[1]《人工智能在OCTA图像分析和眼部疾病诊断中的应用指南(0)》专家组,国际转化医学会眼科专业委员会,中国医药教育协会眼科影像与智能医疗分会.人工智能在OCTA图像分析和眼部疾病诊断中的应用指南(2024)[J].眼科新进展,2024,44(5):337-345.[doi:10.13389/j.cnki.rao.2024.0066]
 Expert Workgroup of Guidelines for Application of Artificial Intelligence in OCTA Image Analysis and Ocular Disease Diagnosis (0),Ophthalmic Imaging and Intelligent Medicine Branch of Chinese Medicine Education Association,Ophthalmology Committee of International Association of Translational Medicine.Guidelines for the application of artificial intelligence in optical coherence tomography angiography image analysis and ocular disease diagnosis (2024)[J].Recent Advances in Ophthalmology,2024,44(5):337-345.[doi:10.13389/j.cnki.rao.2024.0066]
点击复制

人工智能在OCTA图像分析和眼部疾病诊断中的应用指南(2024)/HTML
分享到:

《眼科新进展》[ISSN:1003-5141/CN:41-1105/R]

卷:
44卷
期数:
2024年5期
页码:
337-345
栏目:
述评
出版日期:
2024-04-30

文章信息/Info

Title:
Guidelines for the application of artificial intelligence in optical coherence tomography angiography image analysis and ocular disease diagnosis (2024)
作者:
《人工智能在OCTA图像分析和眼部疾病诊断中的应用指南(2024)》专家组国际转化医学会眼科专业委员会中国医药教育协会眼科影像与智能医疗分会
Author(s):
Expert Workgroup of Guidelines for Application of Artificial Intelligence in OCTA Image Analysis and Ocular Disease Diagnosis (2024)Ophthalmic Imaging and Intelligent Medicine Branch of Chinese Medicine Education AssociationOphthalmology Committee of International Association of Translational Medicine
关键词:
光学相干断层扫描血管成像人工智能图像分析疾病诊断
Keywords:
optical coherence tomography angiography artificial intelligence image analysis disease diagnosis
分类号:
R770.4
DOI:
10.13389/j.cnki.rao.2024.0066
文献标志码:
A
摘要:
光学相干断层扫描血管成像(OCTA)是一种无创成像技术,可提供三维、信息丰富的血管图像。大量研究表明,OCTA技术在影像生物标志物量化、诊断和监测方面具有独特的优势,因此在实验及临床研究中得到了迅速的应用。图像分析工具可快速、准确地量化OCTA的血管和病理特征,从而大大提高了OCTA成像的价值。近年来,人工智能(AI)已成为最强大的图像分析方法,特别是基于深度学习的图像分析可提供各种情况下的精确测量,包括不同的疾病和眼部区域。在此,中国医药教育协会眼科影像与智能医疗分会和国际转化医学会眼科专业委员会组织专家总结了国内外AI在OCTA图像分析和疾病诊断中的应用,其中包括脉络膜新生血管等病变的准确检测、视网膜灌注的精确量化以及可靠的疾病诊断,并分析目前面临的挑战和发展方向,经过多轮讨论和修改,形成了AI在OCTA图像分析和眼部疾病诊断中的应用指南,该指南旨在为临床提供新的见解和参考。
Abstract:
Optical coherence tomography angiography (OCTA) is a non-invasive imaging technique that provides three-dimensional, informative vascular images. Numerous studies have shown that OCTA technology has unique advantages in biomarker quantification, diagnosis and monitoring, and has therefore been rapidly applied in experiments and clinical studies. Image analysis tools can quickly and accurately quantify vascular and pathological features, greatly improving the value of OCTA imaging. In recent years, artificial intelligence (AI) has become the most powerful image analysis method, especially deep learning-based image analysis, which can provide accurate measurements in various situations, including different diseases and eye regions. The Ophthalmic Imaging and Intelligent Medicine Branch of Chinese Medicine Education Association and the Ophthalmology Committee of International Association of Translational Medicine designated experts to summarize the application of AI in OCTA image analysis and disease diagnosis at home and abroad, including accurate detection of choroidal neovascularization and other lesions, accurate quantification of retinal perfusion, and reliable disease diagnosis. They also analyzed the current challenges and development directions. After multiple rounds of discussion and revisions, they drafted the guidelines for the application of AI in OCTA image analysis and ocular disease diagnosis, aiming to provide new insights and references for clinical practice.

参考文献/References:

[1] 王烽,梁栋.光学相干断层扫描血管成像在神经退行性疾病中的应用进展[J].眼科学报,2021,36(10):804-809.
WANG F,LIANG D.Advances in the application of optical coherence tomography angiography in neurodegenerative disorders[J].Eye Sci,2021,36(10):804-809.
[2] HOLMEN I C,KONDA S M,PAK J W,MCDANIEL K W,BLODI B,STEPIEN K E,et al.Prevalence and severity of artifacts in optical coherence tomographic angiograms[J].JAMA Ophthalmol,2020,138(2):119-126.
[3] LITJENS G,KOOI T,BEJNORDI B E,SETIO A A A,CIOMPI F,GHAFOORIAN M,et al.A survey on deep learning in medical image analysis[J].Med Image Anal,2017,42:60-88.
[4] HORMEL T T,HWANG T S,BAILEY S T,WILSON D J,HUANG D,JIA Y.Artificial intelligence in OCT angiography[J].Prog Retin Eye Res,2021,85:100965.
[5] 杨卫华,邵毅,许言午.眼科人工智能临床研究评价指南(2023)[J].国际眼科杂志,2023,23(7):1064-1071.
YANG W H,SHAO Y,XU Y W.Guidelines on clinical research evaluation of artificial intelligence in ophthalmology (2023)[J].Int Eye Sci,2023,23(7):1064-1071.
[6] ELADAWI N,ELMOGY M,KHALIFA F,GHAZAL M,GHAZI N,ABOELFETOUH A,et al.Early diabetic retinopathy diagnosis based on local retinal blood vessel analysis in optical coherence tomography angiography (OCTA) images[J].Med Phys,2018,45(10):4582-4599.
[7] 邵毅,陈蔚,杨卫华,谭钢,迟玮,陈新建,等.人工智能在干眼临床诊断中的应用专家共识(2023)[J].眼科新进展,2023,43(4):253-259.
SHAO Y,CHEN W,YANG W H,TAN G,CHI W,CHEN X J,et al.Expert consensus on clinical application of artificial Intelligence in Dry Eyes(2023)[J].Rec Adv Ophthalmol,2023,43(4):253-259.
[8] WEI X,HORMEL T T,GUO Y,HWANG T S,JIA Y.High-resolution wide-field OCT angiography with a self-navigation method to correct microsaccades and blinks[J].Biomed Opt Express,2020,11(6):3234-3245.
[9] HOSSBACH J,HUSVOGT L,KRAUS M F,FUJIMOTO J G,MAIER A K.Deep OCT Angiography Image Generation for Motion Artifact Suppression[J].Bildverarb Med,2020,2020:248-253.
[10] MARIAMPILLAI A,LEUNG M K K,JARVI M,STANDISH B A,LEE K,WILSON B C,et al.Optimized speckle variance OCT imaging of microvasculature[J].Opt Lett,2010,35(8):1257-1259.
[11] CAMINO A,ZHANG M,LIU L,WANG J,JIA Y,HUANG D.Enhanced quantification of retinal perfusion by improved discrimination of blood flow from bulk motion signal in OCTA[J].Transl Vis Sci Technol,2018,7(6):20.
[12] CAMINO A,JIA Y,YU J,WANG J,LIU L,HUANG D.Automated detection of shadow artifacts in optical coherence tomography angiography[J].Biomed Opt Express,2019,10(3):1514-1531.
[13] GUO Y,HORMEL T T,XIONG H,WANG B,CAMINO A,WANG J,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,2019,10(7):3257-3268.
[14] AL-SHEIKH M,TEPELUS T C,NAZIKYAN T,SADDA S R.Repeatability of automated vessel density measurements using optical coherence tomography angiography[J].Br J Ophthalmol,2017,101(4):449-452.
[15] 傅娆,刘大川.光学相干断层扫描血管成像在糖尿病性视网膜病变临床应用研究进展[J].国际眼科杂志,2021,21(10):1727-1731.
FU R,LIU D C.Research progress of clinical application of optical coherence tomography angiography in diabetic retinopathy[J].Int Eye Sci,2021,21(10):1727-1731.
[16] 黄薇,蒋沁,曹国凡.光学相干断层扫描血管成像技术在青光眼诊治中的研究进展[J].国际眼科杂志,2017,17(4):665-668.
HUANG W,JIANG Q,CAO G F.Development of optical coherence tomography angiography in the diagnosis and treatment of glaucoma[J].Int Eye Sci,2017,17(4):665-668.
[17] LIU X,BI L,XU Y,FENG D,KIM J,XU X.Robust deep learning method for choroidal vessel segmentation on swept source optical coherence tomography images[J].Biomed Opt Express,2019,10(4):1601-1612.
[18] GAO M,GUO Y,HORMEL T T,SUN J,HWANG T S,JIA Y.Reconstruction of high-resolution 6 × 6-mm OCT angiograms using deep learning[J].Biomed Opt Express,2020,11(7):3585-3600.
[19] LI M,CHEN Y,JI Z,XIE K,YUAN S,CHEN Q,et al.Image projection network:3D to 2D image segmentation in OCTA images[J].IEEE Trans Med Imaging,2020,39(11):3343-3354.
[20] CHEN L,ZHANG X,WEN F.Venous beading in two or more quadrants might not be a sensitive grading criterion for severe nonproliferative diabetic retinopathy[J].Graefes Arch Clin Exp Ophthalmol,2018,256(6):1059-1065.
[21] ALAM M,TOSLAK D,LIM J I,YAO X.Color fundus image guided artery-vein differentiation in optical coherence tomography angiography[J].Invest Ophthalmol Vis Sci,2018,59(12):4953-4962.
[22] ALAM M,LE D,SON T,LIM J I,YAO X.AV-Net:deep learning for fully automated artery-vein classification in optical coherence tomography angiography[J].Biomed Opt Express,2020,11(9):5249-5257.
[23] NIKI T,MURAOKA K,SHIMIZU K.Distribution of capillary nonperfusion in early-stage diabetic retinopathy[J].Ophthalmology,1984,91(12):1431-1439.
[24] SCHOTTENHAMML J,MOULT E M,PLONER S,LEE B,NOVAIS E A,COLE E,et al.An automatic,intercapillary area-based algorithm for quantifying diabetes-related capillary dropout using optical coherence tomography angiography[J].Retina,2016,36 (Suppl 1):S93-S101.
[25] NESPER P L,SOETIKNO B T,TREISTER A D,FAWZI A A.Volume-rendered projection-resolved OCT angiography:3D lesion complexity is associated with therapy response in wet age-related macular degeneration[J].Invest Ophthalmol Vis Sci,2018,59(5):1944-1952.
[26] GUO Y,HORMEL T T,XIONG H,WANG B,CAMINO A,WANG J,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,2019,10(7):3257-3268.
[27] WANG J,HORMEL T T,YOU Q,GUO Y,WANG X,CHEN L,et al.Robust non-perfusion area detection in three retinal plexuses using convolutional neural network in OCT angiography[J].Biomed Opt Express,2019,11(1):330-345.
[28] ANTONETTI D A,KLEIN R,GARDNER T W.Diabetic retinopathy[J].N Engl J Med,2012,366(13):1227-1239.
[29] MITCHELL P,LIEW G,GOPINATH B,WONG T Y.Age-related macular degeneration[J].Lancet,2018,392(10153):1147-1159.
[30] LIU L,GAO S S,BAILEY S T,HUANG D,LI D,JIA Y.Automated choroidal neovascularization detection algorithm for optical coherence tomography angiography[J].Biomed Opt Express,2015,6(9):3564-3576.
[31] WANG J,HORMEL T T,GAO L,ZANG P,GUO Y,WANG X,et al.Automated diagnosis and segmentation of choroidal neovascularization in OCT angiography using deep learning[J].Biomed Opt Express,2020,11(2):927-944.
[32] GOPINATH K,SIVASWAMY J.Segmentation of retinal cysts from optical coherence tomography volumes via selective enhancement[J].IEEE J Biomed Health Inform,2019,23(1):273-282.
[33] GUO Y,HORMEL T T,XIONG H,WANG J,HWANG T S,JIA Y.Automated segmentation of retinal fluid volumes from structural and angiographic optical coherence tomography using deep learning[J].Transl Vis Sci Technol,2020,9(2):54.
[34] WANG B,CAMINO A,PI S,GUO Y,WANG J,HUANG D,et al.Three-dimensional structural and angiographic evaluation of foveal ischemia in diabetic retinopathy:method and validation[J].Biomed Opt Express,2019,10(7):3522-3532.
[35] LU Y,SIMONETT J M,WANG J,ZHANG M,HWANG T,HAGAG A M,et al.Evaluation of automatically quantified foveal avascular zone metrics for diagnosis of diabetic retinopathy using optical coherence tomography angiography[J].Invest Ophthalmol Vis Sci,2018,59(6):2212-2221.
[36] DONGYE C,ZHANG M,HWANG T S,WANG J,GAO S S,LIU L,et al.Automated detection of dilated capillaries on optical coherence tomography angiography[J].Biomed Opt Express,2017,8(2):1101-1109.
[37] WANG J,ZHANG M,HWANG T S,BAILEY S T,HUANG D,WILSON D J,et al.Reflectance-based projection-resolved optical coherence tomography angiography[J].Biomed Opt Express,2017,8(3):1536-1548.
[38] GAO E,SHI F,ZHU W,JIN C,SUN M,CHEN H,et al.Graph search:active appearance model based automated segmentation of retinal layers for optic nerve head centered OCT images[J].Med Imaging,2017,10133:101331Q.
[39] SANDHU H S,ELMOGY M,TAHER SHARAFELDEEN A,ELSHARKAWY M,EL-ADAWY N,ELTANBOLY A,et al.Automated diagnosis of diabetic retinopathy using clinical biomarkers,optical coherence tomography,and optical coherence tomography angiography[J].Am J Ophthalmol,2020,216:201-206.
[40] XIAO P,MA K,YE X,WANG G,DUAN Z,HUANG Y,et al.Classification of Vogt-Koyanagi-Harada disease using feature selection and classification based on wide-field swept-source optical coherence tomography angiography[J].Front Bioeng Biotechnol,2023,11:1086347.
[41] 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.
[42] RUSSAKOFF D B,LAMIN A,OAKLEY J D,DUBIS A M,SIVAPRASAD S.Deep learning for prediction of AMD progression:a pilot study[J].Invest Ophthalmol Vis Sci,2019,60(2):712-722.
[43] LE D,ALAM M,YAO C K,LIM J I,HSIEH Y T,CHAN R V P,et al.Transfer learning for automated OCTA detection of diabetic retinopathy[J].Transl Vis Sci Technol,2020,9(2):35.
[44] HEISLER M,KARST S,LO J,MAMMO Z,YU T,WARNER S,et al.Ensemble deep learning for diabetic retinopathy detection using optical coherence tomography angiography[J].Transl Vis Sci Technol,2020,9(2):20.

相似文献/References:

[1]董秀芬,钟华.Angio-OCT在眼科疾病临床应用中研究进展[J].眼科新进展,2016,36(7):697.[doi:10.13389/j.cnki.rao.2016.0185]
 DONG Xiu-Fen,ZHONG Hua.Application of Angio-OCT in ophthalmic diseases[J].Recent Advances in Ophthalmology,2016,36(5):697.[doi:10.13389/j.cnki.rao.2016.0185]
[2]刘青,艾明.光学相干断层扫描血管成像(OCTA)和荧光素血管造影(FFA)对比观察增生型糖尿病视网膜病变(PDR)[J].眼科新进展,2017,37(1):052.[doi:10.13389/j.cnki.rao.2017.0014]
 LIU Qing,AI Ming.Characteristics of proliferative diabetic retinopathy observed by optical coherence tomography angiography and fundus fluorescein angiography[J].Recent Advances in Ophthalmology,2017,37(5):052.[doi:10.13389/j.cnki.rao.2017.0014]
[3]仲妍,车慧欣.光学相干断层扫描血管成像(OCTA)在原发性青光眼患者中的检测价值[J].眼科新进展,2018,38(4):352.[doi:10.13389/j.cnki.rao.2018.0082]
 ZHONG Yan,CHE Hui-Xin.Detective values of optical coherence tomography angiographyfor primary glaucoma[J].Recent Advances in Ophthalmology,2018,38(5):352.[doi:10.13389/j.cnki.rao.2018.0082]
[4]冷云霞,张柳,张蒙,等.早产儿视网膜病变黄斑中心视网膜微血管形态特征:基于光学相干断层扫描血管成像(OCTA)的观察[J].眼科新进展,2018,38(4):357.[doi:10.13389/j.cnki.rao.2018.0083]
 LENG Yun-Xia,ZHANG Liu,ZHANG Meng,et al.Observation of central macular retinal microvascular network morphology of retinopathy of prematurity by optical coherence tomography angiography[J].Recent Advances in Ophthalmology,2018,38(5):357.[doi:10.13389/j.cnki.rao.2018.0083]
[5]焦亚,付碧波,叶波,等.视网膜脱离复位术后黄斑区血流密度:基于光学相干断层扫描血管成像(OCTA)的观察[J].眼科新进展,2018,38(4):373.[doi:10.13389/j.cnki.rao.2018.0087]
 JIAO Ya,FU Bi-Bo,YE Bo,et al.Clinical observation of optical coherence tomography angiography in the macular vascular density after repair of retinal detachment[J].Recent Advances in Ophthalmology,2018,38(5):373.[doi:10.13389/j.cnki.rao.2018.0087]
[6]郑丹,庞东渤.应用光学相干断层扫描血管成像(OCTA)评估糖尿病患者早期黄斑区视网膜微循环[J].眼科新进展,2018,38(6):548.[doi:10.13389/j.cnki.rao.2018.0128]
 ZHENG Dan,PANG Dong-Bo.Evaluation of early macular retinal microcirculation in diabetic patients using optical coherence tomography angiography[J].Recent Advances in Ophthalmology,2018,38(5):548.[doi:10.13389/j.cnki.rao.2018.0128]
[7]袁晴,闵幼兰,邵毅.光学相干断层扫描血管成像技术在神经眼科疾病中的应用[J].眼科新进展,2018,38(8):794.[doi:10.13389/j.cnki.rao.2018.0188]
 YUAN Qing,MIN You-Lan,SHAO Yi.Application of optical coherence tomography angiography in neuro-ophthalmological diseases[J].Recent Advances in Ophthalmology,2018,38(5):794.[doi:10.13389/j.cnki.rao.2018.0188]
[8]张晓培,曹国凡,蒋沁.光学相干断层扫描血管成像(OCTA)对早期原发性开角型青光眼的诊断能力[J].眼科新进展,2018,38(9):847.[doi:10.13389/j.cnki.rao.2018.0200]
 ZHANG Xiao-Pei,CAO Guo-Fan,JIANG Qin.Discriminant function of optical coherence tomography angiography to determine early primary open angle glaucoma[J].Recent Advances in Ophthalmology,2018,38(5):847.[doi:10.13389/j.cnki.rao.2018.0200]
[9]孙姣,王佳琳,王艳玲,等.眼部血管密度测量及其临床意义研究进展[J].眼科新进展,2018,38(11):1089.[doi:10.13389/j.cnki.rao.2018.0257]
 SUN Jiao,WANG Jia-Lin,WANG Yan-Ling,et al.Research progress of vessel density in ocular diseases[J].Recent Advances in Ophthalmology,2018,38(5):1089.[doi:10.13389/j.cnki.rao.2018.0257]
[10]吕湘云,艾明.光学相干断层扫描血管成像(OCTA)在黄斑疾病中的应用进展[J].眼科新进展,2019,39(1):094.[doi:10.13389/j.cnki.rao.2019.0022]
 LV Xiang-Yun,AI Ming.Research advance in clinical application of optical coherence tomography angiography in macular diseases[J].Recent Advances in Ophthalmology,2019,39(5):094.[doi:10.13389/j.cnki.rao.2019.0022]

备注/Memo

备注/Memo:
国家自然科学基金(编号:82160195);江西省双千计划科技创新高端领军人才项目(编号:jxsq2023201036);江西省重大(重点)研发专项计划(编号:20223BBH80014)
注:本指南的国际实践指南注册号为 PREPARE-2023CN663(http://www.guidelines-redistry.cn/)。
更新日期/Last Update: 2024-05-05