International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 10 | Oct 2025
p-ISSN: 2395-0072
www.irjet.net
BRAIN TUMOR DETECTION USING AI: A DEEP LEARNING APPROACH USING A CNN MODEL Rohan Mundlik1 1MCA SE, Pune
2Prof. Shahuraj Yevate, Dept. of MCA, RJSPM Dudulgaon, Pune , Maharashtra, India
---------------------------------------------------------------------***--------------------------------------------------------------------2004 and 2020 from nearly 10% to 15% [16]. There are Abstract - The proposed model utilizes a Convolutional Neural Network (CNN) for efficient brain tumor detection and about 130 different forms of tumors that can affect the classification using MRI images. By comparing the CNN with brain and CNS, all of which can range from benign to models like ResNet-50, VGG16, and Inception V3, and malignant, from exceedingly rare to common [5]. The evaluating them using metrics such as accuracy, recall, loss, 130 brain cancers are divided into primary and and AUC, the CNN achieved superior performance with an secondary tumors [17]: accuracy of 99% on a dataset of 3264 MR images. This demonstrates the model’s reliability for early and accurate detection of various brain tumors, contributing to timely diagnosis and treatment.
Primary brain tumors: Primary brain tumors are those that develop in the brain. A primary brain tumor may develop from the brain cells and may be encased in nerve cells that surround the brain. This type of brain tumor can be benign or malignant [18]. Secondary brain tumors: The majority of brain malignancies are secondary brain tumors, which are cancerous and fatal. Breast cancer, kidney cancer, or skin cancer are examples of conditions that begin in one area of the body and progress to the brain. Although benign tumors do not migrate from one section of the body to the other, secondary brain tumors are invariably cancerous [19].
Key Words: brain tumor; CNN; deep learning; MR images
1.INTRODUCTION The brain, which is the primary component of the human nervous system, and the spinal cord make up the human central nervous system (CNS) [1]. The majority of bodily functions are managed by the brain, including analyzing, integrating, organizing, deciding, and giving the rest of the body commands.
1.1 Problem Statement
The human brain has an extremely complicated anatomical structure [2]. There are some CNC disorders, including stroke, infection, brain tumors, and headaches, that are exceedingly challenging to recognize, analyze, and develop a suitable treatment for [3]. A brain tumor is a collection of abnormal cells that develops in the inflexible skull enclosing the brain [4–6]. Any expansion within such a constrained area can lead to issues. Any type of tumor developing inside the skull results in brain injury, which poses a serious risk to the brain [7,8]. In both adults and children, brain tumors rank as the tenth most prevalent cause of death [9].
Brain tumors are life-threatening conditions that require early detection for effective treatment. Traditional diagnosis relies on manual MRI scan analysis by radiologists, which can be time- consuming, subjective, and prone to errors. Additionally, distinguishing between benign and malignant tumors is challenging due to similar visual features in MRI images. This project aims to develop an AI-based brain tumor detection system using deep learning (VGG16 CNN model) to classify brain scans as tumor or no tumor. The goal is to create an automated, accurate, and fast diagnosis tool that can assist healthcare professionals, reducing diagnostic errors and improving patient outcomes. The system will be accessible through a REST API and a React-based web application, making it easy for users to upload and analyze MRI images.
Every year, 14.1% of Americans are affected by primary brain tumors, of which 70% are children. Although there is no early therapy for primary brain tumors, they do have long- term negative effects [14,15]. Brain tumor cases increased significantly globally between © 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 539