📌 Overview
This project presents a high-performance deep learning pipeline for automated brain tumor classification using MRI images. It employs EfficientNetB3, a cutting-edge convolutional neural network (CNN) architecture, fine-tuned to accurately distinguish between various types of brain tumors.
Our goal is to provide a fast, reliable, and scalable solution that can assist medical professionals in making informed diagnostic decisions, reducing manual workload, and improving early detection rates.
🚀Highlights
🎯 High-accuracy multi-class classification of brain tumors.
⚡ Powered by EfficientNetB3, known for its efficiency and superior performance.
🧹 Built-in data preprocessing and augmentation to enhance generalization.
📊 Rich metrics visualization and confusion matrix for evaluation insights.
🔁 Modular design for seamless training, evaluation, and deployment.
🌐 Includes an interactive Streamlit web app.
🧠 Tumor Classes The model classifies MRI brain scans into the following four categories:
Glioma Tumor
Meningioma Tumor
Pituitary Tumor
No Tumor
📈 Model Performance
Metric Score
Accuracy ✅ 97%+
Precision ✅ High
Recall ✅ High
F1-Score ✅ Balanced
🙌 Contributing
We welcome all kinds of contributions! Whether it's bug fixes, suggestions, or adding new features — feel free to fork the repo and submit a pull request.
