Convolutional Neural Networks

In recent years, digital image processing is widely used for the medical treatment classification and diagnosis. Lung cancer is the most leading cause of death in all over the world nowadays. Based on the signs and symptoms it can’t be diagnosis and treatment classified at the early stage. However it can be identified through the symptoms like coughing up blood and chest pain, the stages and risk factors of the cancer cannot be identified through the symptoms. The CT scanned lung images should be involved in image classification processing for earlier prediction of stages and treatment diagnosis. In existing, machine learning treatment classification can be done through the SVM classification. In case of large set of training samples, this will not be in accurate manner and it has less accuracy because of improper feature extraction techniques. Thus the performance of the classification based on the segmented features obtained in preceding sections. The extracted fine-grained training data through deep learning are utilized for the classification using Convolution Neural Network (CNN). In this paper, we propose a novel framework to classify both small cell and large cell lung cancer and predict its type and treatment using CNN. It is also concentrates on the preprocessing and segmentation processes to accomplish the accuracy in prediction. The experiment results in Python - TensorFlow with Kaggle image dataset show that compared to state of the art of classification and prediction methods, the proposed scheme can obtain much higher accuracy in type prediction and treatment diagnosis.