• 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

利用深度学习评估扫频源 OCT 血管造影对高度近视性青光眼的黄斑微血管的诊断能力。

Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learning.

机构信息

Department of Ophthalmology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Korea.

Biomedical Research Institute, Seoul National University Hospital, Seoul, Korea.

出版信息

Sci Rep. 2023 Mar 30;13(1):5209. doi: 10.1038/s41598-023-32164-9.

DOI:10.1038/s41598-023-32164-9
PMID:36997639
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10063664/
Abstract

Macular OCT angiography (OCTA) measurements have been reported to be useful for glaucoma diagnostics. However, research on highly myopic glaucoma is lacking, and the diagnostic value of macular OCTA measurements versus OCT parameters remains inconclusive. We aimed to evaluate the diagnostic ability of the macular microvasculature assessed with OCTA for highly myopic glaucoma and to compare it with that of macular thickness parameters, using deep learning (DL). A DL model was trained, validated and tested using 260 pairs of macular OCTA and OCT images from 260 eyes (203 eyes with highly myopic glaucoma, 57 eyes with healthy high myopia). The DL model achieved an AUC of 0.946 with the OCTA superficial capillary plexus (SCP) images, which was comparable to that with the OCT GCL+ (ganglion cell layer + inner plexiform layer; AUC, 0.982; P = 0.268) or OCT GCL++ (retinal nerve fiber layer + ganglion cell layer + inner plexiform layer) images (AUC, 0.997; P = 0.101), and significantly superior to that with the OCTA deep capillary plexus images (AUC, 0.779; P = 0.028). The DL model with macular OCTA SCP images demonstrated excellent and comparable diagnostic ability to that with macular OCT images in highly myopic glaucoma, which suggests macular OCTA microvasculature could serve as a potential biomarker for glaucoma diagnosis in high myopia.

摘要

黄斑 OCT 血管造影(OCTA)测量值已被证明可用于青光眼的诊断。然而,对于高度近视性青光眼的研究较少,OCTA 测量值与 OCT 参数的诊断价值仍不确定。我们旨在使用深度学习(DL)评估 OCTA 评估的黄斑微血管对高度近视性青光眼的诊断能力,并将其与黄斑厚度参数进行比较。使用来自 260 只眼睛(203 只高度近视性青光眼,57 只健康高度近视)的 260 对黄斑 OCTA 和 OCT 图像,训练、验证和测试了一个 DL 模型。DL 模型使用 OCTA 浅层毛细血管丛(SCP)图像的 AUC 为 0.946,与 OCT GCL+(神经节细胞层+内丛状层;AUC,0.982;P=0.268)或 OCT GCL++(视网膜神经纤维层+神经节细胞层+内丛状层;AUC,0.997;P=0.101)图像相当,并且明显优于 OCTA 深层毛细血管丛图像(AUC,0.779;P=0.028)。黄斑 OCTA SCP 图像的 DL 模型在高度近视性青光眼的诊断能力方面表现出出色且相当的能力,这表明黄斑 OCTA 微血管可作为高度近视性青光眼诊断的潜在生物标志物。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d71b/10063664/b67518813578/41598_2023_32164_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d71b/10063664/597b6b6a04dd/41598_2023_32164_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d71b/10063664/c953d1820eac/41598_2023_32164_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d71b/10063664/b67518813578/41598_2023_32164_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d71b/10063664/597b6b6a04dd/41598_2023_32164_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d71b/10063664/c953d1820eac/41598_2023_32164_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d71b/10063664/b67518813578/41598_2023_32164_Fig3_HTML.jpg

相似文献

1
Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learning.利用深度学习评估扫频源 OCT 血管造影对高度近视性青光眼的黄斑微血管的诊断能力。
Sci Rep. 2023 Mar 30;13(1):5209. doi: 10.1038/s41598-023-32164-9.
2
Diagnostic ability of vessel density measured by spectral-domain optical coherence tomography angiography for glaucoma in patients with high myopia.频域光相干断层扫描血管造影测量血管密度对高度近视患者青光眼的诊断能力。
Sci Rep. 2020 Feb 20;10(1):3027. doi: 10.1038/s41598-020-60051-0.
3
The ability of macular parameters and circumpapillary retinal nerve fiber layer by three SD-OCT instruments to diagnose highly myopic glaucoma.三种 SD-OCT 仪器的黄斑参数和环周视网膜神经纤维层对高度近视性青光眼的诊断能力。
Invest Ophthalmol Vis Sci. 2013 Sep 5;54(9):6025-32. doi: 10.1167/iovs.13-12630.
4
Development of a deep learning system to detect glaucoma using macular vertical optical coherence tomography scans of myopic eyes.利用近视眼的黄斑垂直光学相干断层扫描开发一种深度学习系统来检测青光眼。
Sci Rep. 2023 May 17;13(1):8040. doi: 10.1038/s41598-023-34794-5.
5
Diagnostic performance of wide-field optical coherence tomography angiography for high myopic glaucoma.广角光学相干断层扫描血管造影术在高度近视性青光眼诊断中的性能。
Sci Rep. 2024 Jan 3;14(1):367. doi: 10.1038/s41598-023-49542-y.
6
Glaucoma detection ability of ganglion cell-inner plexiform layer thickness by spectral-domain optical coherence tomography in high myopia.高度近视患者的光谱域光学相干断层扫描检测神经节细胞-内丛状层厚度的青光眼能力。
Invest Ophthalmol Vis Sci. 2013 Mar 28;54(3):2296-304. doi: 10.1167/iovs.12-10530.
7
Quantitative assessment of the retinal microvasculature and choriocapillaris in myopic patients using swept-source optical coherence tomography angiography.使用扫频源光学相干断层扫描血管造影术对近视患者视网膜微血管和脉络膜毛细血管进行定量评估。
Graefes Arch Clin Exp Ophthalmol. 2020 Jun;258(6):1173-1180. doi: 10.1007/s00417-020-04639-2. Epub 2020 Mar 6.
8
Diagnostic Accuracy of Wide-Field Map from Swept-Source Optical Coherence Tomography for Primary Open-Angle Glaucoma in Myopic Eyes.超广角扫频源光学相干断层扫描在近视患者原发性开角型青光眼诊断中的准确性。
Am J Ophthalmol. 2020 Oct;218:182-191. doi: 10.1016/j.ajo.2020.05.032. Epub 2020 Jun 20.
9
Glaucoma Detection Ability of Macular Ganglion Cell-Inner Plexiform Layer Thickness in Myopic Preperimetric Glaucoma.黄斑神经节细胞-内丛状层厚度在近视性视野缺损前期青光眼患者中的青光眼检测能力
Invest Ophthalmol Vis Sci. 2015 Dec;56(13):8306-13. doi: 10.1167/iovs.15-18141.
10
Combined wide-field optical coherence tomography angiography density map for high myopic glaucoma detection.用于高度近视性青光眼检测的宽视野光学相干断层扫描血管造影密度图的联合应用。
Sci Rep. 2021 Nov 11;11(1):22034. doi: 10.1038/s41598-021-01661-0.

引用本文的文献

1
Assessment of Retinal Microcirculation in Primary Open-Angle Glaucoma Using Adaptive Optics and OCT Angiography: Correlation with Structural and Functional Damage.使用自适应光学和光学相干断层扫描血管造影术评估原发性开角型青光眼的视网膜微循环:与结构和功能损害的相关性
J Clin Med. 2025 Jul 14;14(14):4978. doi: 10.3390/jcm14144978.
2
Widefield OCT angiography.广角光学相干断层扫描血管造影术
Prog Retin Eye Res. 2025 Jul;107:101378. doi: 10.1016/j.preteyeres.2025.101378. Epub 2025 Jun 13.
3
Artificial Intelligence in Glaucoma: Advances in Diagnosis, Progression Forecasting, and Surgical Outcome Prediction.

本文引用的文献

1
External Validation of Deep Learning Algorithms for Radiologic Diagnosis: A Systematic Review.用于放射诊断的深度学习算法的外部验证:一项系统评价。
Radiol Artif Intell. 2022 May 4;4(3):e210064. doi: 10.1148/ryai.210064. eCollection 2022 May.
2
Domain Shifts in Machine Learning Based Covid-19 Diagnosis From Blood Tests.基于血液检测的机器学习新冠病毒诊断中的域转移
J Med Syst. 2022 Mar 29;46(5):23. doi: 10.1007/s10916-022-01807-1.
3
Vision Transformer-based recognition of diabetic retinopathy grade.基于 Vision Transformer 的糖尿病视网膜病变分级识别。
青光眼领域的人工智能:诊断、病情进展预测及手术结果预测的进展
Int J Mol Sci. 2025 May 8;26(10):4473. doi: 10.3390/ijms26104473.
4
Advances in OCT Angiography.光学相干断层扫描血管造影术的进展。
Transl Vis Sci Technol. 2025 Mar 3;14(3):6. doi: 10.1167/tvst.14.3.6.
5
Machine Learning Approaches in High Myopia: Systematic Review and Meta-Analysis.高度近视的机器学习方法:系统评价与荟萃分析
J Med Internet Res. 2025 Jan 3;27:e57644. doi: 10.2196/57644.
6
Advanced Analysis of OCT/OCTA Images for Accurately Differentiating Between Glaucoma and Healthy Eyes Using Deep Learning Techniques.使用深度学习技术对光学相干断层扫描(OCT)/光学相干断层扫描血管造影(OCTA)图像进行高级分析,以准确区分青光眼和健康眼睛。
Clin Ophthalmol. 2024 Nov 26;18:3493-3502. doi: 10.2147/OPTH.S472231. eCollection 2024.
7
Application of artificial intelligence in glaucoma care: An updated review.人工智能在青光眼护理中的应用:最新综述。
Taiwan J Ophthalmol. 2024 Sep 13;14(3):340-351. doi: 10.4103/tjo.TJO-D-24-00044. eCollection 2024 Jul-Sep.
8
Diagnosing Glaucoma Based on the Ocular Hypertension Treatment Study Dataset Using Chat Generative Pre-Trained Transformer as a Large Language Model.基于眼压治疗研究数据集,使用聊天生成预训练变换器作为大语言模型诊断青光眼
Ophthalmol Sci. 2024 Aug 22;5(1):100599. doi: 10.1016/j.xops.2024.100599. eCollection 2025 Jan-Feb.
9
Diagnostic performance of wide-field optical coherence tomography angiography for high myopic glaucoma.广角光学相干断层扫描血管造影术在高度近视性青光眼诊断中的性能。
Sci Rep. 2024 Jan 3;14(1):367. doi: 10.1038/s41598-023-49542-y.
Med Phys. 2021 Dec;48(12):7850-7863. doi: 10.1002/mp.15312. Epub 2021 Nov 16.
4
Predicting sex from retinal fundus photographs using automated deep learning.利用自动化深度学习从眼底照片预测性别。
Sci Rep. 2021 May 13;11(1):10286. doi: 10.1038/s41598-021-89743-x.
5
Retinal applications of swept source optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA).扫频源光学相干断层扫描(OCT)和光相干断层扫描血管造影(OCTA)在视网膜中的应用。
Prog Retin Eye Res. 2021 Sep;84:100951. doi: 10.1016/j.preteyeres.2021.100951. Epub 2021 Jan 28.
6
Prediction of systemic biomarkers from retinal photographs: development and validation of deep-learning algorithms.从视网膜照片预测系统性生物标志物:深度学习算法的开发和验证。
Lancet Digit Health. 2020 Oct;2(10):e526-e536. doi: 10.1016/S2589-7500(20)30216-8.
7
Detection of Progressive Glaucomatous Optic Nerve Damage on Fundus Photographs with Deep Learning.利用深度学习技术在眼底照片上检测青光眼性视神经进行性损伤
Ophthalmology. 2021 Mar;128(3):383-392. doi: 10.1016/j.ophtha.2020.07.045. Epub 2020 Jul 28.
8
Diagnostic Accuracy of Wide-Field Map from Swept-Source Optical Coherence Tomography for Primary Open-Angle Glaucoma in Myopic Eyes.超广角扫频源光学相干断层扫描在近视患者原发性开角型青光眼诊断中的准确性。
Am J Ophthalmol. 2020 Oct;218:182-191. doi: 10.1016/j.ajo.2020.05.032. Epub 2020 Jun 20.
9
Gradient-Boosting Classifiers Combining Vessel Density and Tissue Thickness Measurements for Classifying Early to Moderate Glaucoma.基于血管密度和组织厚度测量的梯度提升分类器在早期至中期青光眼分类中的应用。
Am J Ophthalmol. 2020 Sep;217:131-139. doi: 10.1016/j.ajo.2020.03.024. Epub 2020 Mar 25.
10
Asymmetry analysis of macular optical coherence tomography angiography in patients with glaucoma and healthy subjects.青光眼患者与健康受试者的黄斑光学相干断层扫描血管造影的不对称性分析。
Br J Ophthalmol. 2020 Dec;104(12):1724-1729. doi: 10.1136/bjophthalmol-2019-315592. Epub 2020 Feb 27.