[1]喻鲁立,陈 黎.基于 U-Net 的多尺度视网膜血管分割方法[J].计算机技术与发展,2022,32(04):140-145.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 024]
　YU Lu-li,CHEN Li.Multi-scale Segmentation of Retinal Vessels Based on U-Net[J].,2022,32(04):140-145.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 024]
点击复制

基于 U-Net 的多尺度视网膜血管分割方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年04期
页码:
140-145
栏目:
应用前沿与综合
出版日期:
2022-04-10

文章信息/Info

Title:
Multi-scale Segmentation of Retinal Vessels Based on U-Net
文章编号:
1673-629X(2022)04-0140-06
作者:
喻鲁立1 ; 陈 黎1; 2
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
Author(s):
YU Lu-li1 ; CHEN Li1; 2
1. School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China;
2. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System,Wuhan 430065,China
关键词:
视网膜血管; U-Net; 卷积神经网络; 图像分割; 密集连接; 多尺度策略
Keywords:
retinal vessels; U-Net; convolutional neural network; image segmentation; dense connection; multiscale strategy
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 04. 024
摘要:
视网膜血管的形态和结构一直是高血压、冠心病、糖尿病等疾病的重要诊断指标之一,其检测和分割具有十分重要的意义。 为了解决视网膜血管分割中,血管末梢缺失和细小血管断裂的问题, 提出了一种基于 U-Net 改进模型的多尺度分割方法, 通过在编码阶段和解码阶段之间采用增加卷积块的方式来保持对不同尺度下的特征提取,同时对增加的卷积块采用密集连接的方式解决由于网络加深带来的浅层特征缺失和梯度消失问题,从而增强模型的特征提取能力并提高分割性能。 此外,采用 Dice 损失函数解决数据集中正负样本不均衡的问题。 实验采用 CHASE_DB1 和 DRIVE 两个数据集进行训练和测试,通过与 U-net、Residual U-net、Ladder-Net 以及 R2U-Net 的对比表明,由于保留了多尺度的细节信息,该方法取得了更好的分割效果。 实验证明,该方法能够有效提取健康视网膜图像和病变视网膜图像中的血管网络,能够较好地分割细小血管。
Abstract:
The morphology and structure of retinal vessels have always been one of the important diagnostic indicators of hypertension,coronary heart disease,diabetes and other diseases,and their detection and segmentation are of great significance. In order to solve the problems of loss of vascular endings and rupture of small vessels in the segmentation of retinal vessels,a multi-scale segmentation method? based on the improved U-Net model is proposed,which maintains feature extraction at different scales by adding convolutional blocks between the encoding stage and the decoding stage. At the same time,the added convolution blocks are densely connected to solve the problems of shallow layer feature loss? and gradient disappearance caused by the deepening of the network,so as to enhance the feature extraction ability of the model and improve? ?the segmentation performance. In addition,Dice loss function is used to solve the problem of unbalanced positive and negative samples in the data set. Two data sets,CHASE_DB1 and Drive,were used for training and testing in the experiment. The comparison with U- Net,Residual U - Net,Ladder - Net and R2U - Net shows that the proposed method has achieved better segmentation effect due to the retention of multi-scale details. Experimental results show that the proposed method can effectively extract the vascular network from healthy and pathological retinal images,and can better segment small vessels.

相似文献/References:

[1]刘　鑫,赵慧杰,武苏雯.基于Ｕ－Ｎｅｔ的岩层图像裂缝检测算法应用[J].计算机技术与发展,2021,31(05):73.[doi:10. 3969 / j. issn. 1673-629X. 2021. 05. 013]
　,,et al.ＡｐｐｌｉｃａｔｉｏｎｏｆＵ－ＮｅｔＢａｓｅｄＲｏｃｋＦｏｒｍａｔｉｏｎＩｍａｇｅＣｒａｃｋＤｅｔｅｃｔｉｏｎＡｌｇｏｒｉｔｈｍ[J].,2021,31(04):73.[doi:10. 3969 / j. issn. 1673-629X. 2021. 05. 013]
[2]李博文,唐贵进,崔子冠.基于Ｒｅｔｉｎｅｘ模型的弱光照图像增强算法[J].计算机技术与发展,2021,31(05):79.[doi:10. 3969 / j. issn. 1673-629X. 2021. 05. 014]
　,ＡＷｅａｋｌｙＩｌｌｕｍｉｎａｔｅｄＩｍａｇｅＥｎｈａｎｃｅｍｅｎｔＡｌｇｏｒｉｔｈｍ ＢａｓｅｄｏｎＲｅｔｉｎｅｘＭｏｄｅｌ[J].,2021,31(04):79.[doi:10. 3969 / j. issn. 1673-629X. 2021. 05. 014]
[3]史健婷,崔闫靖,常 亮.基于优化 U-Net 网络的乳腺肿瘤区域分割方法[J].计算机技术与发展,2021,31(08):156.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 027]
　SHI Jian-ting,CUI Yan-jing,CHANG Liang.A Segmentation Method of Breast Tumor Region Based onOptimized U-Net[J].,2021,31(04):156.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 027]
[4]龚 安,赵 莉,姚鑫杰.基于改进的 U-Net 网络模型的气胸分割算法[J].计算机技术与发展,2021,31(10):173.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 029]
　GONG An,ZHAO Li,YAO Xin-jie.Pneumothorax Segmentation Algorithm Based on Improved U-Net Network Model[J].,2021,31(04):173.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 029]
[5]黄 莉,何美玲*.基于 U-Net 改进模型的多模态脑肿瘤分割方法[J].计算机技术与发展,2022,32(11):58.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 009]
　HUANG Li,HE Mei-ling*.Multi-model Brain Tumor Segmentation Method Based on Improved U-Net Model[J].,2022,32(04):58.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 009]
[6]季倓正,邵允学,吕摇 刚.基于深度学习的钢坯入炉前定位技术[J].计算机技术与发展,2022,32(S2):36.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 006]
　JI Tan-zheng,SHAO Yun-xue,LYU Gang.Positioning Technology of Billet before Furnace Based on Deep Learning[J].,2022,32(04):36.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 006]
[7]罗 杨,万黎明,李 理,等.基于改进 U-Net 网络的半监督裂缝分割方法[J].计算机技术与发展,2022,32(12):179.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 027]
　LUO Yang,WAN Li-ming,LI Li,et al.A Semi-supervised Crack Segmentation Method Based on Improved U-Net Network[J].,2022,32(04):179.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 027]
[8]李秀华,朱水成.一种基于改进 U-Net 的肝脏肿瘤分割方[J].计算机技术与发展,2023,33(02):71.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 011]
　LI Xiu-hua,ZHU Shui-cheng.A Liver Tumor Segmentation Method Based on Improved U-Net[J].,2023,33(04):71.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 011]
[9]王宇昕,付晓薇,赵思宇,等.基于多层融合注意力的乳腺肿瘤图像分割方法[J].计算机技术与发展,2023,33(07):139.[doi:10. 3969 / j. issn. 1673-629X. 2023. 07. 021]
　WANG Yu-xin,FU Xiao-wei,ZHAO Si-yu,et al.Breast Tumor Images Segmentation Method Based on Multi-layer Fusion Attention[J].,2023,33(04):139.[doi:10. 3969 / j. issn. 1673-629X. 2023. 07. 021]
[10]谢宏彪,刘志勤,王庆凤,等.基于半监督的 3D 肝脏 CT 自动分割方法研究[J].计算机技术与发展,2023,33(09):149.[doi:10. 3969 / j. issn. 1673-629X. 2023. 09. 022]
　XIE Hong-biao,LIU Zhi-qin,WANG Qing-feng,et al.Automated Segmentation of 3D Liver CT Images Using Semi-supervision[J].,2023,33(04):149.[doi:10. 3969 / j. issn. 1673-629X. 2023. 09. 022]

更新日期/Last Update: 2022-04-10