Kidney Stone AI Analyzer

A full-stack AI-powered web application for classifying kidney CT scan images as Normal, Cyst, Stone, or Tumor.

Features

• User login authentication
• Upload and analyze kidney CT scan images
• Deep learning model (MobileNetV2 transfer learning)
• Real-time predictions with confidence scores
• Modern, responsive UI

Getting Started

Prerequisites

• Python 3.8+
• Node.js & npm (for frontend)

Backend Setup

1. Navigate to the backend directory:

   cd backend
   

2. Create a virtual environment and activate it:

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

3. Install dependencies:

   pip install -r requirements.txt
   

4. Run the backend server:

   python app.py
   

Frontend Setup

1. Navigate to the frontend directory:

   cd frontend
   

2. Install dependencies:

   npm install
   

3. Start the frontend:

   npm run dev
   

4. Open your browser at http://localhost:5173

Login Credentials

• Username: admin
• Password: password123

Project Structure

kidney-stone-analyzer/
├── backend/
│   ├── app.py                    # Flask backend server
│   ├── train_model.py           # Model training script
│   ├── kidney_stone_cnn_model.h5 # Trained model file
│   ├── class_labels.json       # Class labels for predictions
│   ├── requirements.txt        # Python dependencies
│   └── samples/                # Sample images for testing
├── frontend/
│   ├── src/
│   │   ├── components/         # React components
│   │   └── pages/             # React pages
│   ├── package.json           # Node.js dependencies
│   └── ...                    # Other frontend config files
├── README.md
└── LICENSE

Dataset

The data/ directory contains ~12,000 CT scan images organized by class:

• Cyst: 3,709 images
• Normal: 5,077 images
• Stone: 1,377 images
• Tumor: 2,283 images

Note: The whole dataset is excluded from the Git repository due to its large size (~GB). If you need to download the Dataset completly then See data/README.md for more details.

License

MIT

Screenshots