• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于曲波变换和图论的光学相干断层扫描图像中脉络膜自动分割

Automatic Choroidal Segmentation in Optical Coherence Tomography Images Based on Curvelet Transform and Graph Theory.

作者信息

Eghtedar Reza Alizadeh, Esmaeili Mahdad, Peyman Alireza, Akhlaghi Mohammadreza, Rasta Seyed Hossein

机构信息

Medical Bioengineering Department, School of Advanced Medical Sciences, Tabriz University of Medical Sciences, Tabriz, Iran.

Department of Ophthalmology, Isfahan University of Medical Sciences, Isfahan, Iran.

出版信息

J Med Signals Sens. 2023 May 29;13(2):92-100. doi: 10.4103/jmss.jmss_144_21. eCollection 2023 Apr-Jun.

DOI:10.4103/jmss.jmss_144_21
PMID:37448544
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10336906/
Abstract

BACKGROUND

Automatic segmentation of the choroid on optical coherence tomography (OCT) images helps ophthalmologists in diagnosing eye pathologies. Compared to manual segmentations, it is faster and is not affected by human errors. The presence of the large speckle noise in the OCT images limits the automatic segmentation and interpretation of them. To solve this problem, a new curvelet transform-based K-SVD method is proposed in this study. Furthermore, the dataset was manually segmented by a retinal ophthalmologist to draw a comparison with the proposed automatic segmentation technique.

METHODS

In this study, curvelet transform-based K-SVD dictionary learning and Lucy-Richardson algorithm were used to remove the speckle noise from OCT images. The Outer/Inner Choroidal Boundaries (O/ICB) were determined utilizing graph theory. The area between ICB and outer choroidal boundary was considered as the choroidal region.

RESULTS

The proposed method was evaluated on our dataset and the average dice similarity coefficient (DSC) was calculated to be 92.14% ± 3.30% between automatic and manual segmented regions. Moreover, by applying the latest presented open-source algorithm by Mazzaferri . on our dataset, the mean DSC was calculated to be 55.75% ± 14.54%.

CONCLUSIONS

A significant similarity was observed between automatic and manual segmentations. Automatic segmentation of the choroidal layer could be also utilized in large-scale quantitative studies of the choroid.

摘要

背景

光学相干断层扫描（OCT）图像上脉络膜的自动分割有助于眼科医生诊断眼部疾病。与手动分割相比，它速度更快且不受人为误差影响。OCT图像中存在的大量斑点噪声限制了对其进行自动分割和解读。为解决此问题，本研究提出了一种基于曲波变换的K-SVD方法。此外，数据集由视网膜眼科医生进行手动分割，以便与所提出的自动分割技术进行比较。

方法

在本研究中，基于曲波变换的K-SVD字典学习和Lucy-Richardson算法被用于去除OCT图像中的斑点噪声。利用图论确定外/内脉络膜边界（O/ICB）。ICB与脉络膜外边界之间的区域被视为脉络膜区域。

结果

在所构建的数据集上对所提方法进行评估，自动分割区域与手动分割区域之间的平均骰子相似系数（DSC）计算为92.14%±3.30%。此外，通过在我们的数据集上应用Mazzaferri等人最新提出的开源算法，平均DSC计算为55.75%±14.54%。

结论

自动分割与手动分割之间观察到显著的相似性。脉络膜层的自动分割也可用于脉络膜的大规模定量研究。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/eda331c6fbe1/JMSS-13-92-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/56f7c18a28e7/JMSS-13-92-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/bc01dfc9f56e/JMSS-13-92-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/04fb1e4eeb6c/JMSS-13-92-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/6ca5da3e7ee0/JMSS-13-92-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/af345f1fc5db/JMSS-13-92-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/bb5efd0a760e/JMSS-13-92-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/5d9db3dabde1/JMSS-13-92-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/ba6fa885a530/JMSS-13-92-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/eda331c6fbe1/JMSS-13-92-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/56f7c18a28e7/JMSS-13-92-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/bc01dfc9f56e/JMSS-13-92-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/04fb1e4eeb6c/JMSS-13-92-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/6ca5da3e7ee0/JMSS-13-92-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/af345f1fc5db/JMSS-13-92-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/bb5efd0a760e/JMSS-13-92-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/5d9db3dabde1/JMSS-13-92-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/ba6fa885a530/JMSS-13-92-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7791/10336906/eda331c6fbe1/JMSS-13-92-g012.jpg

相似文献

1
Automatic Choroidal Segmentation in Optical Coherence Tomography Images Based on Curvelet Transform and Graph Theory.基于曲波变换和图论的光学相干断层扫描图像中脉络膜自动分割
J Med Signals Sens. 2023 May 29;13(2):92-100. doi: 10.4103/jmss.jmss_144_21. eCollection 2023 Apr-Jun.
2
Three-dimensional Segmentation of Retinal Cysts from Spectral-domain Optical Coherence Tomography Images by the Use of Three-dimensional Curvelet Based K-SVD.基于三维曲波的K-SVD算法对光谱域光学相干断层扫描图像中视网膜囊肿的三维分割
J Med Signals Sens. 2016 Jul-Sep;6(3):166-71.
3
Automatic segmentation of choroidal thickness in optical coherence tomography.光学相干断层扫描中脉络膜厚度的自动分割
Biomed Opt Express. 2013 Nov 11;4(12):2795-812. doi: 10.1364/BOE.4.002795. eCollection 2013.
4
An Open-Source Deep Learning Algorithm for Efficient and Fully Automatic Analysis of the Choroid in Optical Coherence Tomography.一种用于光学相干断层扫描中脉络膜高效全自动分析的开源深度学习算法。
Transl Vis Sci Technol. 2023 Nov 1;12(11):27. doi: 10.1167/tvst.12.11.27.
5
Speckle Noise Reduction in Optical Coherence Tomography Using Two-dimensional Curvelet-based Dictionary Learning.基于二维曲波字典学习的光学相干断层扫描散斑噪声抑制
J Med Signals Sens. 2017 Apr-Jun;7(2):86-91.
6
Automatic segmentation of layers in chorio-retinal complex using Graph-based method for ultra-speed 1.7 MHz wide field swept source FDML optical coherence tomography.基于图论的方法对超快速 1.7MHz 宽场扫频源 FDML 光学相干断层扫描的脉络膜视网膜复合体进行自动分层分割。
Med Biol Eng Comput. 2024 May;62(5):1375-1393. doi: 10.1007/s11517-023-03007-6. Epub 2024 Jan 9.
7
Three-dimensional curvelet-based dictionary learning for speckle noise removal of optical coherence tomography.基于三维曲波的字典学习用于光学相干断层扫描散斑噪声去除
Biomed Opt Express. 2020 Jan 3;11(2):586-608. doi: 10.1364/BOE.377021. eCollection 2020 Feb 1.
8
An Update on Choroidal Layer Segmentation Methods in Optical Coherence Tomography Images: a Review.光学相干断层扫描图像中脉络膜层分割方法的最新进展：综述
J Biomed Phys Eng. 2022 Feb 1;12(1):1-20. doi: 10.31661/jbpe.v0i0.1234. eCollection 2022 Feb.
9
Automatic choroidal segmentation in OCT images using supervised deep learning methods.基于监督深度学习方法的 OCT 图像脉络膜自动分割。
Sci Rep. 2019 Sep 16;9(1):13298. doi: 10.1038/s41598-019-49816-4.
10
An automated method for choroidal thickness measurement from Enhanced Depth Imaging Optical Coherence Tomography images.一种从增强深度成像光学相干断层扫描图像中测量脉络膜厚度的自动化方法。
Comput Med Imaging Graph. 2018 Jan;63:41-51. doi: 10.1016/j.compmedimag.2018.01.001. Epub 2018 Jan 6.

引用本文的文献

1
Design and Simulation of an Ultrahigh-resolution Spectral-domain Optical Coherence Tomography.超高分辨率光谱域光学相干断层扫描的设计与仿真
J Med Signals Sens. 2025 Apr 19;15:12. doi: 10.4103/jmss.jmss_36_24. eCollection 2025.

本文引用的文献

1
An Update on Choroidal Layer Segmentation Methods in Optical Coherence Tomography Images: a Review.光学相干断层扫描图像中脉络膜层分割方法的最新进展：综述
J Biomed Phys Eng. 2022 Feb 1;12(1):1-20. doi: 10.31661/jbpe.v0i0.1234. eCollection 2022 Feb.
2
Automatic Choroid Layer Segmentation from Optical Coherence Tomography Images Using Deep Learning.基于深度学习的光学相干断层扫描图像脉络膜自动分割。
Sci Rep. 2019 Feb 28;9(1):3058. doi: 10.1038/s41598-019-39795-x.
3
Automated segmentation of the choroid in EDI-OCT images with retinal pathology using convolution neural networks.
使用卷积神经网络对患有视网膜病变的EDI-OCT图像中的脉络膜进行自动分割。
Fetal Infant Ophthalmic Med Image Anal (2017). 2017 Sep;10554:177-184. doi: 10.1007/978-3-319-67561-9_20. Epub 2017 Sep 9.
4
Automated choroid segmentation of three-dimensional SD-OCT images by incorporating EDI-OCT images.通过结合 EDI-OCT 图像对三维 SD-OCT 图像进行自动脉络膜分割。
Comput Methods Programs Biomed. 2018 May;158:161-171. doi: 10.1016/j.cmpb.2017.11.002. Epub 2017 Nov 4.
5
An automated method for choroidal thickness measurement from Enhanced Depth Imaging Optical Coherence Tomography images.一种从增强深度成像光学相干断层扫描图像中测量脉络膜厚度的自动化方法。
Comput Med Imaging Graph. 2018 Jan;63:41-51. doi: 10.1016/j.compmedimag.2018.01.001. Epub 2018 Jan 6.
6
Speckle Noise Reduction in Optical Coherence Tomography Using Two-dimensional Curvelet-based Dictionary Learning.基于二维曲波字典学习的光学相干断层扫描散斑噪声抑制
J Med Signals Sens. 2017 Apr-Jun;7(2):86-91.
7
Automatic Choroidal Layer Segmentation Using Markov Random Field and Level Set Method.基于马尔可夫随机场和水平集方法的自动脉络膜层分割。
IEEE J Biomed Health Inform. 2017 Nov;21(6):1694-1702. doi: 10.1109/JBHI.2017.2675382. Epub 2017 Mar 20.
8
Open-source algorithm for automatic choroid segmentation of OCT volume reconstructions.用于 OCT 体积重建的自动脉络膜分割的开源算法。
Sci Rep. 2017 Feb 9;7:42112. doi: 10.1038/srep42112.
9
Automated choroid segmentation in three-dimensional 1-μm wide-view OCT images with gradient and regional costs.基于梯度和区域代价的三维 1μm 宽视野 OCT 图像中脉络膜的自动分割。
J Biomed Opt. 2016 Dec 1;21(12):126017. doi: 10.1117/1.JBO.21.12.126017.
10
Validation of Macular Choroidal Thickness Measurements from Automated SD-OCT Image Segmentation.基于自动谱域光学相干断层扫描图像分割的黄斑脉络膜厚度测量的验证
Optom Vis Sci. 2016 Nov;93(11):1387-1398. doi: 10.1097/OPX.0000000000000985.