SAT-Net: a side attention network for retinal image segmentation

Retinal vessel segmentation plays an important role in the automatic assessment of eye health. Deep learning technology has been extensively employed in medical image segmentation. Specifically, U-net based methods achieve great success in medical image segmentation. However, due to its continuous p...

Full description

Saved in:
Bibliographic Details
Published in:Applied intelligence (Dordrecht, Netherlands) Netherlands), 2021-07, Vol.51 (7), p.5146-5156
Main Authors: Tong, Huilin, Fang, Zhijun, Wei, Ziran, Cai, Qingping, Gao, Yongbin
Format: Article
Language:English
Subjects:
Artificial Intelligence
Blood vessels
Classification
Coders
Computer Science
Convolution
Datasets
Deep learning
Diabetic retinopathy
Disease
Feature maps
Image segmentation
Machines
Manufacturing
Mechanical Engineering
Medical imaging
Neural networks
Noise reduction
Processes
Retinal images
Semantics
Spatial data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Retinal vessel segmentation plays an important role in the automatic assessment of eye health. Deep learning technology has been extensively employed in medical image segmentation. Specifically, U-net based methods achieve great success in medical image segmentation. However, due to its continuous pooling layer and convolution operation, the spatial information and texture information of the image are destroyed. To address this issue, we propose a SAT-Net that integrates side attention and dense atrous convolution block, which also consists of multi-scale input so that the network can retain more features of the image of the encoder stage. The dense atrous convolution block enables multiple receptive field fusion, which preserves the context information of the image, and the side attention mechanism further enhances the high-level information of the encoded features and reduces the noise in the feature map. We apply this method to different retinal image segmentation datasets and compare with the other methods. The experimental results demonstrate the effectiveness of the proposed method.
ISSN:0924-669X
1573-7497
DOI:10.1007/s10489-020-01966-z