An AI-powered web application that helps users understand possible health issues from medical images using the Google Gemini API.
Warning
Disclaimer: This tool is for educational and informational purposes only. Always consult a qualified doctor before making any medical decisions.
The project is structured into dedicated modules for better maintainability and scalability:
app.py: Main entry point and Streamlit UI logic.ai_engine.py: Handles Google Gemini API configurations, prompts, and image analysis.pdf_utils.py: Logic for generating high-quality medical reports in PDF format.history_manager.py: Manages local storage of analysis results and image files.
- 📤 Multi-Image Upload: Batch process medical images (JPG, PNG).
- 🖼️ Grid View: Modern UI for previewing multiple uploaded files.
- 🧠 Advanced AI Analysis: Powered by Google Gemini (1.5-Flash) for pattern recognition.
- 📋 Structured Reports: Detailed findings, recommendations, and confidence scores.
- 📥 PDF Export: Download professional medical reports for each analysis.
- 📊 CSV Export: Export your entire analysis history for record-keeping.
- 📜 Persistent History: Keep track of past analyses with local image storage.
- ⚡ Interactive UI: Fast, responsive design with dark mode support.
- Python 3.9+
- Google Gemini API Key
-
Clone the repository
git clone https://github.com/fizaayesha/disease_identifier.git cd disease_identifier -
Create and activate a virtual environment
python -m venv venv source venv/bin/activate # Linux/Mac # OR venv\Scripts\activate # Windows
-
Install dependencies
pip install -r requirements.txt
-
Add your API key Create a
.streamlit/secrets.tomlfile:GOOGLE_API_KEY = "YOUR_GEMINI_API_KEY"
-
Run the application
streamlit run app.py
Contributions are welcome! Please follow our CONTRIBUTING.md guide. [Please start picking issues from here on which you can work, tag me and I will assign the issue and add labels accordingly. | #48]
This project is open source. See the LICENSE file for details.