Deep neural network based classification of tumourous and non-tumorous medical images

Abstract

Tumor identification and classification from various medical images is a very challenging task. Various image processing and pattern identification techniques can be used for tumor identification and classification process. Deep learning is evolving technique under machine learning that provides the advantage for automatically extracting the features from the images. The computer aided diagnosis system proposed in this research work can assist the radiologists in cancer tumor identification based on various facts and studies done previously. The system can expedite the process of identification even in earlier stages by adding up the facility of a second opinion which makes the process simpler and faster. In this paper, we have proposed a framework of convolution neural network (CNN), that is a technique under Deep Learning. The research work implements the framework on AlexNet and ZFNet architectures and have trained the system for tumor detection in lung nodules and well as brain. The accuracy for classification is more than 97% for both the architectures and both the datasets of lung CT and brain MRI images.