Attention Guided Network for Retinal Image Segmentation

TL;DR

This paper introduces AG-Net, an attention-guided neural network that enhances retinal image segmentation by preserving structural information and reducing background noise, leading to improved segmentation accuracy.

Contribution

The paper proposes a novel AG-Net architecture combining guided filtering and attention mechanisms to better retain structural details in retinal images.

Findings

Effective in blood vessel segmentation

Improves optic disc and cup segmentation accuracy

Reduces background noise influence

Abstract

Learning structural information is critical for producing an ideal result in retinal image segmentation. Recently, convolutional neural networks have shown a powerful ability to extract effective representations. However, convolutional and pooling operations filter out some useful structural information. In this paper, we propose an Attention Guided Network (AG-Net) to preserve the structural information and guide the expanding operation. In our AG-Net, the guided filter is exploited as a structure sensitive expanding path to transfer structural information from previous feature maps, and an attention block is introduced to exclude the noise and reduce the negative influence of background further. The extensive experiments on two retinal image segmentation tasks (i.e., blood vessel segmentation, optic disc and cup segmentation) demonstrate the effectiveness of our proposed method.