[1]中国医药教育协会数字影像与智能医疗专委会,中国医药教育协会智能医学专委会.全球眼科图像公开数据库使用指南（2022）[J].眼科新进展,2022,42(12):925-932.[doi:10.13389/j.cnki.rao.2022.0190]
　Digital Imaging and Intelligent Medical Branch of China Medical Education Association,Intelligent Medical Special Committee of China Medical Education Association.Guidelines for the use of global public databases on ophthalmic images (2022)[J].Recent Advances in Ophthalmology,2022,42(12):925-932.[doi:10.13389/j.cnki.rao.2022.0190]
点击复制

全球眼科图像公开数据库使用指南（2022）/HTML
分享到：

《眼科新进展》[ISSN:1003-5141/CN:41-1105/R]

卷:
42卷
期数:
2022年12期
页码:
925-932
栏目:
述评
出版日期:
2022-12-05

文章信息/Info

Title:
Guidelines for the use of global public databases on ophthalmic images (2022)
作者:
中国医药教育协会数字影像与智能医疗专委会; 中国医药教育协会智能医学专委会
Author(s):
Digital Imaging and Intelligent Medical Branch of China Medical Education Association; Intelligent Medical Special Committee of China Medical Education Association
关键词:
眼科图像; 眼科数据库; 图像数据库; 使用指南
Keywords:
ophthalmic images;  ophthalmic databases;  image databases;  guidelines for use
分类号:
R77
DOI:
10.13389/j.cnki.rao.2022.0190
文献标志码:
A
摘要:
可公开获取的医学数据是数字健康研究的宝贵资源。目前，一些包含眼科图像的公开数据库常被用于机器学习的研究中，但如何规范高效地使用这些数据库尚无统一标准。本指南旨在筛选确定部分公开可用的眼科图像数据库，详细描述其包含的疾病类型、图像来源和成像方式。使用MEDLINE、Google搜索引擎和Google数据集搜索，确定了94个开放获取数据库，包含来自122 364名患者的507 724张图片和125段视频。该指南为眼科数据库相关研究提供了帮助与参考。同时，指南还发现数据库中不同人群和疾病群体代表性的差距越来越大。改进的元数据报告将使研究人员能够根据他们的需要访问最合适的数据库，并最大限度地发挥这些图像数据资源的作用。
Abstract:
Publicly accessible medical data are valuable for digital health research. Some public databases containing ophthalmic images are commonly used in machine learning studies, but there have been no criteria for standard and efficient use of these databases. These guidelines aim to identify some publicly available ophthalmic image databases with a detailed description of the disease types, image sources and imaging modalities. Using MEDLINE, Google’s search engine, and Google dataset search, we identified 94 open-access databases containing 507 724 images and 125 videos from 122 364 patients. These guidelines provide support and reference for ophthalmic database-related research. In addition, increasing disparities in different populations and disease groups in the databases were found. The improved metadata reports enable researchers to access the most appropriate databases as required and maximize the role of image resources.

参考文献/References:

［1］　PARIK KIM H R B,GDOWSKI A,PATT D A,HERTLER A,MERMEL C,BEKELMAN J E.Using big data and predictive analytics to determine patient risk in oncology［J］.Am Soc Clin Oncol Educ Book,2019,39:e53-e58.
［2］　WONG Z S Y,ZHOU J,ZHANG Q.Artificial intelligence for infectious disease big data analytics［J］.Infect Dis Health,2019,24(1):44-48.
［3］　KIM H E,KIM H H,HAN B K,KIM K H,HAN K,NAM H,et al.Changes in cancer detection and false-positive recall in mammography using artificial intelligence:a retrospective,multireader study［J］.Lancet Digit Health,2020,2(3):e138-e148.
［4］　ESTEVA A,KUPREL B,NOVOA R A,KO J,SWETTER S M,BLAU H M,et al.Dermatologist-level classification of skin cancer with deep neural networks［J］.Nature,2017,542(7639):115-118.
［5］　KERMANY D S,GOLDBAUM M,CAI W,VALENTIM C C S,LIANG H,BAXTER S L,et al.Identifying medical diagnoses and treatable diseases by image-based deep learning［J］.Cell,2018,172(5):1122-1131.
［6］　LIU X,FAES L,KALE A U,WAGNER S K,FU D J,BRUYNSEELS A,et al.A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging:a systematic review and meta-analysis［J］.Lancet Digit Health,2019,1(6):e271-e297.
［7］　MCKINNEY S M,SIENIEK M,GODBOLE V,GODWIN J,ANTROPOVA N,ASHRAFIAN H,et al.International evaluation of an AI system for breast cancer screening［J］.Nature,2020,577(7788):89-94.
［8］　ARCADU F,BENMANSOUR F,MAUNZ A,WILLIS J,HASKOVA Z,PRUNOTTO M.Deep learning algorithm predicts diabetic retinopathy progression in individual patients［J］.NPJ Digit Med,2019,2:92.
［9］　YIM J,CHOPRA R,SPITZ T,WINKENS J,OBIKA A,KELLY C,et al.Predicting conversion to wet age-related macular degeneration using deep learning［J］.Nat Med,2020,26(6):892-899.
［10］　MILEA D,NAJJAR R P,ZHUBO J,TING D,VASSENEIX C,XU X,et al.Artificial intelligence to detect papilledema from ocular fundus photographs［J］.N Engl J Med,2020,382(18):1687-1695.
［11］　DEFAUW 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.
［12］　TING D S W,PASQUALE L R,PENG L,CAMPBELL J P,LEE A Y,RAMAN R,et al.Artificial intelligence and deep learning in ophthalmology［J］.Br J Ophthalmol,2019,103(2):167-175.
［13］　ABRAMOFF M D,LAVIN P T,BIRCH M,SHAH N,FOLK J C.Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices［J］.NPJ Digit Med,2018,1:39.
［14］　WEN J C,LEE C S,KEANE P A,XIAO S,ROKEM A S,CHEN P P,et al.Forecasting future humphrey visual fields using deep learning［J］.PLoS One,2019,14(4):e0214875.
［15］　DECENCIRE E,ZHANG X,CAZUGUEL G,LA B,COCHENER B,TRONE C,et al.Feedback on a publicly distributed image database:the messidor database［J］.Image Analy Stereol,2014,33(3):231-234.
［16］　NIEMEIJER M, STAAL J J, GINNEKEN B V, LOOG M, ABRAMOFF M D.DRIVE:digital retinal Images for vessel extraction［DB/OL］.［2020-10-15］.https://drive.grand-challenge.org.
［17］　GULSHAN V,PENG L,CORAM M,STUMPE M C,WU D,NARAYANASWAMY A,et al.Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs［J］.JAMA,2016,316(22):2402-2410.
［18］　DECENCIRE E,CAZUGUEL G,ZHANG X,THIBAULT G,KLEIN J C,MEYER F,et al.TeleOphta:machine learning and image processing methods for teleophthalmology［J］.IRBM,2013,34(2):196-203.
［19］　BURTON M J,FAAL H B,RAMKE J,RAVILLA T,HOLLAND P,WANG N,et al.Announcing the lancet global health commission on global eye health［J］.Lanc Glob Health,2019,7(12):e1612-e1613.
［20］　Service U D.Data access policy［EB/OL］.［2022-10-15］.https://www.ukdataservice.ac.uk/get-data/data-access-policy/open-data.aspx.
［21］　MILEA D,AZMI S,REGINALD P,VERPILLAT P,FRANCOIS C.A review of accessibility of administrative healthcare databases in the Asia-Pacific region［J］.J Mark Access Health Policy,2015,3:PMID27123180.
［22］　Biobank［DB/OL］.［2022-10-15］.http://www.ukbiobank.ac.uk/scientists-3.
［23］　Diabetic Retinopathy Detection.Diabetic retinopathy detection［M/OL］.［2022-10-15］.https://www.kaggle.com/c/diabetic-retinopathy-detection:California Healthcare Foundation.
［24］　FUSEK R.MRL eye dataset［DB/OL］.［2022-10-15］.http://mrl.cs.vsb.cz/eyedataset.
［25］　SCANLON P H.The English national screening programme for diabetic retinopathy 2003-2016［J］.Acta Diabetol,2017,54(6):515-525.
［26］　RIBEIRO L,OLIVEIRA C M,NEVES C,RAMOS J D,FERREIRA H,CUNHA-VAZ J.Screening for diabetic retinopathy in the Central Region of Portugal.Added value of automated ‘disease/no disease’ grading［J］.Ophthalmologica,2015,233(2):96-103.
［27］　MASSIN P,CHABOUIS A,ERGINAY A,VIENS-BITKER C,LECLEIRE-COLLET A,MEAS T,et al.A telemedical network screening system for diabetic retinopathy in the le-de-France［J］.Diabetes Metab,2008,34(3):227-234.
［28］　KRAUSE J,GULSHAN V,RAHIMY E,KARTH P,WIDNER K,CORRADO G S,et al.Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy［J］.Ophthalmology,2018,125(8):1264-1272.
［29］　BLOG G A.Building Google dataset search and fostering an open data ecosystem［EB/OL］.［2022-10-15］.https://ai.googleblog. com/2018/09/building-google-dataset-search-and.html.
［30］　CHALAKKAL R J,ABDULLA W.Automatic segmentation of retinal vasculature:ICASSP,IEEE international conference on acoustics,speech and signal processing-proceedings［C］.New Orleans:ICASSP,2017.
［31］　XU X,DING W,WANG X,CAO R,ZHANG M,L P,et al.Smartphone-based accurate analysis of retinal vasculature towards point-of-care diagnostics［J］.Sci Rep,2016,6:34603.
［32］　GEBRU T,MORGENSTERN J,VECCHIONE B,VAUGHAN J W,WALLACH H,DAUME H,III,et al.Datasheets for datasets:Proceedings of the 5th Workshop on Fairness,Accountability,and Transparency in Machine Learning［C］.Sweden:Stockholm,2018.
［33］　HRYNASZKIEWICZ I,NORTON M L,VICKERS A J,ALTMAN D G.Preparing raw clinical data for publication:guidance for journal editors,authors,and peer reviewers［J］.BMJ,2010,340:c181.
［34］　YIM J,CHOPRA R,SPITZ T,WINKENS J,OBIKA A,KELLY C,et al.Predicting conversion to wet age-related macular degeneration using deep learning［J］.Nat Med,2020,26(6):892-899.
［35］　LARRAZABAL A J,NIETO N,PETERSON V,MILONE D H,FERRANTE E.Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis［J］.Proc Natl Acad Sci U S A,2020,117(23):12592-12594.
［36］　ADAMSON A S,SMITH A.Machine learning and health care disparities in dermatology［J］.JAMA Dermatology,2018,154(11):1247-1248.
［37］　CHEN I Y,JOSHI S,GHASSEMI M.Treating health disparities with artificial intelligence［J］.Nat Med,2020,26(1):16-17.
［38］　FLAXMAN S R,BOURNE R R A,RESNIKOFF S,ACKLAND P,BRAITHWAITE T,CICINELLI M V,et al.Global causes of blindness and distance vision impairment 1990-2020:a systematic review and meta-analysis［J］.Lancet Glob Health,2017,5(12):e1221-e1234.

备注/Memo

备注/Memo:
国家自然科学基金资助（编号：82160195）；江西省双千计划科技创新高端人才项目（2022）；江西省重大研发专项接榜挂帅计划（编号：2022103；20181BBG70004；20203BBG73059）；江西省杰出青年基金（编号：20192BCBL23020）
更新日期/Last Update: 2022-12-05