Retina4IRD Models Release

This repository hosts the official release of An AI-based Clinician-Decision Support System for Inherited Retinal Diseases: A Multicenter Clinical Validation Trial: GitHub Repository

We release Retina4IRD_imageModel_CFP, Retina4IRD_imageModel_OCT, Retina4IRD_combinedModel_CFP, and Retina4IRD_combinedModel_OCT, which are designed for inherited retinal disease (IRD) diagnosis using CFP images, OCT images, and clinical metadata as inputs.

Model Overview

The released checkpoints include:

Model	Description
Retina4IRD_imageModel_CFP	Image-only model trained on CFP images
Retina4IRD_imageModel_OCT	Image-only model trained on OCT images
Retina4IRD_combinedModel_CFP	Model trained on CFP images and clinical metadata
Retina4IRD_combinedModel_OCT	Model trained on OCT images and clinical metadata

Model Details

• Retina4IRD_imageModel_CFP: Designed for IRD diagnosis using CFP images only.
• Retina4IRD_imageModel_OCT: Designed for IRD diagnosis using OCT images only.
• Retina4IRD_combinedModel_CFP: Designed for IRD diagnosis using CFP images and clinical metadata.
• Retina4IRD_combinedModel_OCT: Designed for IRD diagnosis using OCT images and clinical metadata.

Usage

To use the models in Python and PyTorch, please refer to the detailed usage tutorial at GitHub Repository

Citation

If you use Retina4IRD in your research, please cite the corresponding paper.