Eye Disease Detection System

This application uses deep learning to detect eye diseases from fundus images. Currently supports detection of:

  • Central Serous Chorioretinopathy
  • Diabetic Retinopathy
  • Disc Edema
  • Glaucoma
  • Healthy (normal eye)
  • Macular Scar
  • Myopia
  • Retinal Detachment
  • Retinitis Pigmentosa
Model Architecture

Examples (Please add your own example images)
Examples

How to use this application:

  1. Upload an image: Click the upload button to select a fundus image from your computer
  2. Specify model (Optional):
    • Enter the path to your trained model file (.pth)
    • Select the model architecture that was used for training
  3. Analyze: Click the "Analyze Image" button to get results
  4. Interpret results: The system will show the detected condition, probability distribution, and an attention heatmap

Attention Heatmap:

The attention heatmap visualizes which regions of the fundus image the model is focusing on when making its prediction.

  • Red/Yellow areas: Regions the model considers most important for the diagnosis
  • Blue/Green areas: Regions with less influence on the prediction

This helps in understanding and validating the model's decision-making process.

Model Information:

This system supports multiple model architectures:

  • MobileNetV4: Lightweight and efficient model
  • LeViT: Vision Transformer designed for efficiency
  • EfficientViT: Hybrid CNN-Transformer architecture
  • GENet: General and Efficient Network
  • RegNetX: Systematically designed CNN architecture

For best results, ensure you're using a high-quality fundus image and the correct model type.