Brain Tumor Detection Using Deep Learning Models

Abstract

A brain tumor is a disease caused due to the growth of abnormal cells in the brain. There are two main categories of brain tumor, they are non-cancerous (benign) brain tumor and cancerous(malignant) brain tumor. Survival rate of a tumor prone patient is difficult to predict because brain tumor is uncommon and are different types. As per the cancer research by United Kingdom, around 15 out of every 100 people with brain cancer will be able to survive for ten or more years after being diagnosed. Treatment for brain tumor depends on various factors like: the type of tumor, how abnormal the cells are and where it is in the brain etc. With the growth of Artificial Intelligence, Deep learning models are used to diagnose the brain tumor by taking the images of magnetic resonance imaging. Magnetic Resonances Imaging (MRI) is a type of scanning method that uses strong magnetic fields and radio waves to produce detailed images of the inner body. The research work carried out uses Deep learning models like convolutional neural network (CNN) model and VGG-16 architecture (built from scratch) to detect the tumor region in the scanned brain images. We have considered Brain MRI images of 253 patients, out of which 155 MRI images are tumorous and 98 of them are non-tumorous. The paper presents a comparative study of the outcomes of CNN model and VGG-16 architecture used.