An Interpretable Multiple-Instance Approach for the Detection of referable Diabetic Retinopathy from Fundus Images

TL;DR

This paper introduces an interpretable multiple-instance learning approach for detecting referable Diabetic Retinopathy from fundus images, achieving high accuracy and providing visual explanations of the disease manifestations.

Contribution

It presents a novel multiple-instance learning framework with an attention mechanism for DR detection that combines high accuracy with interpretability.

Findings

Achieves near state-of-the-art classification performance.

Provides visual explanations highlighting DR lesions.

Demonstrates effectiveness on public retinal image datasets.

Abstract

Diabetic Retinopathy (DR) is a leading cause of vision loss globally. Yet despite its prevalence, the majority of affected people lack access to the specialized ophthalmologists and equipment required for assessing their condition. This can lead to delays in the start of treatment, thereby lowering their chances for a successful outcome. Machine learning systems that automatically detect the disease in eye fundus images have been proposed as a means of facilitating access to DR severity estimates for patients in remote regions or even for complementing the human expert's diagnosis. In this paper, we propose a machine learning system for the detection of referable DR in fundus images that is based on the paradigm of multiple-instance learning. By extracting local information from image patches and combining it efficiently through an attention mechanism, our system is able to achieve high classification accuracy. Moreover, it can highlight potential image regions where DR manifests through its characteristic lesions. We evaluate our approach on publicly available retinal image datasets, in which it exhibits near state-of-the-art performance, while also producing interpretable visualizations of its predictions.