Region Guided Attention Network for Retinal Vessel Segmentation

TL;DR

This paper introduces a lightweight encoder-decoder network with region-guided attention and weighted dice loss for improved retinal vessel segmentation, demonstrating superior performance on benchmark datasets.

Contribution

The work proposes a novel region-guided attention mechanism within a lightweight segmentation network, enhancing focus on foreground regions and addressing class imbalance with weighted dice loss.

Findings

Achieved higher recall, precision, accuracy, and F1 scores compared to existing methods.

Effectively handled class imbalance in retinal vessel segmentation.

Improved boundary delineation and reduced fragmentation in segmentation results.

Abstract

Retinal imaging has emerged as a promising method of addressing this challenge, taking advantage of the unique structure of the retina. The retina is an embryonic extension of the central nervous system, providing a direct in vivo window into neurological health. Recent studies have shown that specific structural changes in retinal vessels can not only serve as early indicators of various diseases but also help to understand disease progression. In this work, we present a lightweight retinal vessel segmentation network based on the encoder-decoder mechanism with region-guided attention. We introduce inverse addition attention blocks with region guided attention to focus on the foreground regions and improve the segmentation of regions of interest. To further boost the model's performance on retinal vessel segmentation, we employ a weighted dice loss. This choice is particularly effective in addressing the class imbalance issues frequently encountered in retinal vessel segmentation tasks. Dice loss penalises false positives and false negatives equally, encouraging the model to generate more accurate segmentation with improved object boundary delineation and reduced fragmentation. Extensive experiments on a benchmark dataset show better performance (0.8285, 0.8098, 0.9677, and 0.8166 recall, precision, accuracy and F1 score respectively) compared to state-of-the-art methods.