首页 > 论文 > 激光与光电子学进展 > 57卷 > 24期(pp:241702--1)

基于CNN和改进的图搜索分割OCT图像中的视网膜层

Segmentation of Retinal Layers in OCT Images Based on CNN and Improved Graph Search

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

摘要

提出一种结合卷积神经网络(CNN)和改进的图搜索来分割光学相干断层扫描成像(OCT)图像中的7个视网膜层边界的方法。首先利用CNN自动提取每个边界的特征并训练相应的分类器,由此将获得的每个边界的概率图作为分割的感兴趣区域;其次,提出一种改进的图搜索方法,该方法在垂直梯度的基础上添加了横向约束,当遇到血管阴影时,分割线可以横向穿过阴影。使用所提方法对正常图像进行分割,并对得到的结果和图搜索方法、基于CNN的方法得到的结果进行比较。实验结果表明,所提方法能精确分割7个视网膜层边界,平均层边界误差为(4.31±5.87) μm。

Abstract

Herein, a method that combines convolutional neural networks (CNNs) and improved graph search is proposed to segment seven retinal-layer boundaries in optical coherence tomography (OCT) images. First, CNN is used to extract the features of each boundary automatically and to train the corresponding classifier to obtain the probability map of each boundary as the region of interest for boundary segmentation. Second, an improved graph search method is proposed to add lateral constraints based on the vertical gradient. When encountering a vascular shadow, the segmentation line can laterally cross the shadow. The normal image is segmented using the proposed method, and the results are compared with those obtained using the graph search method and the method based on CNN. Experimental results show that the proposed method can accurately segment seven retinal-layer boundaries with an average layer boundary error of (4.31±5.87)μm.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:O438

DOI:10.3788/LOP57.241702

所属栏目:医用光学与生物技术

基金项目:国家自然科学基金、 广东省自然科学基金、 佛山科学技术学院高层次建设与科研项目、 佛山科学技术学院高层次人才科研启动项目、 国家级大学生创新创业训练计划、 广东大学生科技创新培育专项资金;

收稿日期:2020-06-01

修改稿日期:2020-07-03

网络出版日期:2020-12-01

作者单位    点击查看

唐艳红:佛山科学技术学院物理与光电工程学院, 广东 佛山 528200
陈允照:佛山科学技术学院物理与光电工程学院, 广东 佛山 528200
刘明迪:佛山科学技术学院物理与光电工程学院, 广东 佛山 528200
曾亚光:佛山科学技术学院物理与光电工程学院, 广东 佛山 528200
周月霞:佛山科学技术学院物理与光电工程学院, 广东 佛山 528200

联系人作者:周月霞(19714213@qq.com)

备注:国家自然科学基金、 广东省自然科学基金、 佛山科学技术学院高层次建设与科研项目、 佛山科学技术学院高层次人才科研启动项目、 国家级大学生创新创业训练计划、 广东大学生科技创新培育专项资金;

【1】Huang D, Swanson E A, Lin C P, et al. Optical coherence tomography [J]. Science. 1991, 254(5035): 1178-1181.

【2】Yazdanpanah A, Hamarneh G, Smith B, et al. Intra-retinal layer segmentation in optical coherence tomography using an active contour approach [J]. Medical Image Computing and Computer-Assisted Intervention. 2009, 12: 649-656.

【3】Luo S T, Fan Y W, Chang W, et al. Boundary region of stomach mucinous carcinoma with swept source optical coherence tomography [J]. Acta Optica Sinica. 2018, 38(5): 0517001.
罗斯特, 范应威, 常玮, 等. 扫频光学相干层析成像应用于判断黏液型胃癌边界区域 [J]. 光学学报. 2018, 38(5): 0517001.

【4】Li P, Yang S S, Ding Z H, et al. Research progress in Fourier domain optical coherence tomography [J]. Chinese Journal of Lasers. 2018, 45(2): 0207011.
李培, 杨姗姗, 丁志华, 等. 傅里叶域光学相干层析成像技术的研究进展 [J]. 中国激光. 2018, 45(2): 0207011.

【5】Fang L, Cunefare D, Wang C, et al. Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search [J]. Biomedical Optics Express. 2017, 8(5): 2732-2744.

【6】Chiu S J, Li X T, Nicholas P, et al. Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation [J]. Optics Express. 2010, 18(18): 19413-19428.

【7】Chen Q, Fan W, Niu S J, et al. Automated choroid segmentation based on gradual intensity distance in HD-OCT images [J]. Optics Express. 2015, 23(7): 8974-8994.

【8】Wang Q, Peng H L, Wang P H, et al. Dither removing of three-dimensional optical coherence tomography retinal image [J]. Acta Optica Sinica. 2019, 39(3): 0317001.
汪权, 朋汉林, 汪平河, 等. 光学相干层析成像眼底视网膜三维图像去抖动方法 [J]. 光学学报. 2019, 39(3): 0317001.

【9】Niu S J, Chen Q, Lu S T, et al. SD-OCT image layer segmentation using multi-scale 3-D graph search method [J]. Computer Science. 2015, 42(9): 272-277.
牛四杰, 陈强, 陆圣陶, 等. 应用多尺度三维图搜索的SD-OCT图像层分割方法 [J]. 计算机科学. 2015, 42(9): 272-277.

【10】Guo Y K, Camino A, Zhang M, et al. Automated segmentation of retinal layer boundaries and capillary plexuses in wide-field optical coherence tomographic angiography [J]. Biomedical Optics Express. 2018, 9(9): 4429-4442.

【11】Zawadzki R J, Fuller A R, Wiley D F, et al. Adaptation of a support vector machine algorithm for segmentation and visualization of retinal structures in volumetric optical coherence tomography data sets [J]. Journal of Biomedical Optics. 2007, 12(4): 041206.

【12】Lang A, Carass A, Hauser M, et al. Retinal layer segmentation of macular OCT images using boundary classification [J]. Biomedical Optics Express. 2013, 4(7): 1133-1152.

【13】Chen Q, Xu J, Niu S J. Retinal nerve fiber layer segmentation of spectral domain optical coherence tomography images based on random forest [J]. Journal of Electronics & Information Technology. 2017, 39(5): 1101-1108.
陈强, 徐军, 牛四杰. 基于随机森林的频谱域光学相干层析技术的图像视网膜神经纤维层分割 [J]. 电子与信息学报. 2017, 39(5): 1101-1108.

【14】Kugelman J, Alonso-Caneiro D, Read S A, et al. Automatic segmentation of OCT retinal boundaries using recurrent neural networks and graph search [J]. Biomedical Optics Express. 2018, 9(11): 5759-5777.

【15】Liu X M, Cao J, Fu T, et al. Semi-supervised automatic segmentation of layer and fluid region in retinal optical coherence tomography images using adversarial learning [J]. IEEE Access. 2019, 7: 3046-3061.

【16】Hamwood J, Alonso-Caneiro D, Read S A, et al. Effect of patch size and network architecture on a convolutional neural network approach for automatic segmentation of OCT retinal layers [J]. Biomedical Optics Express. 2018, 9(7): 3049-3066.

【17】Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM. 2017, 60(6): 84-90.

【18】Anantrasirichai N, Nicholson L, Morgan J E, et al. Adaptive-weighted bilateral filtering and other pre-processing techniques for optical coherence tomography [J]. Computerized Medical Imaging and Graphics. 2014, 38(6): 526-539.

引用该论文

Tang Yanhong,Chen Yunzhao,Liu Mingdi,Zeng Yaguang,Zhou Yuexia. Segmentation of Retinal Layers in OCT Images Based on CNN and Improved Graph Search[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241702

唐艳红,陈允照,刘明迪,曾亚光,周月霞. 基于CNN和改进的图搜索分割OCT图像中的视网膜层[J]. 激光与光电子学进展, 2020, 57(24): 241702

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