首页 > 论文 > 激光与光电子学进展 > 56卷 > 18期(pp:181004--1)

基于Frangi滤波器和Otsu视网膜血管分割

Retinal Vessel Segmentation Based on Frangi Filter and Otsu Algorithm

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

分析视网膜血管结构的变化是诊断和检测糖尿病、高血压等血管类相关疾病的最重要步骤。为此,提出了一种基于Frangi滤波器和大津法(Otsu)的视网膜血管分割方法。基于Frangi滤波器视网膜血管分割方法先对视网膜血管进行预处理,再基于Frangi滤波器对其边缘进行检测,并根据形态学方法分割出视网膜血管。然后,利用Otsu阈值分割预处理和增强后的视网膜血管。将上述两种方法获得的分割图像进行融合,获得最终的分割结果。实验结果表明,所提算法在DRIVE和STARE数据集上的平均灵敏性分别为58.1%、78.7%,特异性分别为93.1%、96.4%,而准确性则分别为93.8%、95.8%,其算法的执行时间仅为1.8 s。与传统的无监督分割算法相比,所提算法简单高效,能够很好地抑制噪声。

Abstract

Analysis of changes in retinal vascular structure is the key in the detection and diagnosis of vascular-related diseases, such as diabetes and hypertension. Herein, we propose retinal vessel segmentation methods based on the Frangi filter and Otsu algorithm. The Frangi filter-based method comprises the following steps. First, the preprocessing for retinal blood vessel is performed and then retinal blood vessel edges are detected using the Frangi filter; finally, retinal blood vessels are segmented using morphological approaches. The second method, based on the Otsu threshold segmentation technique, uses the retinal blood vessels after the Otsu threshold segmentation preprocessing and image enhancement. The final segmentation image is obtained by combining the outcomes of the above two methods. We apply the proposed algorithms on the two well-known DRIVE and STARE datasets. The average sensitivities obtained are 58.1% and 78.7%, the average specificities obtained are 93.1% and 96.4%, and the average accuracies obtained are 93.8% and 95.8%, respectively. The execution time of our method is 1.8 s. Results show that our algorithms are simpler and more efficient than the conventional unsupervised segmentation algorithm; in addition, they suppress noise very well.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.181004

所属栏目:图像处理

基金项目:山东省中医药科技发展计划项目、山东省重点研发项目、山东省研究生导师指导能力提升项目、山东省研究生教育优质课程建设项目;

收稿日期:2019-01-20

修改稿日期:2019-04-01

网络出版日期:2019-09-01

作者单位    点击查看

孟琳:山东中医药大学理工学院, 山东 济南 250355
刘静:山东中医药大学理工学院, 山东 济南 250355
曹慧:山东中医药大学理工学院, 山东 济南 250355
史婷瑶:山东中医药大学理工学院, 山东 济南 250355
张驰:山东中医药大学理工学院, 山东 济南 250355

联系人作者:曹慧(caohui63@163.com)

备注:山东省中医药科技发展计划项目、山东省重点研发项目、山东省研究生导师指导能力提升项目、山东省研究生教育优质课程建设项目;

【1】Zheng T Y, Tang C and Lei Z K. Multi-scale retinal vessel segmentation based on fully convolutional neural network. Acta Optica Sinica. 39(2), (2019).
郑婷月, 唐晨, 雷振坤. 基于全卷积神经网络的多尺度视网膜血管分割. 光学学报. 39(2), (2019).

【2】Shanmugam V. Wahida Banu R S D. Retinal blood vessel segmentation using an extreme learning machine approach. [C]∥2013 IEEE Point-of-Care Healthcare Technologies (PHT), January 16-18, 2013, Bangalore, India. New York: IEEE. 318-321(2013).

【3】Wang S L, Yin Y L, Cao G B et al. Hierarchical retinal blood vessel segmentation based on feature and ensemble learning. Neurocomputing. 149, 708-717(2015).

【4】Miri M S and Mahloojifar A. Retinal image analysis using curvelet transform and multistructure elements morphology by reconstruction. IEEE Transactions on Biomedical Engineering. 58(5), 1183-1192(2011).

【5】Nugroho H A, Aras R A, Lestari T et al. Retinal vessel segmentation based on Frangi filter and morphological reconstruction. [C]∥2017 International Conference on Control, Electronics, Renewable Energy and Communications (ICCREC), September 26-28, 2017, Yogyakarta, Indonesia. New York: IEEE. 181-184(2017).

【6】BahadarKhan K, Khaliq A A and Shahid M. A morphological hessian based approach for retinal blood vessels segmentation and denoising using region based Ostu thresholding. PLoS ONE. 11(7), (2016).

【7】Mendonca A M and Campilho A. Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction. IEEE Transactions on Medical Imaging. 25(9), 1200-1213(2006).

【8】Fraz M M, Barman S A, Remagnino P et al. An approach to localize the retinal blood vessels using bit planes and centerline detection. Computer Methods and Programs in Biomedicine. 108(2), 600-616(2012).

【9】Fraz M M, Basit A and Barman S A. Application of morphological bit planes in retinal blood vessel extraction. Journal of Digital Imaging. 26(2), 274-286(2013).

【10】Elson J, Precilla J, Reshma P et al. Automated extraction and analysis of retinal blood vessels with multi scale matched filter. [C]∥2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), July 6-7, 2017, Kerala State, Kannur, India. New York: IEEE. 775-779(2017).

【11】Zhu C Z, Zou B J, Zhao R C et al. Retinal vessel segmentation in colour fundus images using extreme learning machine. Computerized Medical Imaging and Graphics. 55, 68-77(2017).

【12】Dash J and Bhoi N. A method for blood vessel segmentation in retinal images using morphological reconstruction. [C]∥2016 International Conference on Computer, Electrical & Communication Engineering (ICCECE), December 16-17, 2016, Kolkata, India. New York: IEEE. 8009564, (2016).

【13】Wu C Y, Yi B S, Zhang Y G et al. Retinal vessel image segmentation based on improved convolutional neural network. Acta Optica Sinica. 38(11), (2018).
吴晨玥, 易本顺, 章云港 等. 基于改进卷积神经网络的视网膜血管图像分割. 光学学报. 38(11), (2018).

【14】Gupta N. Performance evaluation of retinal vessel segmentation using a combination of filters. [C]∥2016 2nd International Conference on Next Generation Computing Technologies (NGCT), October 14-16, 2016, Dehradun, India. New York: IEEE. 725-730(2017).

【15】Qiu Y L, Jiang X G and Xiong J. A multi-scale retinal vessels enhancement filtering method based on Hessian operator. Computer Applications and Software. 31(9), 201-205(2014).
丘赟立, 蒋先刚, 熊娟. 基于Hessian算子的多尺度视网膜血管增强滤波方法. 计算机应用与软件. 31(9), 201-205(2014).

【16】Zhang X, Zhong C, Huang T H et al. Method of image analysis of aggregate particle group based on gray morphological reconstruction. Journal of Building Materials. 21(6), 886-891, 905(2018).
张雄, 钟晨, 黄廷皓 等. 基于灰度形态学重建的骨料颗粒群图像分析方法. 建筑材料学报. 21(6), 886-891, 905(2018).

【17】Fang Y M, Wang H J, Huang K Y et al. Research on image preprocessing method for 3D reconstruction of targets in complex background. Laser & Optoelectronics Progress. 56(13), (2019).
方雅媚, 王红军, 黄矿裕 等. 复杂背景下目标三维重构的图像预处理方法研究. 激光与光电子学进展. 56(13), (2019).

【18】Yu Y, Kong L and Yu C. Image threshold segmentation algorithm based on adaptive particle swarm optimization of two-dimensional OSTU. Journal of Electronic Measurement and Instrumentation. 31(6), 827-832(2017).
于洋, 孔琳, 虞闯. 自适应粒子群集优化二维OSTU的图像阈值分割算法. 电子测量与仪器学报. 31(6), 827-832(2017).

【19】Staal J, Abramoff M D, Niemeijer M et al. Ridge-based vessel segmentation in color images of the retina. IEEE Transactions on Medical Imaging. 23(4), 501-509(2004).

【20】Hoover A D, Kouznetsova V and Goldbaum M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Transactions on Medical Imaging. 19(3), 203-210(2000).

【21】Zhu C Z, Zou B J, Xiang Y et al. A survey of retinal vessel segmentation in fundus images. Journal of Computer-Aided Design & Computer Graphics. 27(11), 2046-2057(2015).
朱承璋, 邹北骥, 向遥 等. 彩色眼底图像视网膜血管分割方法研究进展. 计算机辅助设计与图形学学报. 27(11), 2046-2057(2015).

【22】Fraz M M, Remagnino P, Hoppe A et al. Blood vessel segmentation methodologies in retinal images: a survey. Computer Methods and Programs in Biomedicine. 108(1), 407-433(2012).

引用该论文

Lin Meng,Jing Liu,Hui Cao,Tingyao Shi,Chi Zhang. Retinal Vessel Segmentation Based on Frangi Filter and Otsu Algorithm[J]. Laser & Optoelectronics Progress, 2019, 56(18): 181004

孟琳,刘静,曹慧,史婷瑶,张驰. 基于Frangi滤波器和Otsu视网膜血管分割[J]. 激光与光电子学进展, 2019, 56(18): 181004

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF