🧠 Brain Tumor Classification and Segmentation using Deep Learning

A deep learning-powered system for accurate brain tumor Classification and Segmentation using CNN models.

---

🔗 Project Links

• 🌐 Website Preview: View Live
• 📂 Full Project Files (Drive): Download from Google Drive
• 🧠 Trained Models (Drive): Access Model Files
• 📄 Published Research Paper: Springer Link

---

📁 Repository Structure

This repository consists of the following three main folders:

1. documents/

Contains all the documentation related to the project:

• Abstract
• Final Report
• PPT Presentations
• Research Paper

2. flask_app/

The core Flask application:

• app.py: Flask server
• templates/: HTML templates
• static/: CSS, JS, and images
• model/: Training scripts and saved models
• requirements.txt: Python dependencies

3. docs/

Static version of the app, suitable for GitHub Pages deployment.

---

🧠 Project Overview

Brain tumor Classification and Segmentation is a critical task in medical imaging. This project presents a web-based intelligent system powered by deep learning to assist radiologists and doctors in diagnosing brain tumors from MRI images. Models such as VGG16, EfficientNetB0, and ResNet50 were used to classify different types of tumors with high accuracy.

🔬 Key Features:

• CNN-based detection of glioma, meningioma, and pituitary tumors
• Real-time prediction via Flask web app
• Visualization of results, accuracy graphs, and predictions
• Research published in Springer

---

🖥️ System Specifications

Component	Specification
OS	Windows 11 / Ubuntu 22.04
Processor	Intel Core i5
RAM	8 GB DDR4
GPU	Google Colab / CUDA-compatible GPU (optional)
Libraries	TensorFlow, Keras, Flask, OpenCV, NumPy
IDE	VS Code / Jupyter Notebook

---

📸 Screenshots

---

👨‍💻 Developers

• Mohammed Aflah

• Minhaj Akavalapil

• Mohammed Aseel

• Mohammed Jasim A.

---

🎓 Faculty Coordinators

• Najla Musthafa – Assistant proffessor, MEAEC

• Dr. Shanid Malayil – Associate proffessor, MEAEC

• Mubeena A K – Assistant proffessor, MEAEC

---

📚 Research Publication

Title: EfficientNet-Based and YOLO-Driven Brain Tumor Detection and Segmentation.
Published in: Springer
Authors: Mohammed Aflah, Minhaj Akavalappil, Mohammed Aseel, Mohammed Jasim A., Najla Musthafa, Dr. Shanid Malayil, Mubeena AK
📄 DOI & Link: Springer Link
🏫 Affiliation: Department of Computer Science & Engineering, MEA Engineering College

---

⚖️ License & Acknowledgement

© 2025 Department of Computer Science & Engineering, MEA Engineering College, Perinthalmanna
All rights reserved. This project is submitted as part of the final academic capstone and is protected under institutional copyright.

Special thanks to Students and all faculty members for their continued support and mentorship.

---

📫 Contact

For queries or collaboration, contact:
📧 mohdaflah77@gmail.com
🌐 LinkedIn – Mohammed Aflah

---