Title
A refined equilibrium generative adversarial network for retinal vessel segmentation
Abstract
•Enhanced adversarial training promotes segmenting elusive vessels in the fundus image.•Multi-scale feature refine blocks maintain the high-resolution information.•The top-to-down feature delivery strategy supplements the detailed representation.•Self-attention mechanism highlights the informative channels for vessel segmentation.•The proposed method outperforms state-of-the-arts in segmenting and generalisability.
Year
DOI
Venue
2021
10.1016/j.neucom.2020.06.143
Neurocomputing
Keywords
DocType
Volume
Retinal vessel segmentation,Symmetric adversarial architecture,Refine blocks,Attention mechanism
Journal
437
ISSN
Citations 
PageRank 
0925-2312
1
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Yukun Zhou111.02
Zailiang Chen2439.10
Hailan Shen3304.07
Xianxian Zheng410.68
Rongchang Zhao593.81
Xuanchu Duan610.34