🏥 Medical Imaging Diagnosis Agent

A powerful AI-powered application for analyzing and diagnosing medical images. This tool leverages Google's Gemini model to provide detailed analysis of various medical imaging formats including X-rays, MRIs, CT scans, and DICOM files.

⚠️ DISCLAIMER: This tool is for educational and informational purposes only. It is not a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of qualified healthcare providers for any medical concerns.

🌟 Features

• Modern, Intuitive UI: Clean and professional interface built with Streamlit
• Multi-format Support: Handles standard image formats (JPG, PNG, JPEG) and medical DICOM files
• AI-Powered Analysis: Utilizes Google's Gemini 2.0 model for state-of-the-art image interpretation
• Comprehensive Reports: Generates structured analysis including:
  • Image Type & Region Identification
  • Detailed Key Findings
  • Diagnostic Assessment with Confidence Levels
  • Patient-Friendly Explanations
  • Research Context with Recent Medical Literature

📋 Sample Analysis Output

The analysis provides a structured report with the following sections:

### 1. Image Type & Region
- X-ray imaging of the chest, PA (posteroanterior) view
- Good image quality with proper exposure and positioning

### 2. Key Findings
- Clear lung fields without infiltrates or masses
- Normal cardiac silhouette
- No pleural effusions
- Normal bony structures

### 3. Diagnostic Assessment
- Primary: Normal chest radiograph (95% confidence)
- No acute cardiopulmonary process identified

### 4. Patient-Friendly Explanation
Your chest X-ray looks normal. The lungs appear clear without any signs of infection or fluid...

### 5. Research Context
Recent studies on normal chest radiographs:
- [Link to relevant medical literature]
- [Standard protocols for chest X-ray interpretation]

🛠️ Installation & Setup

Prerequisites

• Python 3.8+
• Google API Key from Google AI Studio

Step-by-Step Installation

1. Clone the repository

   git clone https://github.com/apix7/ai-med.git
   cd ai-med

2. Create and activate a virtual environment

   python -m venv venv
   
   # On Windows
   venv\Scripts\activate
   
   # On macOS/Linux
   source venv/bin/activate

3. Install dependencies

   pip install -r requirements.txt

🚀 Usage

1. Start the application

   streamlit run med.py

2. Enter your Google API Key

   • On first launch, you'll be prompted to enter your Google API Key in the sidebar
   • This key is securely stored in your session state and not shared externally
   • You can get your API key from Google AI Studio

3. Upload a medical image

   • Use the file uploader to select an image file
   • Supported formats: JPG, JPEG, PNG, DICOM
   • Maximum file size: 200MB

4. Get AI Analysis

   • Click the "Analyze Image" button
   • Wait for the AI to process the image (typically 10-30 seconds)
   • Review the comprehensive analysis report

🔒 Privacy & Security

• All image processing happens on your local machine
• API keys are stored only in your session state and not persisted
• No patient data is stored or transmitted beyond what's needed for analysis

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

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

🙏 Acknowledgements

• Streamlit for the amazing web app framework
• Google Gemini for the AI model
• Agno AI for the agent framework