Diabetic Retinopathy Lesion Segmentation through Attention Mechanisms

TL;DR

This paper introduces an attention-enhanced deep learning model for precise segmentation of diabetic retinopathy lesions, significantly improving detection accuracy and supporting early diagnosis through pixel-level annotations.

Contribution

It presents a novel Attention-DeepLab model that integrates attention mechanisms with DeepLab-V3+ for improved lesion segmentation in DR.

Findings

Increased mean average precision from 0.3010 to 0.3326

Enhanced microaneurysm detection from 0.0205 to 0.0763

Achieved better pixel-level lesion segmentation results

Abstract

Diabetic Retinopathy (DR) is an eye disease which arises due to diabetes mellitus. It might cause vision loss and blindness. To prevent irreversible vision loss, early detection through systematic screening is crucial. Although researchers have developed numerous automated deep learning-based algorithms for DR screening, their clinical applicability remains limited, particularly in lesion segmentation. Our method provides pixel-level annotations for lesions, which practically supports Ophthalmologist to screen DR from fundus images. In this work, we segmented four types of DR-related lesions: microaneurysms, soft exudates, hard exudates, and hemorrhages on 757 images from DDR dataset. To enhance lesion segmentation, an attention mechanism was integrated with DeepLab-V3+. Compared to the baseline model, the Attention-DeepLab model increases mean average precision (mAP) from 0.3010 to 0.3326 and the mean Intersection over Union (IoU) from 0.1791 to 0.1928. The model also increased microaneurysm detection from 0.0205 to 0.0763, a clinically significant improvement. The detection of microaneurysms is the earliest visible symptom of DR.