[1]杨丽丹,李青蒨,陈倩茵,等.人工智能在青光眼诊断中的研究进展[J].眼科新进展,2023,43(6):500-504.[doi:10.13389/j.cnki.rao.2023.0102]
　YANG Lidan,LI Qingqian,CHEN Qianyin,et al.Research progress of artificial intelligence in the diagnosis of glaucoma[J].Recent Advances in Ophthalmology,2023,43(6):500-504.[doi:10.13389/j.cnki.rao.2023.0102]
点击复制

人工智能在青光眼诊断中的研究进展/HTML
分享到：

《眼科新进展》[ISSN:1003-5141/CN:41-1105/R]

卷:
43卷
期数:
2023年6期
页码:
500-504
栏目:
文献综述
出版日期:
2023-06-05

文章信息/Info

Title:
Research progress of artificial intelligence in the diagnosis of glaucoma
作者:
杨丽丹; 李青蒨; 陈倩茵; 马红婕; 东田理沙; 林迪; 林晨
410035　湖南省长沙市，中南大学爱尔眼科学院（杨丽丹，马红婕，林晨）；518081　广东省深圳市，盐田区人民医院眼科（李青蒨）；510040　广东省广州市，暨南大学附属广州爱尔眼科医院（陈倩茵，马红婕）；518055　广东省深圳市，南方科技大学计算机科学与工程系（东田理沙）；300072　天津市，天津大学计算机科学与技术学院（林迪）；518020　广东省深圳市，深圳市人民医院眼科（林晨）
Author(s):
YANG Lidan1; LI Qingqian2; CHEN Qianyin3; MA Hongjie1; 3; RISA Higashita4; LIN Di5; LIN Chen1; 6
1.The Aier School of Ophthalmology,Central South University,Changsha 410035
2.Department of Ophthalmology,Yantian District People’s Hospital,Shenzhen 518081
3.Guangzhou Aier Eye Hospital to Jinan University,Guangzhou 510040
4.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen
5.School of Computer Science and Technology,Tianjin University,Tianjin 300072
6.Department of Ophthalmology,Shenzhen People’s Hospital,Shenzhen
关键词:
青光眼; 人工智能; 深度学习
Keywords:
glaucoma;  artificial intelligence;  deep learning
分类号:
R775.1
DOI:
10.13389/j.cnki.rao.2023.0102
文献标志码:
A
摘要:
近年来，随着以深度学习（DL）为代表的人工智能（AI）技术发展，为眼科领域带来了新的研究手段，提高了眼科疾病的筛查和诊断水平。目前，AI对糖尿病视网膜病变、白内障、早产儿视网膜病变、角膜炎等多种疾病的诊断效率较高。在青光眼方面，AI可用于分析眼底彩色照相、光学相干断层扫描（OCT）、视野等多模态影像综合评估结构及功能改变，从而提高青光眼的诊断水平。本文主要对AI在青光眼诊断中的研究进展进行综述，探讨其优势和现阶段的局限性。
Abstract:
In recent years, the developing artificial intelligence (AI) represented by deep learning has created many new methods for clinical research in ophthalmology, improving the efficiency of screening and diagnosing ophthalmic diseases. AI has been well applied in the diagnosis of diabetic retinopathy, cataract, retinopathy of prematurity, and keratitis. In the field of glaucoma, AI can be used to analyze multimodal images based on fundus photography, optical coherence tomography, and perimetry, so as to evaluate the structural and functional changes in the retina, improving the diagnostic level of glaucoma. This article reviews the application of AI in diagnosing glaucoma and discusses its advantages and limitations at the current stage.

参考文献/References:

［1］　SOH Z,YU M,BETZLER B K,MAJITHIA S,THAKUR S,THAM Y C,et al.The global extent of undetected glaucoma in adults:A systematic review and meta-analysis ［J］.Ophthalmology,2021,128(10):1393-1404.
［2］　THOMPSON A C,JAMMAL A A,BERCHUCK S I,MARIOTTONI E B,MEDEIROS F A.Assessment of a segmentation-free deep learning algorithm for diagnosing glaucoma from optical coherence tomography scans ［J］.JAMA Ophthalmol,2020,138(4):333-339.
［3］　LIANG Y B,FRIEDMAN D S,ZHOU Q,YANG X,SUN L P,GUO L X,et al.Prevalence of primary open angle glaucoma in a rural adult chinese population:the handan eye study ［J］.Invest Ophthalmol Vis Sci,2011,52(11):8250-8257.
［4］　MWANZA J C,LEE G,BUDENZ D L,WARREN J L,WALL M,ARTES P H,et al.Validation of the unc oct index for the diagnosis of early glaucoma ［J］.Transl Vis Sci Technol,2018,7(2):16.
［5］　LIU H,LI L,WORMSTONE I M,QIAO C,ZHANG C,LIU P,et al.Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs ［J］.JAMA Ophthalmol,2019,137(12):1353-1360.
［6］　RAMESH A N,KAMBHAMPATI C,MONSON J R,DREW P J.Artificial intelligence in medicine ［J］.Ann R Coll Surg Engl,2004,86(5):334-338.
［7］　TING D S W,PENG L,VARADARAJAN A V,KEANE P A,BURLINA P M,CHIANG M F,et al.Deep learning in ophthalmology:The technical and clinical considerations ［J］.Prog Retin Eye Res,2019,72:e100759.
［8］　SINTHANAYOTHIN C,BOYCE J F,COOK H L,WILLIAMSON T H.Automated localisation of the optic disc,fovea,and retinal blood vessels from digital colour fundus images ［J］.Br J Ophthalmol,1999,83(8):902-910.
［9］　XU Y,HU M,LIU H,YANG H,WANG H,LU S,et al.A hierarchical deep learning approach with transparency and interpretability based on small samples for glaucoma diagnosis ［J］.NPJ Digit Med,2021,4(1):48.
［10］　张悦,余双,马锴,初春燕,张莉,庞睿奇,et al.人工智能关于视盘区多任务深度学习模型在青光眼分类中的应用 ［J］.中华眼科医学杂志（电子版）,2020,10(2):70-75.
ZHANG Y,YU S,MA K,CHU C Y,ZHANG L，PANG R Q,et al.The application of artificial intelligence multi-task deep learning model of optic disc area in the classification of glaucoma ［J］.Chin J Ophthalmol Med (Electr Ed),2020,10(2):70-75.
［11］　MAHESHWARI S,KANHANGAD V,PACHORI R B,BHANDARY S V,ACHARYA U R.Automated glaucoma diagnosis using bit-plane slicing and local binary pattern techniques ［J］.Comput Biol Med,2019,105:72-80.
［12］　HALEEM M S,HAN L,HEMERT J,FLEMING A,PASQUALE L R,SILVA P S,et al.Regional image features model for automatic classification between normal and glaucoma in fundus and scanning laser ophthalmoscopy (slo) images ［J］.J Med Syst,2016,40(6):132.
［13］　JAMPEL H D,FRIEDMAN D,QUIGLEY H,VITALE S,MILLER R,KNEZEVICH F,et al.Agreement among glaucoma specialists in assessing progressive disc changes from photographs in open-angle glaucoma patients ［J］.Am J Ophthalmol,2009,147(1):39-44
［14］　MEDEIROS F A,JAMMAL A A,THOMPSON A C.From machine to machine:an oct-trained deep learning algorithm for objective quantification of glaucomatous damage in fundus photographs ［J］.Ophthalmology,2019,126(4):513-521.
［15］　THOMPSON A C,JAMMAL A A,MEDEIROS F A.A deep learning algorithm to quantify neuroretinal rim loss from optic disc photographs ［J］.Am J Ophthalmol,2019,201:9-18.
［16］　GOLZAN S M,MORGAN W H,GEORGEVSKY D,GRAHAM S L.Correlation of retinal nerve fibre layer thickness and spontaneous retinal venous pulsations in glaucoma and normal controls ［J］.PLoS One,2015,10(6):e0128433.
［17］　GHEISARI S,SHARIFLOU S,PHU J,KENNEDY P J,AGAR A,KALLONIATIS M,et al.A combined convolutional and recurrent neural network for enhanced glaucoma detection ［J］.Sci Rep,2021,11(1):1945.
［18］　BURGANSKY-ELIASH Z,WOLLSTEIN G,CHU T,RAMSEY J D,GLYMOUR C,NOECKER R J,et al.Optical coherence tomography machine learning classifiers for glaucoma detection:a preliminary study ［J］.Invest Ophthalmol Vis Sci,2005,46(11):4147-4152.
［19］　SHIN J W,SUNG K R,SONG M K.Ganglion cell-inner plexiform layer and retinal nerve fiber layer changes in glaucoma suspects enable prediction of glaucoma development ［J］.Am J Ophthalmol,2020,210:26-34.
［20］　ASAOKA R,MURATA H,HIRASAWA K,FUJINO Y,MATSUURA M,MIKI A,et al.Using deep learning and transfer learning to accurately diagnose early-onset glaucoma from macular optical coherence tomography images ［J］.Am J Ophthalmol,2019,198:136-145.
［21］　MANSBERGER S L,MENDA S A,FORTUNE B A,GARDINER S K,DEMIREL S.Automated segmentation errors when using optical coherence tomography to measure retinal nerve fiber layer thickness in glaucoma ［J］.Am J Ophthalmol,2017,174:1-8.
［22］　MAETSCHKE S,ANTONY B,ISHIKAWA H,WOLLSTEIN G,SCHUMAN J,GARNAVI R.A feature agnostic approach for glaucoma detection in oct volumes ［J］.PLoS One,2019,14(7):e0219126.
［23］　FORTUNE B.Optical coherence tomography evaluation of the optic nerve head neuro-retinal rim in glaucoma ［J］.Clin Exp Optom,2019,102(3):286-290.
［24］　HUANG X R,KNIGHTON R W,ZHOU Y,ZHAO X P.Reflectance speckle of retinal nerve fiber layer reveals axonal activity ［J］.Invest Ophthalmol Vis Sci,2013,54(4):2616-2623.
［25］　PARK K,KIM J,LEE J.Macular vessel density and ganglion cell/inner plexiform layer thickness and their combinational index using artificial intelligence ［J］.J Glaucoma,2018,27(9):750-760.
［26］　林松,王抒阳,胡雅楠,秦鲁宁,王文赛,杨军.基于超声生物显微镜房角开闭状态的人工智能识别的研究 ［J］.中国超声医学杂志,2021,37(12):1321-1323.
LIN S,WANG S Y,HU Y N,QIN L N,WANG W S,YANG J.Automatic recognition of chamber angle opening and closing by artificial intelligence recognition based on ultrasound biomicroscopy ［J］.Chin J Ultrasound Med,2021,37(12):1321-1323.
［27］　FU H,BASKARAN M,XU Y,LIN S,WONG D W K,LIU J,et al.A deep learning system for automated angle-closure detection in anterior segment optical coherence tomography images ［J］.Am J Ophthalmol,2019,203:37-45.
［28］　LI F,YANG Y,SUN X,QIU Z,ZHANG S,TUN T A,et al.Di-gital gonioscopy based on three-dimensional anterior-segment oct:An international multicenter study ［J］.Ophthalmology,2022,129(1):45-53.
［29］　DENNISS J,TURPIN A,MCKENDRICK A M.Relating optical coherence tomography to visual fields in glaucoma:Structure-function mapping,limitations and future applications ［J］.Clin Exp Optom,2019,102(3):291-299.
［30］　GOLDBAUM M H,SAMPLE P A,WHITE H,CLT B,RAPHAELIAN P,FECHTNER R D,et al.Interpretation of automated perimetry for glaucoma by neural network ［J］.Invest Ophthalmol Vis Sci,1994,35(9):3362-3373.
［31］　LI F,WANG Z,QU G,SONG D,YUAN Y,XU Y,et al.Automatic differentiation of glaucoma visual field from non-glaucoma visual filed using deep convolutional neural network ［J］.BMC Med Imaging,2018,18(1):35.
［32］　ASAOKA R,MURATA H,IWASE A,ARAIE M.Detecting preperimetric glaucoma with standard automated perimetry using a deep learning classifier ［J］.Ophthalmology,2016,123(9):1974-1980.
［33］　SAMPLE P A,CHAN K,BODEN C,LEE T W,BLUMENTHAL E Z,WEINREB R N,et al.Using unsupervised learning with variational bayesian mixture of factor analysis to identify patterns of glaucomatous visual field defects ［J］.Invest Ophthalmol Vis Sci,2004,45(8):2596-2605.
［34］　BOWD C,WEINREB R N,BALASUBRAMANIAN M,LEE I,JANG G,YOUSEFI S,et al.Glaucomatous patterns in frequency doubling technology (FDT) perimetry data identified by unsupervised machine learning classifiers ［J］.PLoS One,2014,9(1):e85941.
［35］　BHARTIYA S,GANGWANI M,KALRA R B,AGGARWAL A,GAGRANI M,SIRISH K N.24-hour intraocular pressure monitoring:The way ahead ［J］.Rom J Ophthalmol,2019,63(4):315-320.
［36］　MARTIN K R,MANSOURI K,WEINREB R N,WASILEWICZ R,GISLER C,HENNEBERT J,et al.Use of machine learning on contact lens sensor-derived parameters for the diagnosis of primary open-angle glaucoma ［J］.Am J Ophthalmol,2018,194:46-53.
［37］　LEITE M T,ZANGWILL L M,WEINREB R N,RAO H L,ALENCAR L M,MEDEIROS F A.Structure-function relationships using the cirrus spectral domain optical coherence tomograph and standard automated perimetry ［J］.J Glaucoma,2012,21(1):49-54.
［38］　BRIGATTI L,HOFFMAN D,CAPRIOLI J.Neural networks to identify glaucoma with structural and functional measurements ［J］.Am J Ophthalmol,1996,121(5):511-521.
［39］　CHRISTOPHER M,BOWD C,BELGHITH A,GOLDBAUM M H,WEINREB R N,FAZIO M A,et al.Deep learning approaches predict glaucomatous visual field damage from oct optic nerve head en face images and retinal nerve fiber layer thickness maps ［J］.Ophthalmology,2020,127(3):346-356.
［40］　HASHIMOTO Y,ASAOKA R,KIWAKI T,SUGIURA H,ASANO S,MURATA H,et al.Deep learning model to predict vi-sual field in central 10 degrees from optical coherence tomography measurement in glaucoma ［J］.Br J Ophthalmol,2021,105(4):507-513.
［41］　DE FAUW J,LEDSAM J R,ROMERA-PAREDES B,NIKOLOV S,TOMASEV N,BLACKWELL S,et al.Clinically applicable deep learning for diagnosis and referral in retinal disease ［J］.Nat Med,2018,24(9):1342-1350.
［42］　CHOI J Y,YOO T K,SEO J G,KWAK J,UM T T,RIM T H.Multi-categorical deep learning neural network to classify retinal images:A pilot study employing small database ［J］.PLoS One,2017,12(11):e0187336.

相似文献/References:

[1]李翔 谢钊 郭红建 谢学军 路雪婧 王毅 王超.补肾活血中药对大鼠慢性高眼压模型外侧膝状体病理改变的影响[J].眼科新进展,2012,32(1):000.
[2]范虹 刘五存 蔡鸿英 赵堪兴.改良二极管激光睫状体光凝术治疗中晚期青光眼[J].眼科新进展,2012,32(4):000.
[3]王建萍 赵燕麟 马勇 朱涛 程燕 车选义 赵桂娥 王柯.噻吗洛尔和布林佐胺联合曲伏前列素治疗原发性开角型青光眼与高眼压患者的临床研究[J].眼科新进展,2012,32(5):000.
[4]彭坤 靳隽 杨玉新 许银霞 王保君 闫义涛 杨华.长期联合应用噻吗洛尔对结膜组织炎性标记物ICAM-1和HLA-DR表达的影响[J].眼科新进展,2012,32(6):000.
[5]马恩普 赵小钊 董良 刘苏冰 曾照年.Healaflow在青光眼小梁切除术中的应用[J].眼科新进展,2012,32(6):000.
[6]王勇 叶应嘉 鲍先议 周龑丽 许荣 彭婷婷 曾志富.同轴微小切口超声乳化吸出术在青光眼滤过术后白内障摘出术中的应用[J].眼科新进展,2012,32(7):000.
[7]李翔 马世勇 李娟 王毅.补肾活血中药对大鼠慢性高眼压模型视神经病理改变的影响[J].眼科新进展,2013,33(2):000.
[8]白东娥 刘伟 季建.抗青光眼药物对青光眼患者泪液胰岛素水平的影响及其与眼表改变的关系[J].眼科新进展,2013,33(6):000.
[9]马英慧 张铁民 齐建平.原发性开角型青光眼与慢性原发性闭角型青光眼视网膜神经纤维层厚度与视野缺损的关系[J].眼科新进展,2013,33(7):000.
[10]张海涛 杨玉新 毛永 丁晓丽 秦海霞 梁长华 郭英昌.青光眼与非炎症性缺血型视神经病变的傅立叶OCT扫描视神经形态学对比[J].眼科新进展,2013,33(8):000.
[11]赵金凤,吴桢泉,郑磊,等.人工智能在眼科疾病诊疗的应用现状[J].眼科新进展,2019,39(5):495.[doi:10.13389/j.cnki.rao.2019.0114]
　ZHAO Jin-Feng,WU Zhen-Quan,ZHENG Lei,et al.Application of artificial intelligence in the diagnosis and treatment of ocular diseases[J].Recent Advances in Ophthalmology,2019,39(6):495.[doi:10.13389/j.cnki.rao.2019.0114]
[12]余燕,侯银芬,吴昌凡,等.人工智能深度学习技术在常见眼病辅助诊断的应用现状和进展[J].眼科新进展,2020,40(4):396.[doi:10.13389/j.cnki.rao.2020.0092]
　YU Yan,HOU Yinfen,WU Changfan,et al.Application and progress of artificial intelligence deep learning technology in diagnosis of common eye diseases[J].Recent Advances in Ophthalmology,2020,40(6):396.[doi:10.13389/j.cnki.rao.2020.0092]

备注/Memo

备注/Memo:
湖南省临床医疗技术创新引导计划（编号：2017SK50903）;深圳市知识创新计划基础研究项目（编号：JCYJ20170307155030786）
更新日期/Last Update: 2023-06-09