多尺度卷积核U-Net模型的视网膜血管分割方法

doi:10.12068/j.issn.1005-3026.2021.01.002

东北大学学报（自然科学版） ›› 2021, Vol. 42 ›› Issue (1): 7-14.DOI: 10.12068/j.issn.1005-3026.2021.01.002

多尺度卷积核U-Net模型的视网膜血管分割方法

杨丹^1,2,3，刘国如^1,2，任梦成¹，裴宏杨^1,2

(1.东北大学信息科学与工程学院，辽宁沈阳110819； 2.东北大学辽宁省红外光电材料及微纳器件重点实验室，辽宁沈阳110819； 3.东北大学智能工业数据解析与优化教育部重点实验室，辽宁沈阳110819)

出版日期:2021-01-15 发布日期:2021-01-13
通讯作者: 杨丹
作者简介:杨丹(1979-)，女，辽宁营口人，东北大学副教授.
基金资助:
国家自然科学基金资助项目(51607029，61836011).

Retinal Blood Vessel Segmentation Method Based on Multi-scale Convolution Kernel U-Net Model

YANG Dan^1,2,3， LIU Guo-ru^1,2， REN Meng-cheng¹， PEI Hong-yang^1,2

1. School of Information Science & Engineering， Northeastern University， Shenyang 110819， China; 2. Key Laboratory of Infrared Optoelectric Materials and Micro-nano Devices， Liaoning Province， Northeastern University， Shenyang 110819， China; 3. Key Laboratory of Data Analytics and Optimization for Smart Industry， Ministry of Education， Northeastern University， Shenyang 110819， China.

Online:2021-01-15 Published:2021-01-13
Contact: YANG Dan
About author:-
Supported by:
-

摘要/Abstract

摘要： 针对病变视网膜血管结构的计算机辅助诊断问题，提出了一种多尺度卷积核U-Net模型的视网膜血管分割方法.在U-Net模型基础上设计了融合Inception模块和最大索引值上采样方法的多尺度卷积神经网络结构.在网络训练阶段，采取旋转、镜像等操作进行数据集扩充，运用CLAHE算法进行图像预处理；训练后得到的双通道特征图，进行Softmax归一化；最后通过改进的代价损失函数对归一化结果迭代优化，得到完整的视网膜血管分割模型.实验结果表明，所提方法在DRIVE数据集上分割的准确率达到0.9694，灵敏性达到0.7762，特异性达到0.9835，比U-Net模型具有更优的分割效果和泛化能力，与其他现存方法相比具有一定的竞争力.

关键词: 视网膜血管；多尺度卷积核；U-Net模型；Inception模块；CLAHE算法

Abstract: Aiming at the computer-aided diagnosis of diseased retinal vascular structure， a retinal blood vessel segmentation method of multi-scale convolution kernel U-Net model was proposed. Based on the U-Net model， a multi-scale convolutional neural network structure combining with the Inception module and the maximum index value upsampling method was designed. In the network training stage， operations such as rotation and mirroring were used to expand the data sets， and the CLAHE algorithm was used for image preprocessing. The dual-channel feature map obtained after training was normalized by Softmax. Finally， the normalized result was iteratively optimized by the improved cost loss function， then a complete retinal vessel segmentation model was obtained. Experimental results showed that the proposed method on the DRIVE data set achieved an accuracy of 0.9694， a sensitivity of 0.7762， and a specificity of 0.9835. The proposed method has better segmentation effect and generalization ability than the U-Net model， and shows its competitive results compared with other existing methods.

Key words: retinal blood vessel; multi-scale convolution kernel; U-Net model; Inception module; CLAHE algorithm

中图分类号:

TP391.41

杨丹，刘国如，任梦成，裴宏杨. 多尺度卷积核U-Net模型的视网膜血管分割方法[J]. 东北大学学报（自然科学版）, 2021, 42(1): 7-14.

YANG Dan， LIU Guo-ru， REN Meng-cheng， PEI Hong-yang. Retinal Blood Vessel Segmentation Method Based on Multi-scale Convolution Kernel U-Net Model[J]. Journal of Northeastern University(Natural Science), 2021, 42(1): 7-14.

参考文献

[1]Fraz M M，Remagnino P，Hoppe A，et al.Blood vessel segmentation methodologies in retinal images—a survey［J］.Computer Methods and Programs in Biomedicine，2012，108(1): 407-433.
[2]Liu I，Sun Y.Recursive tracking of vascular networks in angiograms based on the detection-deletion scheme［J］.IEEE Transactions on Medical Imaging，1993，12(2): 334-341.
[3]Espona L，Carreira M J，Penedo M G，et al.Retinal vessel tree segmentation using a deformable contour model［C］//2008 19th International Conference on Pattern Recognition.Tampa:IEEE，2008:1-4.
[4]Lam B Y，Yan H.A novel vessel segmentation algorithm for pathological retina images based on the divergence of vector fields［J］.IEEE Transactions on Medical Imaging，2008，27(2): 237-246.
[5]Fraz M M，Barman S A，Remagnino P，et al.An approach to localize the retinal blood vessels using bit planes and centerline detection［J］.Computer Methods and Programs in Biomedicine，2012，108(2):600-616.
[6]Espona L，Carreira M J，Ortega M，et al.A snake for retinal vessel segmentation［C］//Pattern Recognition and Image Analysis.Girona: Springer，2007:178-185.
[7]Marin D，Gegundez-Arias M E，Ponte B，et al.An exudate detection method for diagnosis risk of diabetic macular edema in retinal images using feature-based and supervised classification［J］.Medical & Biological Engineering & Computing，2018，56(8):1379-1390.
[8]Staal J，Abramoff M D，Niemeijer M，et al.Ridge-based vessel segmentation in color images of the retina［J］.IEEE Transactions on Medical Imaging， 2004，23(4):501-509.
[9]Ricci E，Perfetti R.Retinal blood vessel segmentation using line operators and support vector classification［J］.IEEE Transactions on Medical Imaging，2007，26(10):1357-1365.
[10]Wilfred F S，Edward R S.Computerized screening of diabetic retinopathy employing blood vessel segmentation in retinal images［J］.Biocybernetics and Biomedical Engineering，2014，34(2):117-124.
[11]王生生，王萌，王光耀.基于深度神经网络剪枝的两阶段遥感图像目标检测［J］.东北大学学报(自然科学版)，2019，40(2):174-179.(Wang Sheng-sheng，Wang Meng，Wang Guang-yao.Two-stage remote sensing image target detection based on deep neural network pruning［J］.Journal of Northeastern University(Natural Science)，2019，40(2):174-179.)
[12]Dang L M，Min K，Lee S，et al.Tampered and computer-generated face images identification based on deep learning［J］.Applied Sciences， 2020，10(2):505-521.
[13]Ronneberger O，Fischer P，Brox T.U-Net: convolutional networks for biomedical image segmentation［C］//International Conference on Medical Image Computing and Computer-Assisted Intervention.Munich: Springer，2015:234-241.
[14]Zhuang J.LadderNet:multi-path networks based on U-Net for medical image segmentation［EB/OL］.(2019-08-28)［2019-10-10］.https://arxiv.org/abs/1810.07810.
[15]Wang C，Zhao Z Y，Ren Q Q，et al.Dense U-Net based on patch-based learning for retinal vessel segmentation［J］.Entropy， 2019，21(2):168-182.
[16]Jin Q，Meng Z，Pham T D，et al.DUNet:a deformable network for retinal vessel segmentation［J］.Knowledge-Based Systems，2019，178:149-162.
[17]Szegedy C，Liu W，Jia Y Q，et al.Going deeper with convolutions［C］//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Boston:IEEE，2015:1-9.
[18]Chollet F.Xception:deep learning with depthwise separable convolutions［C］//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Hunolulu:IEEE，2017:1251-1258.
[19]Badrinarayanan V，Kendall A，Cipolla R.SegNet: a deep convolutional encoder-decoder architecture for image segmentation［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39(12):2481-2495.
[20]Gang L，Chutatape O，Krishnan S M.Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter［J］.IEEE Transactions on Biomedical Engineering，2002，49(2):168-172.
[21]Fu H Z，Xu Y W，Lin S，et al.Deep vessel: retinal vessel segmentation via deep learning and conditional random field［C］//International Conference on Medical Image Computing and Computer-Assisted Intervention — MICCAI 2016.Athens: Springer，2016:132-139.
[22]Maninis K K，Pont-Tuset J，Arbeláez P，et al.Deep retinal image understanding［C］//International Conforence on Medical Image Computing and Computer-Assisted Intervention — MICCAI 2016.Athens:Springer，2016:140-148.
[23]Mo J，Zhang L.Multi-level deep supervised networks for retinal vessel segmentation［J］.International Journal of Computer Assisted Radiology and Surgery，2017，12(12):2181-2193.
[24]Xiao X，Lian S，Luo Z，et al.Weighted Res-UNet for high-quality retina vessel segmentation［C］//2018 9th International Conference on Information Technology in Medicine and Education(ITME).Hangzhou:IEEE，2018:327-331.
[25]Alom M Z，Hasan M，Yakopcic C，et al.Recurrent residual convolutional neural network based on U-Net(R2U-Net) for medical image segmentation［EB/OL］.(2018-05-29)［2019-11-18］.https://arxiv.org/abs/1802.06955.

多尺度卷积核U-Net模型的视网膜血管分割方法

Retinal Blood Vessel Segmentation Method Based on Multi-scale Convolution Kernel U-Net Model

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	原培新，陈鼎夫. 双能X射线高动态范围安检图像压缩算法[J]. 东北大学学报（自然科学版）, 2021, 42(1): 96-101.
[2]	冯宝，李昌林，李智，刘壮盛. 基于活动轮廓模型和影像组学的乳腺癌LVI状态预测[J]. 东北大学学报:自然科学版, 2020, 41(2): 193-199.
[3]	张云洲，郑瑞，暴吉宁，朱尚栋. 基于多个相关滤波器的行人跟踪尺度算法[J]. 东北大学学报:自然科学版, 2019, 40(9): 1228-1234.
[4]	陈红，于晓升，吴成东，孙鹏. 参数化水平集活动轮廓模型的快速图像分割算法[J]. 东北大学学报:自然科学版, 2019, 40(1): 6-10.
[5]	徐礼胜，张书琪，牛潇，徐阳. 基于全卷积网络的左心室射血分数自动检测[J]. 东北大学学报:自然科学版, 2018, 39(11): 1572-1576.
[6]	齐林，吕旭阳，杨本强，徐礼胜. 基于全卷积网络迁移学习的左心室内膜分割[J]. 东北大学学报:自然科学版, 2018, 39(11): 1577-1582.
[7]	魏国辉，齐守良，钱唯，张魁星. 基于相似性度量的肺结节图像检索算法[J]. 东北大学学报:自然科学版, 2018, 39(9): 1226-1231.
[8]	宫照煊，覃文军，郭薇，赵大哲. 改进的局部扩展拟合图像分割方法[J]. 东北大学学报:自然科学版, 2018, 39(4): 483-487.
[9]	王彬，赵海，朱宏博，朴春赫. 基于CT图像3D特征的肺结节检测[J]. 东北大学学报:自然科学版, 2018, 39(2): 181-185.
[10]	刘晓志，齐迪迪，贲驰. 基于畸变分离的摄像机标定方法[J]. 东北大学学报:自然科学版, 2017, 38(5): 620-624.
[11]	王琪，张铁，张晓梦，张祥德. 基于SIFT和SDM的虹膜定位方法[J]. 东北大学学报:自然科学版, 2017, 38(2): 180-184.
[12]	张祥德，朱和贵，李倩颖，唐青松. 基于MBC和POEM特征的人脸识别方法[J]. 东北大学学报:自然科学版, 2015, 36(11): 1526-1529.
[13]	彭怡书，颜云辉，赵久梁，张尧. 基于非局部稀疏特征的行人检测方法[J]. 东北大学学报:自然科学版, 2015, 36(4): 465-468.
[14]	杜小甫，王成恩. 基于等值线数据的一种新的云图算法[J]. 东北大学学报(自然科学版), 2013, 34(5): 624-627.
[15]	孟琭，沈凝，祁殷俏，张昊园. 基于强化学习的三维游戏控制算法[J]. 东北大学学报（自然科学版）, 2021, 42(4): 478-483.