GREEN: a Graph REsidual rE-ranking Network for Grading Diabetic Retinopathy

TL;DR

GREEN introduces a graph-based residual re-ranking network that explicitly models class dependencies to improve diabetic retinopathy grading accuracy, outperforming existing methods on standard benchmarks.

Contribution

The paper presents a novel GREEN model that incorporates class dependency priors via graph convolutional networks into DR grading, enhancing classification performance.

Findings

GREEN outperforms state-of-the-art methods on benchmark datasets.

The class dependency prior improves grading accuracy.

Residual re-ranking enhances the interpretability of classification results.

Abstract

The automatic grading of diabetic retinopathy (DR) facilitates medical diagnosis for both patients and physicians. Existing researches formulate DR grading as an image classification problem. As the stages/categories of DR correlate with each other, the relationship between different classes cannot be explicitly described via a one-hot label because it is empirically estimated by different physicians with different outcomes. This class correlation limits existing networks to achieve effective classification. In this paper, we propose a Graph REsidual rE-ranking Network (GREEN) to introduce a class dependency prior into the original image classification network. The class dependency prior is represented by a graph convolutional network with an adjacency matrix. This prior augments image classification pipeline by re-ranking classification results in a residual aggregation manner. Experiments on the standard benchmarks have shown that GREEN performs favorably against state-of-the-art approaches.