Diabetic Retinopathy Detection via Deep Convolutional Networks for Discriminative Localization and Visual Explanation

TL;DR

This paper introduces a deep learning approach for diabetic retinopathy detection that not only achieves high accuracy but also provides visual explanations by localizing key retinal regions, enhancing interpretability.

Contribution

The paper presents a novel CNN-based method incorporating regression activation maps for localized and interpretable diabetic retinopathy detection, improving both performance and explainability.

Findings

High detection accuracy comparable to state-of-the-art methods

Effective localization of retinal regions related to DR severity

Enhanced interpretability through visual explanations

Abstract

We proposed a deep learning method for interpretable diabetic retinopathy (DR) detection. The visual-interpretable feature of the proposed method is achieved by adding the regression activation map (RAM) after the global averaging pooling layer of the convolutional networks (CNN). With RAM, the proposed model can localize the discriminative regions of an retina image to show the specific region of interest in terms of its severity level. We believe this advantage of the proposed deep learning model is highly desired for DR detection because in practice, users are not only interested with high prediction performance, but also keen to understand the insights of DR detection and why the adopted learning model works. In the experiments conducted on a large scale of retina image dataset, we show that the proposed CNN model can achieve high performance on DR detection compared with the state-of-the-art while achieving the merits of providing the RAM to highlight the salient regions of the input image.