Article

Explainable Deep Learning for Lesion-Level Detection of Diabetic Retinopathy: A Segmentation Approach Using Fundus Images Graded as Mild-to-Moderate Nonproliferative Diabetic Retinopathy

2025-10-03

Abstract excerpt

Deep learning has shown promise in diabetic retinopathy screening using fundus images. However, many existing models operate as “black boxes,” providing limited interpretability at the lesion level. This study aimed to develop an explainable deep learning model capable of detecting four diabetic retinopathy-related lesions—hemorrhages, hard exudates, cotton wool spots, and microaneurysms—and evaluate its performan...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: a9996789-8923-5139-876f-e79681d56c61
DOI: 10.1101/2025.10.01.25337115

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Explainable Deep Learning for Lesion-Level Detection of Diabetic Retinopathy: A Segmentation Approach Using Fundus Images Graded as Mild-to-Moderate Nonproliferative Diabetic RetinopathyDOI 10.1101/2025.10.01.25337115Read

An Efficient and Interpretable Foundation Model for Retinal Image Analysis in Disease DiagnosisSemantic proximity Read

How does AI detect diabetic retinopathy from retinal photos? A heatmap analysis of 54 deep learning modelsSemantic proximity Read

GRAD-Net: A Unified Pathology-Guided Framework for Automated Diabetic Retinopathy GradingSemantic proximity Read

Automated Interpretation of Fundus Fluorescein Angiography with Multi-Retinal Lesion SegmentationSemantic proximity Read

EDNet-20: Enhancing Multi-Label Ocular Disease Detection through Deep Learning OptimizationSemantic proximity Read

Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification modelsSemantic proximity Read

EyeDx: A Scalable and Interpretable Multitask Deep Learning Framework for Comprehensive Ocular Disease Detection in Fundus ImagesSemantic proximity Read

Delineating retinal breaks in ultra-widefield fundus images with a PraNet-based machine learning modelSemantic proximity Read

Autonomous Screening for Laser Photocoagulation in Fundus Images Using Deep LearningSemantic proximity Read

Clinically Interpretable Deep Learning via Sparse BagNets for Epiretinal Membrane and Related Pathology DetectionSemantic proximity Read

Demystifying CNN with Mathematical Insights: A Prelude with Application to an AI-based Sustainable Solution for Diabetic Retinopathy DiagnosisSemantic proximity Read

Advanced Machine Learning Techniques for Retinal Lesion Segmentation: A Comprehensive Review Across Ophthalmic PathologiesSemantic proximity Read