---
license: mit
library_name: pytorch
pipeline_tag: image-classification
base_model: vgg16
metrics:
- accuracy
tags:
- brain-tumor
- medical-imaging
- mri
- vgg16
- transfer-learning
- colorized-images
- pytorch
- image-classification
language:
- en
---

# Brain Tumor Classification using VGG16 (Colorized MRI)

This repository contains a **VGG16 transfer learning model trained on enhanced colorized MRI images** for automated brain tumor classification.

## 🧠 Tumor Classes
- Glioma  
- Meningioma  
- Pituitary  

## 📊 Model Performance
- **Test Accuracy:** **88.70%**
- **Framework:** PyTorch
- **Architecture:** VGG16 (Transfer Learning)
- **Pre-trained on:** ImageNet
- **Input Size:** 224×224 RGB
- **Number of Classes:** 3

## 🎨 Colorization Strategy
MRI images were enhanced using **CLAHE** and converted into multiple colormap representations to study the impact of color information on classification performance.

## 🏆 Best Model Checkpoint
represents the **best-performing checkpoint**, saved at peak validation accuracy.

## 🔬 Training Highlights
- Transfer learning with frozen convolution layers
- Fine-tuned classifier head
- Data augmentation
- Stratified train/validation/test split (70/15/15)
- Early stopping and learning rate scheduling

## ⚠️ Disclaimer
This model is intended **strictly for research and educational purposes** and must not be used for clinical diagnosis or treatment planning.

## 👤 Author
**Prashant Parwani**

The uploaded file: