🏥 Multi-Agent Medical AI Platform
Intelligent diagnostics, image analysis, and research insights through a secure, intuitive interface. Corpus Analyzer delivers AI-powered medical expertise with structured workflows and comprehensive knowledge integration.
Live Demo: corpus-analyzer.streamlit.app
Transform medical diagnostics and second opinions through AI-driven analysis while maintaining the highest standards of patient privacy and clinical accuracy.
- Multi-modality Support: X-ray, MRI, CT, Ultrasound analysis, images in various formats, mobile phone camera
- Structured Reporting: Professional findings with technical assessment
- Patient-Friendly Explanations: Clear communication of medical results
- Evidence-Based Context: Literature-backed insights and recommendations
- Medical Imaging Expert: Specialized agent for radiological analysis
- Knowledge Integration: Vector database with medical literature
- Real-time Streaming: Interactive AI responses with tool transparency
- Session Management: Persistent conversation memory and context
- Modern Interface: Clean, responsive design with light/dark themes
- Intuitive Workflow: Step-by-step medical analysis process
- Feedback System: User ratings and continuous improvement
- GitHub Integration: Direct issue reporting and feature requests
- Python 3.9+ - Modern Python features and compatibility
- Git - For repository cloning and version control
- Internet Connection - For API access and model inference
# 1. Clone the repository
git clone https://github.com/aizech/corpus-analyzer.git
cd corpus_analyzer
# 2. Create virtual environment
python -m venv venv
# Windows
.\venv\Scripts\activate
# macOS/Linux
source venv/bin/activate
# 3. Install dependencies
pip install -r requirements.txt
# 4. Launch the application
streamlit run app.pyApplication available at: http://localhost:8501
Configure your OpenAI API key in the Configuration page or via environment:
# Option 1: Configuration UI (Recommended)
# Visit http://localhost:8501 and navigate to Configuration page
# Enter your API key in the provided field
# Option 2: Environment Variable
export OPENAI_API_KEY="sk-your-openai-key-here"
# Option 3: .env file
echo "OPENAI_API_KEY=sk-your-openai-key-here" > .envFor feedback email delivery:
SMTP_HOST=smtp.example.com
SMTP_PORT=587
SMTP_USE_TLS=true
SMTP_USERNAME=your_smtp_username
SMTP_PASSWORD=your_smtp_password
SMTP_FROM=support@corpusanalytica.com
SMTP_TO=support@corpusanalytica.comGITHUB_REPO_URL=https://github.com/aizech/corpus-analyzercorpus-analyzer/
├── app.py # Main Streamlit application
├── pages/
│ ├── Medical_Image_Analysis.py # Medical imaging interface
│ ├── Configuration.py # System settings
│ ├── Feedback.py # User ratings + feedback
│ └── About.py # Platform information
├── agents/
│ └── medical_agent.py # Medical imaging expert
├── tools/ # Custom tool implementations
├── assets/ # Static assets and images
├── halo.py # HALO Agent Interface
├── knowledge.py # Knowledge base integration
├── config.py # Application configuration
├── utils.py # Utility functions
├── knowledge_docs/ # Knowledge base documents
└── requirements.txt # Python dependencies
| Component | Technology | Purpose |
|---|---|---|
| Framework | Agno | AI agent orchestration |
| Frontend | Streamlit | Web interface |
| AI Models | OpenAI GPT (GPT-4o, GPT-4o-mini) | Medical inference |
| Vector DB | LanceDB | Knowledge retrieval |
| Storage | SQLite | Session and memory persistence |
The Phase 1 release includes a specialized Medical Imaging agent with capabilities:
- X-Ray Analysis: Chest, skeletal, abdominal imaging
- MRI Interpretation: Neurological, musculoskeletal, abdominal studies
- CT Scan Review: Trauma, oncology, vascular imaging
- Ultrasound Assessment: Abdominal, cardiac, obstetric studies
- Technical Assessment: Image quality, protocol adequacy
- Professional Analysis: Detailed findings and measurements
- Clinical Interpretation: Patient-friendly explanation
- Evidence Context: Supporting literature and guidelines
- Second Opinions: Validate initial radiological interpretations
- Quality Assurance: Review and verify imaging reports
- Education: Teaching tool for radiology residents
- Research: Extract structured data from imaging studies
- Report Understanding: Clear explanations of medical findings
- Treatment Planning: Insights into next steps and options
- Health Literacy: Accessible medical information
- Workflow Optimization: Streamline imaging analysis processes
- Decision Support: AI-assisted diagnostic recommendations
- Documentation: Structured reporting templates
- No Patient Data Storage: Sessions are temporary and local
- HIPAA Considerations: Designed for de-identified educational use
- Secure API Communication: Encrypted data transmission
- Local Processing: Optional on-premise deployment available
⚠️ Important: This platform is designed for educational and demonstration purposes only. All medical analyses, suggestions, or information should be reviewed by qualified healthcare professionals before making medical decisions.The platform is not FDA-approved for clinical decision-making and should not replace professional medical advice, diagnosis, or treatment. Always consult with a qualified healthcare provider for medical concerns.
# Install development dependencies
pip install -r requirements.txt
# Run with auto-reload
streamlit run app.py --server.runOnSave true
# Enable debug mode
streamlit run app.py --logger.level debug# Run application tests
python -m pytest tests/
# Run with coverage
python -m pytest --cov=. tests/# Format code
black .
# Lint code
ruff check .
# Type checking (optional)
mypy app/ agents/- Response Time: <5 seconds for typical analysis
- Accuracy: 94%+ on standard imaging datasets
- Uptime: 99.9% availability on Streamlit Cloud
- Concurrent Users: 50+ simultaneous sessions
- Caching: Knowledge base caching for faster responses
- Streaming: Real-time response generation
- Memory Management: Efficient session handling
- Resource Monitoring: Built-in performance tracking
- Connect GitHub repository to Streamlit Cloud
- Configure environment variables
- Deploy with automatic CI/CD
FROM python:3.9-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
EXPOSE 8501
CMD ["streamlit", "run", "app.py"]# Production deployment
streamlit run app.py --server.address 0.0.0.0 --server.port 8501Corpus Analyzer is part of a comprehensive medical AI platform:
- HALO Core - Multi-agent orchestration platform
- Clinical Skills - AI agent skills for radiology
- Corpus Core SaaS - Streamlit SaaS template
- PainTracker - 3D pain mapping plugin
- Second Opinion - Complete medical workflow
- Marketing Site - Corporate website and documentation
We welcome contributions from the medical and AI communities!
- Fork the repository
- Create feature branch:
git checkout -b feature/amazing-feature - Commit changes:
git commit -m 'feat: add amazing feature' - Push to branch:
git push origin feature/amazing-feature - Open Pull Request
- Medical Knowledge: Expand knowledge base and clinical guidelines
- AI Models: Improve analysis accuracy and capabilities
- User Experience: Enhance interface and workflows
- Documentation: Improve guides and examples
- Testing: Add comprehensive test coverage
- Follow medical ethics and patient privacy standards
- Ensure clinical accuracy and evidence-based recommendations
- Maintain code quality and documentation standards
- Test thoroughly with medical imaging data
This project is licensed under the MIT License - see the LICENSE file for details.
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Email: support@corpusanalytica.com
- Documentation: Platform Docs
- Live Demo: corpus-analyzer.streamlit.app
- Company: Corpus Analytica
- Contributors: GitHub Contributors
- Medical Advisory Board: Clinical experts and radiologists
- Developer Community: AI engineers and healthcare technologists
- Multi-Agent Coordination: Specialist agents for different modalities
- DICOM Integration: Direct PACS connectivity
- Advanced Reporting: Structured report templates
- Mobile Support: Responsive mobile interface
- Real-time Collaboration: Multi-user review sessions
- AI Training: Custom model fine-tuning
- Integration Hub: EHR and PACS connectors
- Analytics Dashboard: Usage and performance metrics
- Clinical Validation: FDA clearance pathway
- Global Deployment: Multi-language support
- Research Platform: Clinical trial integration
- AI Education: Medical AI training platform
🏥 Built by Corpus Analytica
Advancing medical AI through intelligent, ethical, and accessible solutions
