A deep learning system for classifying dental implants using PyTorch, Flask, and Streamlit. The system identifies four types of dental implants: Endosteal, Subperiosteal, Transosteal, and Zygomatic.
- Real-time Classification: Upload and classify dental implant images instantly
- Interactive Dashboard: User-friendly Streamlit interface
- Performance Metrics: Confusion matrix, ROC curves, and class-wise metrics
- REST API: Flask backend for easy integration
-
Clone the repository: bash git clone https://github.com/yourusername/dental_implant_prediction.git cd dental_implant_prediction
-
Create and activate virtual environment: bash python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
-
Install dependencies: bash pip install -r requirements.txt
-
Start the Flask API: bash python src/app.py --port 5001
-
Run the Streamlit frontend: bash streamlit run src/frontend.py
-
Access the web interface at
http://localhost:8501
- Accuracy: 34.42%
- Precision: 13.81%
- Recall: 34.42%
Per-class Performance:
| Class | Precision | Recall | F1 Score |
|---|---|---|---|
| Endosteal | 0.XX | 0.XX | 0.XX |
| Subperiosteal | 0.XX | 0.XX | 0.XX |
| Transosteal | 0.XX | 0.XX | 0.XX |
| Zygomatic | 0.XX | 0.XX | 0.XX |
Total Images: 5,107
- Endosteal: 1,970 images
- Subperiosteal: 511 images
- Transosteal: 704 images
- Zygomatic: 1,922 images
python import requests url = 'http://localhost:5001/predict' files = {'image': open('path/to/image.jpg', 'rb')} response = requests.post(url, files=files) print(response.json())
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
- Deepali Ravindra Paspule - GitHub
Made with ❤️ by Deepali