Classification of Brain Tumors Using Convolutional Neural Networks

Diagnosing a brain tumor usually begins with magnetic resonance imaging (MRI). If MRI detects a tumor in the brain, the type of brain tumor is usually known by looking at the results from a sample of tissue after a biopsy or surgery. This procedure can be time consuming, tedious, and costly. This manual examination mechanism can be replaced by machine learning based automated techniques that can save precious time and significantly reduce human effort and error. This paper aims to make multi-classification of brain tumors using deep learning. The deep learning model can classify the brain tumor into four brain tumor types as normal, glioma, meningioma, and pituitary with an accuracy of 95.26%. Satisfactory classification results are obtained using large and publicly available clinical datasets. The proposed model can be employed to assist physicians and radiologists in detecting brain tumor.