Abstract :

Brain Tumors Are Among The Most Critical Neurological Disorders, Where Early And Accurate Diagnosis Is Crucial For Effective Treatment And Improved Patient Outcomes. Manual Analysis Of Magnetic Resonance Imaging (MRI) Scans Is Timeconsuming, Relies On Expert Radiologists, And Can Lead To Inconsistent Interpretations. To Address These Challenges, This Project Introduces A Deep Learning-Based Medical Image Segmentation System That Automates Brain Tumor Detection And Segmentation From MRI Images. The System Employs A Convolutional Neural Network (CNN) To Classify MRI Scans Into Four Categories: Glioma, Meningioma, Pituitary Tumor, And No Tumor. During Preprocessing, All MRI Images Are Resized To 224 × 224 Pixels And Normalized To Ensure Uniform Input And Enhance Model Accuracy. The CNN Architecture Integrates Convolutional And Max-pooling Layers For Feature Extraction, Dense Layers For Classification, Dropout Layers To Prevent Overfitting, And A SoftMax Output Layer For Multi-class Prediction. Upon Tumor Detection, K-Means Clustering Segments The Tumor Region, Enabling Clear Visualization Of Abnormal Tissues. The System Also Displays Prediction Confidence And Offers Basic Medical Recommendations Based On The Tumor Type. Developed Using Python And The Flask Framework, The Application Features A Secure, User-friendly Web Interface With User Authentication And Image Upload Capabilities. Additionally, The System Supports Model Training, Dataset Analysis, And Performance Visualization. Overall, This Solution Provides A Fast, Accurate, And Reliable Computer-aided Tool For Brain Tumor Detection And Segmentation, Reducing Manual Effort And Assisting Healthcare.

Published:

29-7-2026

Issue:

Vol. 26 No. 7 (2026)

Page Nos:

1362-1370

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite