Fundus Grading
Collection
Trained with: Aptos, EyePACS, DDR and IDRiD.
•
25 items
•
Updated
Fundus DR Grading
Description
This project aims to evaluate the performance of different models for the classification of diabetic retinopathy (DR) in fundus images. The reported perfomance metrics are not always consistent in the literature. Our goal is to provide a fair comparison between different models using the same datasets and evaluation protocol.
- Downloads last month
- 7
Collection including ClementP/FundusDRGrading-resnet50
Evaluation results
- Quadratic Kappa on EYEPACSself-reported0.733
- Quadratic Kappa on IDRIDself-reported0.628
- Quadratic Kappa on DDRself-reported0.710