Abstract | ||
---|---|---|
Automatic retinal vessel segmentation in fundus image can assist effective and efficient diagnosis of retina disease. Microstructure estimation of capillaries is a prolonged challenging issue. To tackle this problem, we propose attention-aware multi-scale fusion network (AMF-Net). Our network is with dense convolutions to perceive microscopic capillaries. Additionally, multi-scale features are extracted and fused with adaptive weights by channel attention module to improve the segmentation performance. Finally, spatial attention is introduced by position attention modules to capture long-distance feature dependencies. The proposed model is evaluated using two public datasets including DRIVE and CHASE_DB1. Extensive experiments demonstrate that our model outperforms existing methods. Ablation study valid the effectiveness of the proposed components. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/EMBC46164.2021.9630756 | 2021 43RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC) |
Keywords | DocType | Volume |
Retinal vessel segmentation, U-Net, attention mechanism, multi-scale fusion | Conference | 2021 |
ISSN | Citations | PageRank |
1557-170X | 0 | 0.34 |
References | Authors | |
0 | 4 |