首页 | 本学科首页   官方微博 | 高级检索  
     

基于条件深度卷积生成对抗网络的视网膜血管分割
引用本文:蒋芸,谭宁.基于条件深度卷积生成对抗网络的视网膜血管分割[J].自动化学报,2021,47(1):136-147.
作者姓名:蒋芸  谭宁
作者单位:1.西北师范大学计算机科学与工程学院 兰州 730000
基金项目:国家自然科学基金(61962054,61163036);2016年甘肃省科技计划资助自然科学基金项目(1606RJZA047);2012年度甘肃省高校基本科研业务费专项资金项目;甘肃省高校研究生导师项目(1201-16);西北师范大学第三期知识与创新工程科研骨干项目(nwnu-kjcxgc-03-67)资助。
摘    要:视网膜血管的分割帮助医生对眼底疾病进行诊断有着重要的意义.但现有方法对视网膜血管的分割存在着各种问题, 例如对血管分割不足, 抗噪声干扰能力弱, 对病灶敏感等.针对现有血管分割方法的缺陷, 本文提出使用条件深度卷积生成对抗网络的方法对视网膜血管进行分割.我们主要对生成器的网络结构进行了改进,在卷积层引入残差模块进行差值学习使得网络结构对输出的改变变得敏感, 从而更好地对生成器的权重进行调整.为了降低参数数目和计算, 在使用大卷积核之前使用小卷积核对输入特征图的通道数进行减半处理.通过使用U型网络的思想将卷积层的输出与反卷积层的输出进行连接从而避免低级信息共享.通过在DRIVE和STARE数据集上对本文的方法进行了验证, 其分割准确率分别为96.08 %、97.71 %, 灵敏性分别达到了82.74 %、85.34 %, $F$度量分别达到了82.08 %和85.02 %, 灵敏度比R2U-Net的灵敏度分别高了4.82 %, 2.4 %.

关 键 词:生成对抗网络    残差网络    视网膜血管分割    条件模型    卷积神经网络
收稿时间:2018-05-07

Retinal Vessel Segmentation Based on Conditional Deep Convolutional Generative Adversarial Networks
JIANG Yun,TAN Ning.Retinal Vessel Segmentation Based on Conditional Deep Convolutional Generative Adversarial Networks[J].Acta Automatica Sinica,2021,47(1):136-147.
Authors:JIANG Yun  TAN Ning
Affiliation:1.College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730000
Abstract:The segmentation of retinal vessels is of significance for doctors to diagnose the fundus diseases.However,existing methods have various problems in the segmentation of the retinal vessels,such as insufficient segmentation of retinal vessels,weak anti-noise interference ability,and sensitivity to lesions,etc.Aiming to the shortcomings of existed methods,this paper proposes the use of conditional deep convolutional generative adversarial networks to segment the retinal vessels.We mainly improve the network structure of the generator.The introduction of the residual module at the convolutional layer for residual learning makes the network structure sensitive to changes in the output,as to better adjust the weight of the generator.In order to reduce the number of parameters and calculations,using a small convolution kernel to halve the number of channels in the input signature before using a large convolution kernel.By used the idea of a U-net to connect the output of the convolutional layer with the output of the deconvolution layer to avoid low-level information sharing.By verifying the method on the DRIVE and STARE datasets,the segmentation accuracy rate is96.08%and 97.71%,the sensitivity reaches 82.74%and 85.34%,respectively,and the F-measure reaches 82.08%and85.02%,respectively.The sensitivity is 4.82%and 2.4%higher than that of R2 U-Net.
Keywords:Generative adversarial network(GAN)  residual networks  retinal vessel segmentation  conditional models  convolutional neural networks(CNNs)
本文献已被 维普 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号