综述
ENGLISH ABSTRACT
人工智能在眼科光相干断层扫描图像中的应用
段恺睿
张弘 [综述]
作者及单位信息
·
DOI: 10.3760/cma.j.cn115989-20191231-00566
Application of artificial intelligence in ophthalmic optical coherence tomography
Duan Kairui
Zhang Hong
Authors Info & Affiliations
Duan Kairui
Eye Hospital, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China
Zhang Hong
Eye Hospital, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China
·
DOI: 10.3760/cma.j.cn115989-20191231-00566
933
237
0
1
5
3
PDF下载
APP内阅读
摘要

人工智能(AI)作为计算机科学的前沿研究领域,在医学领域已有广泛的应用。眼科诊疗过程中产生大量影像学资料,而AI在图像识别方面具有极大优势,将AI应用于眼科影像已逐渐成为眼科领域的研究热点。目前,已有大量研究报道AI技术成功应用于眼科疾病的诊断、分型、分期、治疗途径和治疗效果随访跟踪,如闭角型青光眼、年龄相关性黄斑变性和糖尿病视网膜病变等。此外,近年来有越来越多的研究发现将AI技术应用于光相干断层扫描(OCT)和光相干断层扫描血管成像(OCTA)图像识别、判读,进而诊断眼科疾病,同样具有较高的特异性和准确性。本文就目前AI结合OCT和OCTA图像在眼前节疾病、眼底疾病等眼部疾病中的临床应用作一综述。

人工智能;深度学习;光相干断层扫描;年龄相关性黄斑变性;糖尿病视网膜病变;青光眼
ABSTRACT

Artificial intelligence (AI) has become the forefront of research in computer science, which has been widely used in the medical field.Ophthalmology is a discipline highly dependent on imaging inspection.AI has great advantages in image recognition.The combination of the two has gradually become a research focus in ophthalmology.Recent research results have promoted the development of the diagnosis, classification, staging, treatment approach and follow-up of treatment effects of ophthalmic diseases, such as angle-closure glaucoma, age-related macular degeneration and diabetic retinopathy.In recent years, the rapid development of optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) has become an indispensable part of the ophthalmic auxiliary examination.More and more researchers have applied deep learning technology in AI to identify and interpret OCT and OCTA images to diagnose eye diseases.Some researchers have applied AI to OCTA to improve the quality of images.AI shows excellent specificity and accuracy in interpretation and diagnosis for disease through images which can even be comparable to human experts.This article mainly outlines the concept and characteristics of AI as well as the current application of AI combined with OCT and OCTA images in eye diseases.

Artificial intelligence;Deep learning;Tomography, optical coherence;Age-related macular degeneration;Diabetic retinopathy;Glaucoma
Zhang Hong, Email: mocdef.3ab6165450540831
引用本文

段恺睿,张弘. 人工智能在眼科光相干断层扫描图像中的应用[J]. 中华实验眼科杂志,2022,40(01):83-87.

DOI:10.3760/cma.j.cn115989-20191231-00566

PERMISSIONS

Request permissions for this article from CCC.

评价本文
*以上评分为匿名评价
随着眼科的发展,大部分眼科疾病的诊疗越来越依赖影像学检查,同时产生了大量的眼科检查图像。人工智能(artificial intelligence,AI)在图像识别方面具有极大优势,因此,将AI应用于眼科图像的识别以进一步提高眼科疾病的诊疗效率,近年来逐渐成为眼科领域的研究热点。有研究发现将AI应用于光相干断层扫描(optical coherence tomography,OCT)和光相干断层扫描血管成像(optical coherence tomography angiography,OCTA)图像的识别、判读,进而诊断眼科疾病,具有较高的特异性和准确性。因此,将AI应用于眼科OCT和OCTA图像中的研究具有重要的临床意义。本文对目前AI结合OCT和OCTA图像在眼前节疾病、眼底疾病等眼部疾病中的临床应用研究进展进行综述。
试读结束,您可以通过登录机构账户或个人账户后获取全文阅读权限。
参考文献
[1]
Rahimy E Deep learning applications in ophthalmology[J]Curr Opin Ophthalmol 201829(3)∶254-260. DOI: 10.1097/ICU.0000000000000470 .
返回引文位置Google Scholar
百度学术
万方数据
[2]
Gulshan V Peng L Coram M et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs[J]JAMA 2016316(22)∶2402-2410. DOI: 10.1001/jama.2016.17216 .
返回引文位置Google Scholar
百度学术
万方数据
[3]
Hinton GE Osindero S Teh YW . A fast learning algorithm for deep belief nets[J]Neural Comput 200618(7)∶1527-1554. DOI: 10.1162/neco.2006.18.7.1527 .
返回引文位置Google Scholar
百度学术
万方数据
[4]
Hinton G Deng L Yu D et al. Deep neural networks for acoustic modeling in speech recognition:the shared views of four research groups[J]IEEE Signal processing magazine 201229(6)∶82-97. DOI: 10.1109/MSP.2012.2205597 .
返回引文位置Google Scholar
百度学术
万方数据
[5]
袁进李萌重视我国眼科人工智能发展面临的机遇和挑战[J]中华实验眼科杂志 201937(8)∶599-602. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.002 .
返回引文位置Google Scholar
百度学术
万方数据
Yuan J Li M Attach importance to the opportunities and challenges facing the development of ophthalmic artificial intelligence in China[J]Chin J Exp Ophthalmol 201937(8)∶599-602. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.002 .
Goto CitationGoogle Scholar
Baidu Scholar
Wanfang Data
[6]
Esteva A Robicquet A Ramsundar B et al. A guide to deep learning in healthcare[J]Nat Med 201925(1)∶24-29. DOI: 10.1038/s41591-018-0316-z .
返回引文位置Google Scholar
百度学术
万方数据
[7]
Lewis-Kraus G The great A.I.awakening[N/OL]The New York Times2016-12-14[2021-05-20]https://www.nytimes.com/2016/12/14/magazine/the-great-ai-awakening.html.
返回引文位置Google Scholar
百度学术
万方数据
[8]
Muhkerjee S A.I.versus M.D.What happens when diagnosis is automated?[N/OL]The New Yorker2017-03-27[2021-05-20]https://www.newyorker.com/magazine/2017/04/03/ai-versus-md.
返回引文位置Google Scholar
百度学术
万方数据
[9]
Russakovsky O Deng J Su H et al. ImageNet large scale visual recognition challenge[J/OL]arXiv 20151409.0575[2021-05-20]https://arxiv.org/abs/1409.0575.
返回引文位置Google Scholar
百度学术
万方数据
[10]
Koch C How the computer beat the Go master[N/OL]Scientific American2016-03-19[2021-05-20]https://www.scientifi-camerican.com/article/how-the-computer-beat-the-go-master/.
返回引文位置Google Scholar
百度学术
万方数据
[11]
Silver D Schrittwieser J Simonyan K et al. Mastering the game of Go without human knowledge[J]Nature 2017550(7676)∶354-359. DOI: 10.1038/nature24270 .
返回引文位置Google Scholar
百度学术
万方数据
[12]
Chan S Siegel EL . Will machine learning end the viability of radiology as a thriving medical specialty?[J/OL]Br J Radiol 201992(1094)∶20180416[2021-05-20]http://www.ncbi.nlm.nih.gov/pubmed/30325645. DOI: 10.1259/bjr.20180416 .
返回引文位置Google Scholar
百度学术
万方数据
[13]
Doors M Berendschot TT de Brabander J et al. Value of optical coherence tomography for anterior segment surgery[J]J Cataract Refract Surg 201036(7)∶1213-1229. DOI: 10.1016/j.jcrs.2010.05.002 .
返回引文位置Google Scholar
百度学术
万方数据
[14]
Huang D Swanson EA Lin CP et al. Optical coherence tomography[J]Science 1991254(5035)∶1178-1181. DOI: 10.1126/science.1957169 .
返回引文位置Google Scholar
百度学术
万方数据
[15]
Drexler W Fujimoto JG . State-of-the-art retinal optical coherence tomography[J]Prog Retin Eye Res 200827(1)∶45-88. DOI: 10.1016/j.preteyeres.2007.07.005 .
返回引文位置Google Scholar
百度学术
万方数据
[16]
Izatt JA Hee MR Swanson EA et al. Micrometer-scale resolution imaging of the anterior eye in vivo with optical coherence tomography [J]Arch Ophthalmol 1994112(12)∶1584-1589. DOI: 10.1001/archopht.1994.01090240090031 .
返回引文位置Google Scholar
百度学术
万方数据
[17]
Jia Y Tan O Tokayer J et al. Split-spectrum amplitude-decorrelation angiography with optical coherence tomography[J]Opt Express 201220(4)∶4710-4725. DOI: 10.1364/OE.20.004710 .
返回引文位置Google Scholar
百度学术
万方数据
[18]
Lupidi M Cerquaglia A Chhablani J et al. Optical coherence tomography angiography in age-related macular degeneration:the game changer[J]Eur J Ophthalmol 201828(4)∶349-357. DOI: 10.1177/1120672118766807 .
返回引文位置Google Scholar
百度学术
万方数据
[19]
Treder M Lauermann JL Alnawaiseh M et al. Using deep learning in automated detection of graft detachment in descemet membrane endothelial keratoplasty:a pilot study[J]Cornea 201938(2)∶157-161. DOI: 10.1097/ICO.0000000000001776 .
返回引文位置Google Scholar
百度学术
万方数据
[20]
Hayashi T Tabuchi H Masumoto H et al. A deep learning approach in rebubbling after Descemet ' s membrane endothelial keratoplasty [J]Eye Contact Lens 202046(2)∶121-126. DOI: 10.1097/ICL.0000000000000634 .
返回引文位置Google Scholar
百度学术
万方数据
[21]
Naithani P Sihota R Sony P et al. Evaluation of optical coherence tomography and heidelberg retinal tomography parameters in detecting early and moderate glaucoma[J]Invest Ophthalmol Vis Sci 200748(7)∶3138-3145. DOI: 10.1167/iovs.06-1407 .
返回引文位置Google Scholar
百度学术
万方数据
[22]
Shigueoka LS Vasconcellos J Schimiti RB et al. Automated algorithms combining structure and function outperform general ophthalmologists in diagnosing glaucoma[J/OL]PLoS One 201813(12)∶e0207784[2021-05-26]http://www.ncbi.nlm.nih.gov/pubmed/30517157. DOI: 10.1371/journal.pone.0207784 .
返回引文位置Google Scholar
百度学术
万方数据
[23]
Niwas SI Lin W Bai X et al. Automated anterior segment OCT image analysis for angle closure glaucoma mechanisms classification[J]Comput Methods Programs Biomed 201613065-75. DOI: 10.1016/j.cmpb.2016.03.018 .
返回引文位置Google Scholar
百度学术
万方数据
[24]
Kermany DS Goldbaum M Cai W et al. Identifying medical diagnoses and treatable diseases by image-based deep learning[J]Cell 2018172(5)∶1122-1131. DOI: 10.1016/j.cell.2018.02.010 .
返回引文位置Google Scholar
百度学术
万方数据
[25]
De Fauw J Ledsam JR Romera-Paredes B et al. Clinically applicable deep learning for diagnosis and referral in retinal disease[J]Nat Med 201824(9)∶1342-1350. DOI: 10.1038/s41591-018-0107-6 .
返回引文位置Google Scholar
百度学术
万方数据
[26]
龚雁顾在旺胡衍基于深度学习OCT辅助诊断湿性年龄相关性黄斑变性算法的应用[J]中华实验眼科杂志 201937(8)∶658-662. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.014 .
返回引文位置Google Scholar
百度学术
万方数据
Gong Y Gu ZW Hu Y et al. The application value of deep learning OCT on wet age-related macular degeneration assisted diagnosis[J]Chin J Exp Ophthalmol 201937(8)∶658-662. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.014 .
Goto CitationGoogle Scholar
Baidu Scholar
Wanfang Data
[27]
Schmidt-Erfurth U Waldstein SM Klimscha S et al. Prediction of individual disease conversion in early AMD using artificial intelligence[J]Invest Ophthalmol Vis Sci 201859(8)∶3199-3208. DOI: 10.1167/iovs.18-24106 .
返回引文位置Google Scholar
百度学术
万方数据
[28]
Hwang DK Hsu CC Chang KJ et al. Artificial intelligence-based decision-making for age-related macular degeneration[J]Theranostics 20199(1)∶232-245. DOI: 10.7150/thno.28447 .
返回引文位置Google Scholar
百度学术
万方数据
[29]
Jemshi KM Gopi VP Issac Niwas S Development of an efficient algorithm for the detection of macular edema from optical coherence tomography images[J]Int J Comput Assist Radiol Surg 201813(9)∶1369-1377. DOI: 10.1007/s11548-018-1795-6 .
返回引文位置Google Scholar
百度学术
万方数据
[30]
Samagaio G Estévez A Moura J et al. Automatic macular edema identification and characterization using OCT images[J]Comput Methods Programs Biomed 201816347-63. DOI: 10.1016/j.cmpb.2018.05.033 .
返回引文位置Google Scholar
百度学术
万方数据
[31]
Prahs P Radeck V Mayer C et al. OCT-based deep learning algorithm for the evaluation of treatment indication with anti-vascular endothelial growth factor medications[J] Graefe ' s Arch Clin Exp Ophthalmol 2018256(1)∶91-98. DOI: 10.1007/s00417-017-3839-y .
返回引文位置Google Scholar
百度学术
万方数据
[32]
Sandhu HS Eltanboly A Shalaby A et al. Automated diagnosis and grading of diabetic retinopathy using optical coherence to mography [J]Invest Ophthalmol Vis Sci 201859(7)∶3155-3160. DOI: 10.1167/iovs.17-23677 .
返回引文位置Google Scholar
百度学术
万方数据
[33]
Nagasato D Tabuchi H Masumoto H et al. Automated detection of a nonperfusion area caused by retinal vein occlusion in optical coherence tomography angiography images using deep learning[J/OL]PLoS One 201914(11)∶e0223965[2021-06-16]http://www.ncbi.nlm.nih.gov/pubmed/31697697. DOI: 10.1371/journal.pone.0223965 .
返回引文位置Google Scholar
百度学术
万方数据
[34]
Guo Y Camino A Wang J et al. MEDnet,a neural network for automated detection of avascular area in OCT angiography[J] Biomed Opt Exp ress 20189(11)∶5147-5158. DOI: 10.1364/BOE.9.005147 .
返回引文位置Google Scholar
百度学术
万方数据
[35]
Lauermann JL Treder M Alnawaiseh M et al. Automated OCT angiography image quality assessment using a deep learning algorithm[J] Graefe ' s Arch Clin Exp Ophthalmol 2019257(8)∶1641-1648. DOI: 10.1007/s00417-019-04338-7 .
返回引文位置Google Scholar
百度学术
万方数据
[36]
Guo Y Hormel TT Xiong H et al. Development and validation of a deep learning algorithm for distinguishing the nonperfusion area from signal reduction artifacts on OCT angiography[J]Biomed Opt Express 201910(7)∶3257-3268. DOI: 10.1364/BOE.10.003257 .
返回引文位置Google Scholar
百度学术
万方数据
[37]
Told R Reiter GS Orsolya A et al. Swept source optical coherence tomography angiography,fluorescein angiography,and indocyanine green angiography comparisons revisited:using a novel deep-learning-assisted approach for image registration[J]Retina 202040(10)∶2010-2017. DOI: 10.1097/IAE.0000000000002695 .
返回引文位置Google Scholar
百度学术
万方数据
[38]
Prentašic P Heisler M Mammo Z et al. Segmentation of the foveal microvasculature using deep learning networks[J/OL]J Biomed Opt 201621(7)∶75008[2021-06-26]http://www.ncbi.nlm.nih.gov/pubmed/27401936. DOI: 10.1117/1.JBO.21.7.075008 .
返回引文位置Google Scholar
百度学术
万方数据
备注信息
A
张弘,Email: mocdef.3ab6165450540831
B
所有作者均声明不存在利益冲突
C
国家自然科学基金项目 (81970776、81671844)
黑龙江省医学科学院2017—2018年度科研转化专项基金项目 (CR201809)
评论 (0条)
注册
登录
时间排序
暂无评论,发表第一条评论抢沙发
MedAI助手(体验版)
文档即答
智问智答
机器翻译
回答内容由人工智能生成,我社无法保证其准确性和完整性,该生成内容不代表我们的态度或观点,仅供参考。
生成快照
文献快照

你好,我可以帮助您更好的了解本文,请向我提问您关注的问题。

0/2000

《中华医学会杂志社用户协议》 | 《隐私政策》

《SparkDesk 用户协议》 | 《SparkDesk 隐私政策》

网信算备340104764864601230055号 | 网信算备340104726288401230013号

技术支持:

历史对话
本文全部
还没有聊天记录
设置
模式
纯净模式沉浸模式
字号