Study of Brain Tumor Detection using Deep Learning Model

Abstract

Nowadays people are suffered from various dangerous diseases. Brain tumor is one of the severe diseases among this. The severe stage of brain tumor leads to cancer which is nothing but excess cells growing in an uncontrolled manner in human body. Cancer is the major non-curable disease in the world. Due to cancer huge number of people affected which causes dangerous issues to the patients. Brain tumor cells grow in a way that they eventually take up all the nutrients meant for the healthy cells and tissues, which results in brain failure. Currently, doctors locate the position and the area of brain tumor by looking at the MRI images of the patient manually. The manual process provides inaccurate result and also very time consuming. The medical field needs fast, automated, efficient and reliable technique to detect tumor like brain tumor. This research work is motivated to detect brain tumor at earlier stage using machine learning model. The main objective of this research work is to use machine learning algorithm to detect brain tumor. Hence, this paper considered Deep Learning algorithm named as VGG16 (Visual Geometry Group) to detect the brain tumor. In order to analyze the performance of the machine learning algorithm sample dataset is collected from Kaggle. The collected dataset contains 431 tumor and non-tumor MRI images. The performance of the model is measured in terms of accuracy and confusion matrix and implemented using Python software platform.