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:
