Attention Guided Network for Retinal Image Segmentation
This work addresses the challenge of accurate segmentation in retinal images for medical diagnosis, representing an incremental improvement over existing convolutional neural network methods.
The authors tackled the problem of preserving structural information in retinal image segmentation by proposing an Attention Guided Network (AG-Net), which uses a guided filter and attention block to improve segmentation accuracy, as demonstrated through extensive experiments on blood vessel and optic disc/cup segmentation tasks.
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.