Multi-Class classification of brain tumor images using data augmentation with deep neural network

Abstract Brain is central to the nervous system (CNS) of the human body, it is a group of white masses of cells. These cells grow abnormally by multiplying rapidly with each other is called a brain tumor, which can lead to the death of an individual if not detected. The most common types of tumors which are occurred in the brain are meningioma, glioma, and pituitary tumors. Manually diagnosing and classifying brain tumors is a big challenge for physicians and clinical professionals, accuracy depends solely on their experience. Therefore, computer-assisted technology must be used to overcome these limitations. With the daily improvement of modern medical standards, artificial intelligence plays an important role in identifying and classifying brain tissues and this is of great interest to researchers. It is currently being developed with various machine learning and DL structures. In the past, several ML algorithms such as SVM, KNN, and CNN have been implemented for tumor identification and tumor binary and multi classification using MR images. But these algorithms are not giving the best results. Therefore, we have proposed a DNN based VGG-16 network to improve the accuracy of multi-classification of brain tumor MR images. Finally, our proposed model gives the best results with 98% accuracy after 20 epochs of model training.