The Pneumonia Detection App is a web application built to assist in the diagnosis of pneumonia using chest X-ray images. It utilizes deep learning techniques implemented with TensorFlow and Keras for image classification, and is deployed using Streamlit for a user-friendly interface.
- Upload Image: Users can upload a chest X-ray image to the app.
- Prediction: The app predicts whether the uploaded image indicates pneumonia.
- Comparison: Provides visual comparison with sample normal and pneumonia chest X-ray images.
- User-Friendly Interface: Built with Streamlit to ensure easy navigation and interaction.
You can try the app here.
- TensorFlow: Deep learning framework for model training and prediction.
- Keras: High-level neural networks API (running on TensorFlow) used for building and training the deep learning models.
- Streamlit: Open-source app framework used to build interactive web applications for machine learning and data science.
- Python: Programming language used for development.
- matplotlib, Pillow (PIL): Python libraries used for image visualization and processing.
-
Clone the Repository:
- Clone the repository to your local machine.
-
Install Dependencies:
- Install Python dependencies listed in `requirements.txt`.
-
Run the Streamlit App:
- Start the Streamlit application locally.
-
Upload an Image:
- Use the app interface to upload a chest X-ray image.
-
View Results:
- The app will display the uploaded image and provide a prediction for pneumonia.
- Compare the uploaded image with sample normal and pneumonia images provided by the app.
We welcome contributions to improve the app. Here's how you can contribute:
- Fork the repository
- Create your feature branch (`git checkout -b feature/YourFeature`)
- Commit your changes (`git commit -am 'Add some feature'`)
- Push to the branch (`git push origin feature/YourFeature`)
- Create a new Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
- Mention any libraries or resources that you used or were inspired by during development.
For questions or feedback, feel free to contact Lokesh Vazirani.