International Journal of Research and Innovation in Applied Science (IJRIAS) |Volume VII, Issue IX, September 2022|ISSN 2454-6194
A Deep Learning Based Classification Model for the Detection of Brain Tumor using MRI
Md. Abid Hasan Nayeem*, Mehedi Hasan Shakil*, Sadia Afrin, Sadah Anjum Shanto, Shadia Jahan Mumu, Md. Mahmudul Hasan Shanto
Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh
*Corresponding Author
Abstract: The diagnosis of a brain tumor requires high accuracy, as even small errors in judgment can lead to critical problems. For this reason, brain tumor segmentation is an important challenge for medical purposes. The wrong classification can lead to worse consequences. Therefore, these must be properly divided into many classes or levels, and this is where multiclass classification comes into play. The latest development of image classification technology has made great progress, and the most popular and better method is considered to be the best in this area is CNN, so this paper uses CNN for the brain tumor classification problem. The proposed model successfully classifies brain images into two distinct categories, namely the absence of tumors indicating that a given brain MRI is free of tumors or the Brain contains Tumor. This model produces an accuracy based on the results of a study that was conducted on a group of volunteers.
Keywords: Convolutional Neural Network, Kaggle, Segmentation, Classification, MRI
I. INTRODUCTION
A tumor is a mass of tissue that is caused by abnormal cells grouping together. A brain tumor is a mass or lump in the brain which is caused by uncontrolled cell division in the brain. A brain tumor is considered malignant if it contains cancer cells, or if it consists of harmful cells located in areas that inhibit one or more important functions. Magnetic resonance imaging (MRI) is a medical imaging technique used in radiology to form images of the anatomy and physiological processes of the body. MRI scanners use strong magnetic fields and radio waves to create images of parts of the body. Healthcare professionals use MRI to detect the presence of brain tumors and to assess their location, size, and other features. The contrast agents used in MRI provide better image detail that can help us identify abnormal cells in our brain tissues. Nowadays, there are various ways to classify MRI scans, such as the Fuzzy method, neural network, and differential segmentation. The medical image processing system has provided many helpful methods that help to speed up the classification task in a shorter amount of time and with greater accuracy. The most significant steps in medical image processing are feature extraction and feature selection, image segmentation, and image classification. Feature selection is even more essential than feature extraction because it allows you to get a smaller, more accurate subset of features. Most of the methods used to classify brain tumors are based on segmentation. This means that the problem of classification