基于注意力U-Net的视网膜血管分类识别  

Classification and recognition of retinal vessels based on attention U-Net

作　　者：燕杨[1] 尤紫如 姚远[2] 黄文博[1] Yang YAN;Zi-ru YOU;Yuan YAO;Wen-bo HUANG(College of Computer Science and Technology,Changchun Normal University,Changchun 130032,China;Bureau of Major Tasks,Chinese Academy of Sciences,Beijing 100864,China)

机构地区：[1]长春师范大学计算机科学与技术学院,长春130032 [2]中国科学院重大任务局,北京100864

出　　处：《吉林大学学报（工学版）》2022年第12期2933-2940,共8页Journal of Jilin University:Engineering and Technology Edition

基　　金：吉林省教育厅科学研究项目(JKH20200830KJ,JJKH20210887KJ);吉林省自然科学基金联合基金项目(YDZJ202101ZYTS147).

摘　　要：针对视网膜动静脉血管(A/V)自动分类方法的局限性,提出了基于注意力U-Net(AU-Net)的视网膜A/V自动分类方法。利用血管结构信息、拓扑关系及边缘信息增强视网膜A/V特征信息,在U-Net改进网络VC-Net模型中引入注意力模块,将局部与全局信息相结合,调整权重约束视网膜A/V特征,如抑制背景倾向特征并增强血管边缘及末端特征,实现视网膜A/V的精准分类。在DRIVE数据集中对本文方法性能进行了测试,结果表明,本文方法视网膜A/V分类精度为0.9685,F1值为0.9886,敏感度为0.9803,特异性为0.9957。由实验结果可见,与经典U-Net相比,本文方法各项性能指标均有显著提升,可供临床借鉴。Aiming at the limitations of automatic classification method for retinal artery and vein vessels(A/V),an automatic retinal A/V classification method based on attention U-Net(Attention U-Net,AU-Net)was proposed.The retinal A/V feature information was enhanced by using vascular structure information,topological relationship and edge information.The attention block was introduced into the VC-Net network model,which improvemented on U-Net,combining the local and global information,adjusting weight to restrict the retinal A/V features,such as inhibiting the background tendency features and enhancing the vascular edge and end features,so as to realize the accurate classification of retinal A/V.The method was tested in the DRIVE data set.The retinal A/V classification accuracy is 0.9685,F1 value is 0.9886,sensitivity is 0.9803 and specificity is 0.9957.The experimental results show that compared with the classical U-Net,the performance indexes of the proposed method are significantly improved,which can be used for clinical reference.

关 键 词：深度学习 动静脉血管分类 注意力模块 U-Net 

分 类 号：TP391.7[自动化与计算机技术—计算机应用技术]