基于N-Unet视网膜血管分割  

RETINAL VESSEL SEGMENTATION BASED ON N-UNET

作　　者：田红 陈姚节[1,2,3] Tian Hong;Chen Yaojie(College of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,Hubei,China;Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System,Wuhan 430065,Hubei,China;Metallurgical Industry Process National Virtual Simulation Experimental Teaching Center,Wuhan 430065,Hubei,China)

机构地区：[1]武汉科技大学计算机科学与技术学院,湖北武汉430065 [2]智能信息处理与实时工业系统湖北省重点实验室,湖北武汉430065 [3]冶金工业过程国家级虚拟仿真实验教学中心,湖北武汉430065

出　　处：《计算机应用与软件》2024年第4期219-223,共5页Computer Applications and Software

摘　　要：针对在现阶段视网膜血管分割过程中存在的分支断裂问题,提出一种非局部Unet的模型Non-local Unet(N-Unet)。N-Unet模型保留了编码器-解码器的对称结构,在编码器阶段引入非局部块,使模型在提取特征的过程中关注非局部信息,能更好地捕捉图像中非相邻像素之间的关系。该模型在公开的DRIVE数据集上进行评估,得到的准确性、敏感性、特异性、曲线下面积分别为0.9523、0.8021、0.9743、0.8949。实验结果表明,该方法在解决血管分割过程中的分支断裂问题表现良好,具有研究意义。In order to address the problem of vascular branch breakage existing in the process of retinal vessel segmentation at present,a non-local Unet model(N-Unet)is proposed.The model retained the encoder-decoder symmetric structure,and introduced non-local blocks at the encoder stage,which made the model pay attention to non-local information in the process of feature extraction and better capture the relationship between non-adjacent pixels in the image.This model was evaluated on the public dataset DRIVE,and gained 0.9523 accuracy,0.8021 sensitivity,0.9743 specificity,and 0.8949 AUC,respectively.Experimental results show that this method performs well in solving the problem of branch breakage in the process of blood vessel segmentation,and has research significance.

关 键 词：Unet网络 NON-LOCAL 血管分割 医学图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]