🧠 Brain Tumor MRI Image Classification

🚀 Deep Learning project for automatic Brain Tumor Detection & Classification using MRI Scans.
Built with TensorFlow/Keras, OpenCV, and Python.

---

---

📌 Overview

This project explores deep learning models for classifying Brain MRI Scans into 4 categories:

• 🟢 No Tumor
• 🟡 Meningioma
• 🔵 Glioma
• 🔴 Pituitary Tumor

We evaluate three architectures:

• ⚡ Multilayer Perceptron (MLP) – baseline
• 🧩 AlexNet (custom variant) – CNN-based
• 🚀 InceptionV3 (transfer learning) – best performance

---

🌟 Key Highlights

✨ Feature	🔍 Details
🧹 Preprocessing	Conversion from .mat → RGB, resize (128×128), normalization
🎨 Augmentation	Rotations, zoom, shear, brightness adjustments
🧠 Models	MLP, AlexNet variant, InceptionV3
📊 Dataset	3,459 T2-weighted MRI images
🎯 Results	InceptionV3 achieved 97.85% test accuracy
💡 Improvements	Transfer learning, augmentation, stratified sampling

---

📂 Project Structure

Brain_Tumor_Classification/
├── Brain_Tumor_MRI_Image_Classification.ipynb   # Main Notebook
├── dataset/                                     # MRI dataset
│   ├── Training/ (yes/no + classes)  
│   ├── Validation/  
│   ├── Testing/  
├── models/                                      # Saved models (H5/SavedModel)
├── results/                                     # Confusion matrix, plots
├── docs/                                        # Paper, screenshots
└── README.mdx                                   # Project Documentation

⚙️ Installation

Clone repository

git clone https://github.com/your-username/brain-tumor-classification.git
cd brain-tumor-classification

Create virtual environment

python -m venv venv
source venv/bin/activate   # Mac/Linux
venv\Scripts\activate      # Windows

Install dependencies

pip install -r requirements.txt

Dataset Link

https://drive.google.com/drive/folders/15HJheoZm5NLTytNxTu3X6Nm51lRuxq4g?usp=drive_link