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: 0

Safetensors

Model size

86.5M params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Evaluation results

Quadratic Kappa on EYEPACS
self-reported

0.734
Quadratic Kappa on IDRID
self-reported

0.824
Quadratic Kappa on DDR
self-reported

0.752

View on Papers With Code