Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (14): 217-223.DOI: 10.3778/j.issn.1002-8331.2205-0166

• Graphics and Image Processing • Previous Articles     Next Articles

SAF-Net:Self Attention Fusion Network for Retinal Vessel Segmentation

LIU Na, WANG Guoqiang   

  1. College of Electronic Engineering, Heilongjiang University, Harbin 150080, China
  • Online:2023-07-15 Published:2023-07-15

SAF-Net:自注意力融合网络的视网膜血管分割

刘娜,汪国强   

  1. 黑龙江大学 电子工程学院,哈尔滨 150080

Abstract: Automatic vessel segmentation in the fundus images plays an important role in the screening, diagnosis, treatment, and evaluation of various cardiovascular and ophthalmologic diseases. However, due to the limited well-annotated data, varying size of vessels, and intricate vessel structures, retinal vessel segmentation has become a long-standing challenge. Therefore, it proposes a self-attention fusion network which combines spatial attention and channel attention in parallel to handle the retinal vessels segmentation problem. It focuses on high-frequency information extraction by combining the channel and spatial mechanism. It sums the outputs of the two attention modules to further improve feature representation which contributes to more precise segmentation results. It validates the algorithm on public datasets DRIVE,CHASE_DB1 and STARE. The results show that compared with the retinal vessel segmentation algorithm in recent years, the self attention fusion network proposed in this paper has great advantages over other algorithms.

Key words: retinal vessel segmentation, self attention, channel attention, spatial attention

摘要: 眼底图像中的自动血管分割在各种心血管和眼科疾病的筛查、诊断、治疗和评估中发挥着重要作用。然而,由于注释良好的数据有限、血管大小不一、血管结构复杂,视网膜血管分割已成为一项长期存在的挑战。因此,提出了一种自注意力融合网络,它将空间和通道注意力并行地结合起来处理视网膜血管分割问题。分别从空间维度和通道维度进行特征提取,专注于高频信息提取。该网络将两个注意模块的输出相加,以进一步改进特征表示,从而获得更精确的分割结果。在公开数据集DRIVE、CHASE_DB1和STARE上验证了该算法,实验结果表明,与近几年的视网膜血管分割算法相比,提出的视网膜血管分割算法具有优越性。

关键词: 视网膜血管分割, 自注意力, 通道注意力, 空间注意力