An advanced machine learning application for accurate detection and classification of brain tumors from MRI scans.

This project combines state-of-the-art deep learning techniques with a modern web interface to assist medical professionals in the early detection of brain tumors. Leveraging a fine-tuned ResNet-18 model, our system delivers high-accuracy tumor classification while maintaining an intuitive user experience.

• Intelligent Analysis: Deep learning-powered detection of brain tumors from MRI scans
• Multi-Class Classification: Identification of tumor type with confidence scores
• Interactive Dashboard: Clean, responsive UI for easy navigation and results visualization
• Clinical Reporting: Generate comprehensive PDF reports for medical documentation
• Accessibility: Dark/light mode support and responsive design for all devices

• Framework: React 19 with TypeScript
• Styling: TailwindCSS with custom theme integration
• Components: Headless UI for accessible interactive elements
• Visualization: Chart.js for results representation
• Reporting: jsPDF for clinical documentation

• API: FastAPI for high-performance Python backend
• ML Framework: PyTorch with CUDA acceleration support
• Model: Fine-tuned ResNet-18 architecture
• Image Processing: OpenCV and PIL for preprocessing
• Data Handling: Pandas and NumPy for efficient data management

• Python 3.9+
• Node.js 18+
• GPU support recommended for inference (CUDA compatible)

1. Clone the repository:

   git clone https://github.com/sarcasticdhruv/brain-tumor-detection.git
   cd brain-tumor-detection

2. Install backend dependencies:

   pip install -r requirements.txt

3. Install frontend dependencies:

   cd brain-tumor-classifier
   npm install

4. Start the backend server (set up APIs):

   cd..
   uvicorn app:app --reload

5. In a new terminal, start the frontend:

   cd brain-tumor-classifier
   npm start

6. Access the application at http://localhost:3000

7. If you want to RUN by using just one command, and adjust by doing some Manual changes in app.py and app.js

   cd brain-tumor-classifier
   npm run build
   cd ..
   uvicorn app:app --host 0.0.0.0 --port 3000
   

1. Upload a T1-weighted MRI scan through the interface
2. Review the preprocessing steps applied to the image
3. Examine the detection results with confidence metrics
4. Generate and download a clinical report if desired

Evaluated on a dataset of 3,000 MRI scans across multiple institutions.

We welcome contributions to enhance the system's capabilities:

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• Brain Tumor MRI Dataset for training data
• FastAPI for the backend framework
• React for the frontend framework
• PyTorch for the machine learning framework