InSight is a comprehensive medical imaging analysis system designed to analyze chest X-rays, MRI images for tumor detection, and dementia prediction. It employs various deep learning models to accurately diagnose medical conditions and generate detailed medical reports.
- Dementia Prediction: Utilizes a self-trained model to predict dementia severity levels (no dementia, very mild, mild, moderate).
- Chest X-ray Analysis: Utilizes a DenseNet model from the
torchxrayvisionlibrary to classify 14 different lung diseases accurately. - Tumor Detection: Employs YOLOv3-tiny for brain tumor detection in MRI images.
- Medical Report Generation: Generates detailed medical reports based on the analysis results.
- API Integration with Gemini AI: Connects with Gemini AI through API for report generation from analysis result and provide with cross-checking suggestions for radiologist.
- Report Lab:ReportLab dynamically generates detailed medical reports based on the analysis results obtained
-
Clone the repository:
git clone https://github.com/your-username/InSight.git
-
Install dependencies:
pip install -r requirements.txt npm install #using React.js for frontend -
set the API Key:
import { GoogleGenerativeAI } from "https://esm.run/@google/generative-ai";
-
Start the Flask server:
python server.py
-
Access the application at http://localhost:5000.
-
Upload medical images for analysis and view the generated medical reports.
- Endpoint:
/api/analyze - Method: POST
- Request Body: JSON object containing the medical image data.
- Response: JSON object containing the analysis results and medical report.
Example request:
{
"image": "base64_encoded_image_data"
}Contributions are welcome! Please read the contribution guidelines before making any changes.
This project is licensed under the MIT License.