• 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 Canny 边缘检测的视网膜眼底图像交互式血管分割。

Interactive Blood Vessel Segmentation from Retinal Fundus Image Based on Canny Edge Detector.

机构信息

School of Electrical & Electronic Engineering, Engineering Campus, Universiti Sains Malaysia, Nibong Tebal 14300, Pulau Pinang, Malaysia.

Department of Ophthalmology, School of Medical Sciences, Health Campus, Universiti Sains Malaysia, Kubang Kerian 16150, Kelantan, Malaysia.

出版信息

Sensors (Basel). 2021 Sep 24;21(19):6380. doi: 10.3390/s21196380.

DOI:10.3390/s21196380
PMID:34640698
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8512020/
Abstract

Optometrists, ophthalmologists, orthoptists, and other trained medical professionals use fundus photography to monitor the progression of certain eye conditions or diseases. Segmentation of the vessel tree is an essential process of retinal analysis. In this paper, an interactive blood vessel segmentation from retinal fundus image based on Canny edge detection is proposed. Semi-automated segmentation of specific vessels can be done by simply moving the cursor across a particular vessel. The pre-processing stage includes the green color channel extraction, applying Contrast Limited Adaptive Histogram Equalization (CLAHE), and retinal outline removal. After that, the edge detection techniques, which are based on the Canny algorithm, will be applied. The vessels will be selected interactively on the developed graphical user interface (GUI). The program will draw out the vessel edges. After that, those vessel edges will be segmented to bring focus on its details or detect the abnormal vessel. This proposed approach is useful because different edge detection parameter settings can be applied to the same image to highlight particular vessels for analysis or presentation.

摘要

验光师、眼科医生、斜视矫正师和其他经过专业培训的医疗专业人员使用眼底摄影来监测某些眼部疾病或病症的进展。血管树的分割是视网膜分析的一个基本过程。本文提出了一种基于 Canny 边缘检测的交互式眼底图像血管分割方法。通过简单地在特定血管上移动光标，可以对特定血管进行半自动分割。预处理阶段包括提取绿色通道、应用对比度受限自适应直方图均衡化 (CLAHE) 和去除视网膜轮廓。之后，将应用基于 Canny 算法的边缘检测技术。在开发的图形用户界面 (GUI) 上进行交互式血管选择。程序将绘制出血管边缘。之后，将对这些血管边缘进行分割，以突出其细节或检测异常血管。这种方法很有用，因为可以将不同的边缘检测参数设置应用于同一图像，以突出显示用于分析或演示的特定血管。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/57984cce6838/sensors-21-06380-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/16329faf6115/sensors-21-06380-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/00c467e2ad22/sensors-21-06380-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/45979563fc17/sensors-21-06380-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/49ff77b49dd8/sensors-21-06380-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/f877109dad1e/sensors-21-06380-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/96d4d988329b/sensors-21-06380-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/4e711ffbadfa/sensors-21-06380-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/eb9ac11b1efb/sensors-21-06380-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/9f0163d12204/sensors-21-06380-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/52d9915e50a7/sensors-21-06380-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/2c807d900efc/sensors-21-06380-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/cdf5617b7832/sensors-21-06380-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/8dbcbdad0763/sensors-21-06380-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/5989952b18bc/sensors-21-06380-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/d56f313a3d27/sensors-21-06380-g015a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/b16e51d80a27/sensors-21-06380-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/fa28223875c9/sensors-21-06380-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/4558eb5786ff/sensors-21-06380-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/4e05a9f2240a/sensors-21-06380-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/57984cce6838/sensors-21-06380-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/16329faf6115/sensors-21-06380-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/00c467e2ad22/sensors-21-06380-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/45979563fc17/sensors-21-06380-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/49ff77b49dd8/sensors-21-06380-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/f877109dad1e/sensors-21-06380-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/96d4d988329b/sensors-21-06380-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/4e711ffbadfa/sensors-21-06380-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/eb9ac11b1efb/sensors-21-06380-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/9f0163d12204/sensors-21-06380-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/52d9915e50a7/sensors-21-06380-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/2c807d900efc/sensors-21-06380-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/cdf5617b7832/sensors-21-06380-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/8dbcbdad0763/sensors-21-06380-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/5989952b18bc/sensors-21-06380-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/d56f313a3d27/sensors-21-06380-g015a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/b16e51d80a27/sensors-21-06380-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/fa28223875c9/sensors-21-06380-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/4558eb5786ff/sensors-21-06380-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/4e05a9f2240a/sensors-21-06380-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98b1/8512020/57984cce6838/sensors-21-06380-g020.jpg

相似文献

1
Interactive Blood Vessel Segmentation from Retinal Fundus Image Based on Canny Edge Detector.基于 Canny 边缘检测的视网膜眼底图像交互式血管分割。
Sensors (Basel). 2021 Sep 24;21(19):6380. doi: 10.3390/s21196380.
2
Segmentation of retinal blood vessels by a novel hybrid technique- Principal Component Analysis (PCA) and Contrast Limited Adaptive Histogram Equalization (CLAHE).基于主成分分析（PCA）和对比度受限自适应直方图均衡化（CLAHE）的新型混合技术对视网膜血管的分割。
Microvasc Res. 2023 Jul;148:104477. doi: 10.1016/j.mvr.2023.104477. Epub 2023 Feb 4.
3
An Unsupervised Approach for Extraction of Blood Vessels from Fundus Images.一种从眼底图像中自动提取血管的方法。
J Digit Imaging. 2018 Dec;31(6):857-868. doi: 10.1007/s10278-018-0059-x.
4
Supervised retinal vessel segmentation from color fundus images based on matched filtering and AdaBoost classifier.基于匹配滤波和AdaBoost分类器的彩色眼底图像视网膜血管监督分割
PLoS One. 2017 Dec 11;12(12):e0188939. doi: 10.1371/journal.pone.0188939. eCollection 2017.
5
Iterative Vessel Segmentation of Fundus Images.眼底图像的迭代血管分割
IEEE Trans Biomed Eng. 2015 Jul;62(7):1738-49. doi: 10.1109/TBME.2015.2403295. Epub 2015 Feb 13.
6
Blood vessel segmentation in color fundus images based on regional and Hessian features.基于区域和黑塞特征的彩色眼底图像血管分割
Graefes Arch Clin Exp Ophthalmol. 2017 Aug;255(8):1525-1533. doi: 10.1007/s00417-017-3677-y. Epub 2017 May 4.
7
Segmenting retinal vessels with revised top-bottom-hat transformation and flattening of minimum circumscribed ellipse.基于改进的顶底帽变换和平滑最小外接椭圆的视网膜血管分割。
Med Biol Eng Comput. 2019 Jul;57(7):1481-1496. doi: 10.1007/s11517-019-01967-2. Epub 2019 Mar 22.
8
A new robust method for blood vessel segmentation in retinal fundus images based on weighted line detector and hidden Markov model.基于加权线检测器和隐马尔可夫模型的视网膜眼底图像血管分割新方法。
Comput Methods Programs Biomed. 2020 Apr;187:105231. doi: 10.1016/j.cmpb.2019.105231. Epub 2019 Nov 23.
9
Blood Vessel Segmentation of Fundus Retinal Images Based on Improved Frangi and Mathematical Morphology.基于改进的 Frangi 和数学形态学的眼底视网膜图像血管分割。
Comput Math Methods Med. 2021 May 26;2021:4761517. doi: 10.1155/2021/4761517. eCollection 2021.
10
Blood Vessel Segmentation of Fundus Images by Major Vessel Extraction and Subimage Classification.基于主血管提取和子图像分类的眼底图像血管分割。
IEEE J Biomed Health Inform. 2015 May;19(3):1118-28. doi: 10.1109/JBHI.2014.2335617.

引用本文的文献

1
A Robust Blood Vessel Segmentation Technique for Angiographic Images Employing Multi-Scale Filtering Approach.一种采用多尺度滤波方法的用于血管造影图像的稳健血管分割技术。
J Clin Med. 2025 Jan 8;14(2):354. doi: 10.3390/jcm14020354.
2
An innovative methodology for segmenting vessel like structures using artificial intelligence and image processing.一种使用人工智能和图像处理技术分割血管样结构的创新方法。
Sci Rep. 2024 Dec 5;14(1):30332. doi: 10.1038/s41598-024-81680-9.
3
Alterations in Macular Microvasculature in Pterygium Patients Measured by OCT Angiography.

本文引用的文献

1
A Hybrid Algorithm to Enhance Colour Retinal Fundus Images Using a Wiener Filter and CLAHE.基于维纳滤波器和 CLAHE 的彩色眼底视网膜图像增强混合算法。
J Digit Imaging. 2021 Jun;34(3):750-759. doi: 10.1007/s10278-021-00447-0. Epub 2021 Apr 22.
2
Association between hypertension and retinal vascular features in ultra-widefield fundus imaging.超广角眼底成像中高血压与视网膜血管特征之间的关联
Open Heart. 2020 Jan 8;7(1):e001124. doi: 10.1136/openhrt-2019-001124. eCollection 2020.
3
Analysis of Optic Chiasmal Compression Caused by Brain Tumors Using Optical Coherence Tomography Angiography.
通过光学相干断层扫描血管造影术测量翼状胬肉患者黄斑部微血管的改变。
Diagnostics (Basel). 2023 Apr 30;13(9):1603. doi: 10.3390/diagnostics13091603.
4
[A survey of loss function of medical image segmentation algorithms].[医学图像分割算法的损失函数研究]
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2023 Apr 25;40(2):392-400. doi: 10.7507/1001-5515.202206038.
5
Retinal Vessel Segmentation Based on B-COSFIRE Filters in Fundus Images.基于眼底图像的 B-COSFIRE 滤波器的视网膜血管分割。
Front Public Health. 2022 Sep 9;10:914973. doi: 10.3389/fpubh.2022.914973. eCollection 2022.
6
Brain Tumor Segmentation Based on Bendlet Transform and Improved Chan-Vese Model.基于Bendlet变换和改进的Chan-Vese模型的脑肿瘤分割
Entropy (Basel). 2022 Aug 27;24(9):1199. doi: 10.3390/e24091199.
7
LightEyes: A Lightweight Fundus Segmentation Network for Mobile Edge Computing.LightEyes：面向移动边缘计算的轻量级眼底分割网络。
Sensors (Basel). 2022 Apr 19;22(9):3112. doi: 10.3390/s22093112.
利用光相干断层扫描血管造影术分析脑肿瘤对视交叉的压迫。
Sci Rep. 2020 Feb 7;10(1):2088. doi: 10.1038/s41598-020-59158-1.
4
Multicolor Fundus Imaging of Polypoidal Choroidal Vasculopathy.息肉样脉络膜血管病变的多色眼底成像
Ophthalmol Retina. 2019 May;3(5):400-409. doi: 10.1016/j.oret.2019.01.009. Epub 2019 Jan 18.
5
A retinal model of cerebral malaria.脑型疟疾的视网膜模型。
Sci Rep. 2019 Mar 5;9(1):3470. doi: 10.1038/s41598-019-39143-z.
6
Agreement between retinal images obtained via smartphones and images obtained with retinal cameras or fundoscopic exams - systematic review and meta-analysis.通过智能手机获得的视网膜图像与通过视网膜相机或眼底检查获得的图像之间的一致性——系统评价和荟萃分析。
Clin Ophthalmol. 2018 Dec 11;12:2581-2589. doi: 10.2147/OPTH.S182022. eCollection 2018.
7
Smartphone Fundus Photography.智能手机眼底摄影。
J Vis Exp. 2017 Jul 6(125):55958. doi: 10.3791/55958.
8
A review on automatic analysis techniques for color fundus photographs.彩色眼底照片自动分析技术综述
Comput Struct Biotechnol J. 2016 Oct 6;14:371-384. doi: 10.1016/j.csbj.2016.10.001. eCollection 2016.
9
Advances in retinal imaging for diabetic retinopathy and diabetic macular edema.糖尿病视网膜病变和糖尿病性黄斑水肿的视网膜成像进展。
Indian J Ophthalmol. 2016 Jan;64(1):76-83. doi: 10.4103/0301-4738.178145.
10
Fundus photography as a convenient tool to study microvascular responses to cardiovascular disease risk factors in epidemiological studies.在流行病学研究中，眼底摄影作为一种便捷工具，用于研究微血管对心血管疾病风险因素的反应。
J Vis Exp. 2014 Oct 22(92):e51904. doi: 10.3791/51904.