The standardized design and application guidelines:a primary-oriented artificial intelligence screening system of the lesion sign in the macular region based on fundus color photography_Chinese Journal of Ocular Fundus Diseases

Authors：

 Ocular Fundus Diseases Group of Chinese Ophthalmological Society ,  Expert Group for Artificial Intelligence Research, Development, and Application

Corresponding author: Li Xiaoxin, Email: dr_lixiaoxin@163.com; Zhang Ming, Email: zhangmingscu@126.com; Xu Yangwu, Email: ywxu@ieee.org;

Corresponding?author：

Keywords：

Guidebooks; Artificial intelligence; Macula lutea; Fundus lesions; Screening

DOI：

10.3760/cma.j.cn511434-20220616-00364

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

With the popularity and development of artificial intelligence (AI), disease screening systems based on AI algorithms are gradually emerging in the medical field. Such systems can be used for primary screening of diseases to relieve the pressure on primary health care. In recent years, AI algorithms have demonstrated good performance in the analysis and identification of lesion signs in the macular region of fundus color photography, and a screening system for fundus lesion signs applicable to primary screening is bound to emerge in the future. Therefore, to standardize the design and clinical application of the macular region lesion sign screening systems based on AI algorithms, the Ocular Fundus Diseases Group of Chinese Ophthalmological Society, in collaboration with relevant experts, has developed this guideline after investigating issues, discussing production evidence, and holding guideline workshops. This guideline aims to establish uniform standards for the definition of the macular region and lesion signs, AI adoption scenarios, algorithm model construction, datasets establishment and labeling, architecture and functions design, and image data acquisition for the screening system to guide the implementation of the screening work.

Citation： Ocular Fundus Diseases Group of Chinese Ophthalmological Society, Expert Group for Artificial Intelligence Research, Development, and Application. The standardized design and application guidelines:a primary-oriented artificial intelligence screening system of the lesion sign in the macular region based on fundus color photography. Chinese Journal of Ocular Fundus Diseases, 2022, 38(9): 711-728. doi: 10.3760/cma.j.cn511434-20220616-00364 Copy

1.	陳浩宇. 糖尿病視網膜病變篩查手冊診斷和處理(第2版)[M]. 北京: 人民衛生出版社, 2016: 10-12.Chen HY. Handbook of retinal screening in diabetes diagnosis & management (2 nd ed)[M]. Beijing: People' Medical Publishing House, 2016: 10-12.
2.	沙文茹. 《中國眼健康白皮書》發布: 致盲性眼病有效遏制[J]. 中國醫藥科學, 2020, 10(13): 3. DOI: 10.3969/j.issn.2095-0616.2020.13.002.Sha WR. “China Eye Health White Paper” released: effectively inhibition of blinding eye diseases[J]. China Medicine and Pharmacy, 2020, 10(13): 3. DOI: 10.3969/j.issn.2095-0616.2020.13.002.
3.	Balyen L, Peto T. Promising artificial intelligence-machine learning-deep learning algorithms in ophthalmology[J]. Asia Pac J Ophthalmol (Phila), 2019, 8(3): 264-272. DOI: 10.22608/APO.2018479.
4.	Orlando JI, Fu H, Breda JB, et al. Refuge challenge: a unified framework for evaluating automated methods for glaucoma assessment from fundus photographs[J/OL]. Med Image Anal, 2020, 59: 101570[2019-10-08].　https://pubmed.ncbi.nlm.nih.gov/31630011/. DOI: 10.1016/j.media.2019.101570.
5.	吳樂正, 林順潮. 臨床眼黃斑病學[M]. 北京: 北京科學技術出版社, 2007: 29-104.Wu LZ, Lin SC. Clinical maculopathy[M]. Beijing: Beijing Science and Technology Publishing, 2007: 29-104.
6.	Esteva A, Kuprel B, Novoa RA, et al. Correction: corrigendum: dermatologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017, 546(7660): 686. DOI: 10.1038/nature22985.
7.	Ehteshami Bejnordi B, Veta M, Johannes van Diest P, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer[J]. JAMA, 2017, 318(22): 2199-2210. DOI: 10.1001/jama.2017.14585.
8.	Gargeya R, Leng T. Automated identification of diabetic retinopathy using deep learning[J]. Ophthalmology, 2017, 124(7): 962-969. DOI: 10.1016/j.ophtha.2017.02.008.
9.	中華醫學會眼科學分會青光眼學組, 中國醫學裝備協會眼科人工智能學組. 中國基于眼底照相的人工智能青光眼輔助篩查系統規范化設計及應用指南(2020年)[J]. 中華眼科雜志, 2020, 56(6): 423-432. DOI: 10.3760/cma.j.cn112142-20200102-00003.Chinese Medical Association Ophthalmology Branch Glaucoma Group, China Medical Equipment Association Ophthalmology Artificial Intelligence Group. Guidelines for standardized design and application of artificial intelligence glaucoma auxiliary screening system based on fundus photography in China (2020)[J]. Chin J Ophthalmol, 2020, 56(6): 423-432. DOI: 10.3760/cma.j.cn112142-20200102-00003.
10.	袁進, 雷博, 張明, 等. 基于眼底照相的糖尿病視網膜病變人工智能篩查系統應用指南[J]. 中華實驗眼科雜志, 2019, 37(8): 593-598. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.001.Yuan J, Lei B, Zhang M, et al. Guidelines for artificial intelligent diabetic retinopathy screening system based on fundus photography[J]. Chin J Exp Ophthalmol, 2019, 37(8): 593-598. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.001.
11.	中國食品藥品檢定研究院. 人工智能醫療器械質量要求和評價第1部分: 術語. YY/T 1833.1-2022[S/OL]. (2020-07-03)[2022-06-16]. http://www.cnpharm.com/upload/resources/file/2020/07/03/54879.pdf.National Institutes for Food and Drug Control. Artificial intelligence medical device—Quality requirements and evaluation—Part 1: Terminology. YY/T 1833.1-2022[S/OL]. (2020-07-03)[2022-06-16]. http://www.cnpharm.com/upload/resources/file/2020/07/03/54879.pdf.
12.	中國食品藥品檢定研究院. 人工智能醫療器械質量要求和評價第2部分: 數據集通用要求. YY/T 1833.2-2022[S/OL]. (2020-07-03)[2022-06-16]. https://www.nifdc.org.cn/directory/web/nifdc/infoAttach/38b8b027-8b43-43c1-b744-c0ac891b5ec8.pdf.National Institutes for Food and Drug Control. Artificial intelligence medical device—Quality requirements and evaluation—Part 2: General requirements for datasets. YY/T 1833.2-2022[S/OL]. (2020-07-03) [2022-06-16]. https://www.nifdc.org.cn/directory/web/nifdc/infoAttach/38b8b027-8b43-43c1-b744-c0ac891b5ec8.pdf.
13.	中國食品藥品檢定研究院. 人工智能醫療器械質量要求和評價第3部分: 數據標注通用要求(征求意見稿)[S/OL](2021-06-04)[2022-06-16]. https://www.nifdc.org.cn/directory/web/nifdc/images/2021080213295600571.pdf.National Institutes for Food and Drug Control. Artificial intelligence medical device—Quality requirements and evaluation—Part 2: General requirements for data annotation (draft for comments)[S/OL]. (2021-06-04)[2022-06-16]. https://www.nifdc.org.cn/directory/web/nifdc/images/2021080213295600571.pdf.
14.	中國質量檢驗協會. 眼底彩照標注與質量控制規范(T/CAQI 166-2020)[J]. 中華實驗眼科雜志, 2021, 39(9): 761-768. DOI: 10.3760/cma.j.cn115989-20210106-00013.China Association for Quality Inspection. Annotation and quality control specifications for fundus color photographs (T/CAQI 166-2020)[J]. Chin J Exp Ophthalmol, 2021, 39(9): 761-768. DOI: 10.3760/cma.j.cn115989-20210106-00013.
15.	Davis MD, Gangnon RE, Lee LY, et al. The age-related eye disease study severity scale for age-related macular degeneration: AREDS report no. 17[J]. Arch Ophthalmol, 2005, 123(11): 1484-1498. DOI: 10.1001/archopht.123.11.1484.
16.	Britton G, Liaaenjensen S, Hanspeter P. Carotenoids Volume 5: nutrition and health[J]. Carotenoids, 2009, 24(10): 497-522.
17.	美國眼科學會, 趙家良. 眼科臨床指南[M]. 北京: 人民衛生出版社, 2013: 57-59.American Academy of Ophthalmology, Zhao JL. Preferred practice pattern[M]. Beijing: People' Medical Publishing House, 2013: 57-59.
18.	張承芬. 眼底病學(第2版)[M]. 北京: 人民衛生出版社, 2010: 397-398.Zhang CF. Diseases of ocular fundus (2 nd ed)[M]. Beijing: People' Medical Publishing House, 2010: 397-398.
19.	楊依柳, 楊婷婷, 陸方, 等. 新生血管性老年性黃斑變性亞型報告的國際新命名專家共識解讀[J]. 中華眼底病雜志, 2022, 38(2): 99-107. DOI: 10.3760/cma.j.cn511434-20220128-00055.Yang YL, Yang TT, Lu F, et al. Brief interpretation of the consensus nomenclature for reporting neovascular age-related macular degeneration data[J]. Chin J Ocul Fundus Dis, 2022, 38(2): 99-107. DOI: 10.3760/cma.j.cn511434-20220128-00055.
20.	中華醫學會眼科學分會眼底病學組. 中國老年性黃斑變性臨床診斷治療路徑[J]. 中華眼底病雜志, 2013, 29(4): 343-355. DOI: 10.3760/cma.j.issn.1005-1015.2013.04.002.Fundus Disease Group of Chinese Medical Association Ophthalmology Branch. Clinical pathway of age-related macular degeneration in China[J]. Chin J Ocul Fundus Dis, 2013, 29(4): 343-355. DOI: 10.3760/cma.j.issn.1005-1015.2013.04.002.
21.	文峰, 張雄澤. 提高對視網膜出血的分類及臨床意義的認識[J]. 眼科, 2009, 18(4): 221-224.Wen F, Zhang XZ. Classification and clinical significance of retinal hemorrhage[J]. Ophthalmol CHN, 2009, 18(4): 221-224.
22.	Sarks J, Tang K, Killingsworth M, et al. Development of atrophy of the retinal pigment epithelium around disciform scars[J]. Br J Ophthalmol, 2006, 90(4): 442-446. DOI: 10.1136/bjo.2005.083022.
23.	Gass JD. Reappraisal of biomicroscopic classification of stages of development of a macular hole[J]. Am J Ophthalmol, 1995, 119(6): 752-759. DOI: 10.1016/s0002-9394(14)72781-3.
24.	張惠蓉, 王薇. 特發性黃斑視網膜前膜[J]. 中國實用眼科雜志, 1997, 15(10): 4.Zhang HR, Wang W. Idiopathic preretinal macular membrane[J]. Chin J Pract Ophthalmol, 1997, 15(10): 4.
25.	Early treatment diabetic retinopathy study design and baseline patient characteristics: ETDRS report number 7[J]. Ophthalmology, 1991, 98(5): 741-756. DOI: 10.1016/s0161-6420(13)38009-9.
26.	嚴密. 黃斑囊樣水腫[J]. 中華眼底病雜志, 2002, 18(3): 234-235. DOI: 3760/j. issn: 1005-1015.2002. 03.035.Yan M. Cystoid macular edema[J]. Chin J Ocul Fundus Dis, 2002, 18(3): 234-235. DOI: 10.3760/j.issn:1005-1015.2002.03.035.
27.	Sigler EJ, Randolph JC, Kiernan DF. Longitudinal analysis of the structural pattern of pseudophakic cystoid macular edema using multimodal imaging[J]. Graefe's Arch Clin Exp Ophthalmol, 2016, 254(1): 43-51. DOI: 10.1007/s00417-015-3000-8.
28.	Brinton DA, Wilkinson CP. 視網膜脫離: 原理與實踐(第3版)[M]. 馬凱, 楊慶松, 徐軍, 譯. 2版. 北京: 人民衛生出版社, 2011: 65-67.Brinton DA, Wilkinson CP. Retinal detachment: principles and practice (3rd ed)[M]. Ma K, Yang QS, Xu J, translation. 2nd ed. Beijing: People' Medical Publishing House, 2011: 65-67.
29.	Zayit-Soudry S, Moroz I, Loewenstein A. Retinal pigment epithelial detachment[J]. Surv Ophthalmol, 2007, 52(3): 227-243. DOI: 10.1016/j.survophthal.2007.02.008.
30.	Madjarov G, Kocev D, Gjorgjevikj D, et al. An extensive experimental comparison of methods for multi-label learning[J]. Pattern Recogn, 2012, 45(9): 3084-3104. DOI: 10.1016/j.patcog.2012.03.004.
31.	Landis JR, Koch GG. The measurement of observer agreement for categorical data[J]. Biometrics, 1977, 33(1): 159-174. DOI: 10.2307/2529310.
32.	Liu L, Ouyang W, Wang X, et al. Deep learning for generic object detection: a survey[J]. Int J Comput Vision, 2020, 128(2): 261-318. DOI: 10.1007/s11263-019-01247-4.
33.	Li T, Bo W, Hu C, et al. Applications of deep learning in fundus images: a review[J/OL]. Med Image Anal, 2021, 69: 101971[2021-01-20].https://pubmed.ncbi.nlm.nih.gov/33524824/. DOI: 10.1016/j.media.2021.101971.
34.	Zhang YJ. A survey on evaluation methods for image segmentation[J]. Pattern Recogn, 1996, 29(8): 1335-1346. DOI: 10.1016/0031-3203(95)00169-7.
35.	李建軍, 徐亮, 彭曉燕, 等. 遠程眼科單張眼底像質量標準(征求意見稿)[J]. 眼科, 2015(1): 11-12. DOI: 10.13281/j.cnki.issn.1004-4469.2015.01.005.Li JJ, Xu L, Peng XY, et al. Quality standard for single fundus images in teleophthalmology (draft for comments)[J]. Ophthalmol CHN, 2015(1): 11-12. DOI: 10.13281/j.cnki.issn.1004-4469.2015.01.005.
36.	中華醫學會眼科學分會眼底病學組, 中國醫師協會眼科醫師分會眼底病專業委員會. 我國糖尿病視網膜病變篩查的圖像采集及閱片指南(2017年)[J]. 中華眼科雜志, 2017, 53(12): 890-896. DOI: 10.3760/cma.j.issn.0412-4081.2017.12.003.Fundus Disease Group of Ophthalmology Branch of Chinese Medical Association, Fundus Disease Professional Committee of Ophthalmologist Branch of Chinese Medical Doctor Association. Guidelines for image acquisition and reading of diabetic retinopathy screening in my country (2017)[J]. Chin J Ophthalmol, 2017, 53(12): 890-896. DOI: 10.3760/cma.j.issn.0412-4081.2017.12.003.
37.	周志華. 機器學習[M]. 北京: 清華大學出版社, 2016: 25.Zhou ZH. Machine learning[M]. Beijing: Tsinghua University Press, 2016: 25.
38.	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, 2016, 316(22): 2402-2410. DOI: 10.1001/jama.2016.17216.
39.	國家藥品監督管理局醫療器械技術審評中心. 人工智能醫療器械注冊審查指導原則 [EB/OL]. (2022-03-09)[2022-06-16]. https://www.cmde.org.cn/flfg/zdyz/zdyzwbk/20220309091014461.html.Center for Medical Device Evalution. NMPA. Guidelines for the registration review of artificial intelligence medical devices[EB/OL]. (2022-03-09)[2022-06-16]. https://www.cmde.org.cn/flfg/zdyz/zdyzwbk/20220309091014461.html.
40.	邵志強. 抽樣調查中樣本容量的確定方法[J]. 統計與決策, 2012, 22: 12-14. DOI: 10.13546/j.cnki.tjyjc.2012.22.002.Shao ZQ. The method of determining sample size in a sampling survey [J]. Statistics & Decision. 2012, 22: 12-14. DOI: 10.13546/j.cnki.tjyjc.2012.22.002.
41.	國家食品藥品監督管理總局. 醫療器械臨床試驗質量管理規范[EB/OL]. (2021-09-28)[2022-06-16]. https://www.nmpa.gov.cn/xxgk/fgwj/bmgzh/20160323141701747.html?type=pc&m=.National Medical Products Administration. Practice for quality management of clinical trials of medical devices[EB/OL]. (2021-09-28)[2022-06-16].https://www.nmpa.gov.cn/xxgk/fgwj/bmgzh/20160323141701747.html?type=pc&m=.
42.	國家藥品監督管理局醫療器械技術審評中心. 深度學習輔助決策醫療器械軟件審評要點及相關說明[EB/OL]. (2021-09-28)[2022-06-16]. https://www.cmde.org.cn/xwdt/zxyw/20190628151300923.html.Center for Medical Device Evalution. NMPA. Key points of deep learning assisted decision making medical device software review and related description. [EB/OL]. (2021-09-28)[2022-06-16]. https://www.cmde.org.cn/xwdt/zxyw/20190628151300923.html.
43.	曹葭, 姚勇, 傅東紅, 等. 無錫市50歲及以上人群年齡相關性黃斑變性流行病學調查[J]. 中國實用眼科雜志, 2013, 31(4): 494-498. DOI: 3760/cma. j. issn. 1006-4443.2013. 04.032.Cao J, Yao Y, Fu DH, et al. Prevalence study of age-related macular degeneration over the age of 50's in Wuxi[J]. Chin J Pract Ophthalmol, 2013, 31(4): 494-498. DOI: 10.3760/cma.j.issn.1006-4443.2013.04.032.
44.	楊倩, 韓毳, 劉寧, 等. 免散瞳數碼眼底照相在眼底黃斑部疾病篩查中的應用[J]. 眼科新進展, 2012, 32(5): 473-475. DOI: 10.13389/j.cnki.rao.2012.05.010.Yang Q, Han C, Liu N, et al. Application of non-mydriatic digital fundus photography in fundus macular disease screening[J]. Rec Adv Ophthalmol, 2012, 32(5): 473-475. DOI: 10.13389/j.cnki.rao.2012.05.010.
45.	Jonas JB, Xu L, Wang YX. The Beijing eye study[J]. Acta ophthalmologica, 2009, 87(3): 247-261. DOI: 10.1111/j.1755-3768.2008.01385.x.
46.	Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning[J]. Big Data, 2019, 6(1): 1-48. DOI: 10.1186/s40537-019-0197-0.
47.	Padilla R, Netto SL, Da Silva EA. A survey on performance metrics for object-detection algorithms[C]. 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), Wuhan, 2020: 237-242.
48.	Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Trans Pattern Anal Mach Intell, 2017, 39(6): 1137-1149. DOI: 10.1109/TPAMI.2016.2577031.
49.	中華醫學會健康管理學分會, 《中華健康管理學雜志》編輯委員會. 健康體檢主檢報告撰寫專家共識[J]. 中華健康管理學雜志, 2020, 14(1): 8-11. DOI: 10.3760/cma.j.issn.1674-0815.2020.01.003.Chinese Society of Health Management, The Editorial Board of Chinese Journal of Heatlth Management. Expert consensus on the chief physician report for health checkup[J]. Chin J Health Manage, 2020, 14(1): 8-11. DOI: 10.3760/cma.j.issn.1674-0815.2020.01.003.
50.	國家食品藥品監督管理總局. 中華人民共和國醫藥行業標準: 眼科儀器眼底照相機[S]. 北京: 中國標準出版社, 2008.National Medical Products Administration. People's Republic of China Pharmaceutical Industry Standard: ophthalmic instruments fundus camera[S]. Beijing: China Standards Press, 2008.
51.	宋琳琳, 李志清, 馬文江, 等. 運用云醫療遠程平臺構建糖尿病視網膜病變分級診療模式[J]. 現代醫院管理, 2020, 18(3): 17-20. DOI: 10.3969/j.issn.1672-4232.2020.03.005.Song LL, Li ZQ, Ma WJ, et al. Establishment of a hierarchical diagnosis and treatment model for diabetic retinopathy by cloud medical remote platform[J]. Modern Hospital Management, 2020, 18(3): 17-20. DOI: 10.3969/j.issn.1672-4232.2020.03.005.
52.	譚丹華, 萬里飛, 鄒溢輝. 醫院信息系統HIS和及其應用[J]. 中國醫療器械信息, 2007, 13(9): 39-40. DOI: 10.3969/j.issn.1006-6586.2007.09.011.Tan DH, Wan LF, Zou YH. Hospital information system and its application[J]. China Medical Device Information, 2007, 13(9): 39-40. DOI: 10.3969/j.issn.1006-6586.2007.09.011.
53.	李貴祥, 劉國祥, 李剛榮, 等. 大型綜合性醫院 PACS 系統設計與實施[J]. 中國醫院管理, 2005, 25(1): 46-48. DOI: 10.3969/j.issn.1001-5329.2005.01.019.Li GX, Liu GX, Li GR, et al. The design and implementation of PACS system in large-scale comprehensive hospitals[J]. Chinese Hospital Management, 2005, 25(1): 46-48. DOI: 10.3969/j.issn.1001-5329.2005.01.019.
54.	Long M, Zhu H, Wang J, et al. Unsupervised domain adaptation with residual transfer networks[C]. 30th International Conference on Neural Information Processing Systems, New York: Curran Associates Inc. , 2016: 136-144.
55.	Ganin Y, Lempitsky V. Unsupervised domain adaptation by backpropagation[C]. The 32 nd International Conference on Machine Learning, Lille, 2015: 1180-1189.

1. 陳浩宇. 糖尿病視網膜病變篩查手冊診斷和處理(第2版)[M]. 北京: 人民衛生出版社, 2016: 10-12.Chen HY. Handbook of retinal screening in diabetes diagnosis & management (2 nd ed)[M]. Beijing: People' Medical Publishing House, 2016: 10-12.
2. 沙文茹. 《中國眼健康白皮書》發布: 致盲性眼病有效遏制[J]. 中國醫藥科學, 2020, 10(13): 3. DOI: 10.3969/j.issn.2095-0616.2020.13.002.Sha WR. “China Eye Health White Paper” released: effectively inhibition of blinding eye diseases[J]. China Medicine and Pharmacy, 2020, 10(13): 3. DOI: 10.3969/j.issn.2095-0616.2020.13.002.
3. Balyen L, Peto T. Promising artificial intelligence-machine learning-deep learning algorithms in ophthalmology[J]. Asia Pac J Ophthalmol (Phila), 2019, 8(3): 264-272. DOI: 10.22608/APO.2018479.
4. Orlando JI, Fu H, Breda JB, et al. Refuge challenge: a unified framework for evaluating automated methods for glaucoma assessment from fundus photographs[J/OL]. Med Image Anal, 2020, 59: 101570[2019-10-08].　https://pubmed.ncbi.nlm.nih.gov/31630011/. DOI: 10.1016/j.media.2019.101570.
5. 吳樂正, 林順潮. 臨床眼黃斑病學[M]. 北京: 北京科學技術出版社, 2007: 29-104.Wu LZ, Lin SC. Clinical maculopathy[M]. Beijing: Beijing Science and Technology Publishing, 2007: 29-104.
6. Esteva A, Kuprel B, Novoa RA, et al. Correction: corrigendum: dermatologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017, 546(7660): 686. DOI: 10.1038/nature22985.
7. Ehteshami Bejnordi B, Veta M, Johannes van Diest P, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer[J]. JAMA, 2017, 318(22): 2199-2210. DOI: 10.1001/jama.2017.14585.
8. Gargeya R, Leng T. Automated identification of diabetic retinopathy using deep learning[J]. Ophthalmology, 2017, 124(7): 962-969. DOI: 10.1016/j.ophtha.2017.02.008.
9. 中華醫學會眼科學分會青光眼學組, 中國醫學裝備協會眼科人工智能學組. 中國基于眼底照相的人工智能青光眼輔助篩查系統規范化設計及應用指南(2020年)[J]. 中華眼科雜志, 2020, 56(6): 423-432. DOI: 10.3760/cma.j.cn112142-20200102-00003.Chinese Medical Association Ophthalmology Branch Glaucoma Group, China Medical Equipment Association Ophthalmology Artificial Intelligence Group. Guidelines for standardized design and application of artificial intelligence glaucoma auxiliary screening system based on fundus photography in China (2020)[J]. Chin J Ophthalmol, 2020, 56(6): 423-432. DOI: 10.3760/cma.j.cn112142-20200102-00003.
10. 袁進, 雷博, 張明, 等. 基于眼底照相的糖尿病視網膜病變人工智能篩查系統應用指南[J]. 中華實驗眼科雜志, 2019, 37(8): 593-598. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.001.Yuan J, Lei B, Zhang M, et al. Guidelines for artificial intelligent diabetic retinopathy screening system based on fundus photography[J]. Chin J Exp Ophthalmol, 2019, 37(8): 593-598. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.001.
11. 中國食品藥品檢定研究院. 人工智能醫療器械質量要求和評價第1部分: 術語. YY/T 1833.1-2022[S/OL]. (2020-07-03)[2022-06-16]. http://www.cnpharm.com/upload/resources/file/2020/07/03/54879.pdf.National Institutes for Food and Drug Control. Artificial intelligence medical device—Quality requirements and evaluation—Part 1: Terminology. YY/T 1833.1-2022[S/OL]. (2020-07-03)[2022-06-16]. http://www.cnpharm.com/upload/resources/file/2020/07/03/54879.pdf.
12. 中國食品藥品檢定研究院. 人工智能醫療器械質量要求和評價第2部分: 數據集通用要求. YY/T 1833.2-2022[S/OL]. (2020-07-03)[2022-06-16]. https://www.nifdc.org.cn/directory/web/nifdc/infoAttach/38b8b027-8b43-43c1-b744-c0ac891b5ec8.pdf.National Institutes for Food and Drug Control. Artificial intelligence medical device—Quality requirements and evaluation—Part 2: General requirements for datasets. YY/T 1833.2-2022[S/OL]. (2020-07-03) [2022-06-16]. https://www.nifdc.org.cn/directory/web/nifdc/infoAttach/38b8b027-8b43-43c1-b744-c0ac891b5ec8.pdf.
13. 中國食品藥品檢定研究院. 人工智能醫療器械質量要求和評價第3部分: 數據標注通用要求(征求意見稿)[S/OL](2021-06-04)[2022-06-16]. https://www.nifdc.org.cn/directory/web/nifdc/images/2021080213295600571.pdf.National Institutes for Food and Drug Control. Artificial intelligence medical device—Quality requirements and evaluation—Part 2: General requirements for data annotation (draft for comments)[S/OL]. (2021-06-04)[2022-06-16]. https://www.nifdc.org.cn/directory/web/nifdc/images/2021080213295600571.pdf.
14. 中國質量檢驗協會. 眼底彩照標注與質量控制規范(T/CAQI 166-2020)[J]. 中華實驗眼科雜志, 2021, 39(9): 761-768. DOI: 10.3760/cma.j.cn115989-20210106-00013.China Association for Quality Inspection. Annotation and quality control specifications for fundus color photographs (T/CAQI 166-2020)[J]. Chin J Exp Ophthalmol, 2021, 39(9): 761-768. DOI: 10.3760/cma.j.cn115989-20210106-00013.
15. Davis MD, Gangnon RE, Lee LY, et al. The age-related eye disease study severity scale for age-related macular degeneration: AREDS report no. 17[J]. Arch Ophthalmol, 2005, 123(11): 1484-1498. DOI: 10.1001/archopht.123.11.1484.
16. Britton G, Liaaenjensen S, Hanspeter P. Carotenoids Volume 5: nutrition and health[J]. Carotenoids, 2009, 24(10): 497-522.
17. 美國眼科學會, 趙家良. 眼科臨床指南[M]. 北京: 人民衛生出版社, 2013: 57-59.American Academy of Ophthalmology, Zhao JL. Preferred practice pattern[M]. Beijing: People' Medical Publishing House, 2013: 57-59.
18. 張承芬. 眼底病學(第2版)[M]. 北京: 人民衛生出版社, 2010: 397-398.Zhang CF. Diseases of ocular fundus (2 nd ed)[M]. Beijing: People' Medical Publishing House, 2010: 397-398.
19. 楊依柳, 楊婷婷, 陸方, 等. 新生血管性老年性黃斑變性亞型報告的國際新命名專家共識解讀[J]. 中華眼底病雜志, 2022, 38(2): 99-107. DOI: 10.3760/cma.j.cn511434-20220128-00055.Yang YL, Yang TT, Lu F, et al. Brief interpretation of the consensus nomenclature for reporting neovascular age-related macular degeneration data[J]. Chin J Ocul Fundus Dis, 2022, 38(2): 99-107. DOI: 10.3760/cma.j.cn511434-20220128-00055.
20. 中華醫學會眼科學分會眼底病學組. 中國老年性黃斑變性臨床診斷治療路徑[J]. 中華眼底病雜志, 2013, 29(4): 343-355. DOI: 10.3760/cma.j.issn.1005-1015.2013.04.002.Fundus Disease Group of Chinese Medical Association Ophthalmology Branch. Clinical pathway of age-related macular degeneration in China[J]. Chin J Ocul Fundus Dis, 2013, 29(4): 343-355. DOI: 10.3760/cma.j.issn.1005-1015.2013.04.002.
21. 文峰, 張雄澤. 提高對視網膜出血的分類及臨床意義的認識[J]. 眼科, 2009, 18(4): 221-224.Wen F, Zhang XZ. Classification and clinical significance of retinal hemorrhage[J]. Ophthalmol CHN, 2009, 18(4): 221-224.
22. Sarks J, Tang K, Killingsworth M, et al. Development of atrophy of the retinal pigment epithelium around disciform scars[J]. Br J Ophthalmol, 2006, 90(4): 442-446. DOI: 10.1136/bjo.2005.083022.
23. Gass JD. Reappraisal of biomicroscopic classification of stages of development of a macular hole[J]. Am J Ophthalmol, 1995, 119(6): 752-759. DOI: 10.1016/s0002-9394(14)72781-3.
24. 張惠蓉, 王薇. 特發性黃斑視網膜前膜[J]. 中國實用眼科雜志, 1997, 15(10): 4.Zhang HR, Wang W. Idiopathic preretinal macular membrane[J]. Chin J Pract Ophthalmol, 1997, 15(10): 4.
25. Early treatment diabetic retinopathy study design and baseline patient characteristics: ETDRS report number 7[J]. Ophthalmology, 1991, 98(5): 741-756. DOI: 10.1016/s0161-6420(13)38009-9.
26. 嚴密. 黃斑囊樣水腫[J]. 中華眼底病雜志, 2002, 18(3): 234-235. DOI: 3760/j. issn: 1005-1015.2002. 03.035.Yan M. Cystoid macular edema[J]. Chin J Ocul Fundus Dis, 2002, 18(3): 234-235. DOI: 10.3760/j.issn:1005-1015.2002.03.035.
27. Sigler EJ, Randolph JC, Kiernan DF. Longitudinal analysis of the structural pattern of pseudophakic cystoid macular edema using multimodal imaging[J]. Graefe's Arch Clin Exp Ophthalmol, 2016, 254(1): 43-51. DOI: 10.1007/s00417-015-3000-8.
28. Brinton DA, Wilkinson CP. 視網膜脫離: 原理與實踐(第3版)[M]. 馬凱, 楊慶松, 徐軍, 譯. 2版. 北京: 人民衛生出版社, 2011: 65-67.Brinton DA, Wilkinson CP. Retinal detachment: principles and practice (3rd ed)[M]. Ma K, Yang QS, Xu J, translation. 2nd ed. Beijing: People' Medical Publishing House, 2011: 65-67.
29. Zayit-Soudry S, Moroz I, Loewenstein A. Retinal pigment epithelial detachment[J]. Surv Ophthalmol, 2007, 52(3): 227-243. DOI: 10.1016/j.survophthal.2007.02.008.
30. Madjarov G, Kocev D, Gjorgjevikj D, et al. An extensive experimental comparison of methods for multi-label learning[J]. Pattern Recogn, 2012, 45(9): 3084-3104. DOI: 10.1016/j.patcog.2012.03.004.
31. Landis JR, Koch GG. The measurement of observer agreement for categorical data[J]. Biometrics, 1977, 33(1): 159-174. DOI: 10.2307/2529310.
32. Liu L, Ouyang W, Wang X, et al. Deep learning for generic object detection: a survey[J]. Int J Comput Vision, 2020, 128(2): 261-318. DOI: 10.1007/s11263-019-01247-4.
33. Li T, Bo W, Hu C, et al. Applications of deep learning in fundus images: a review[J/OL]. Med Image Anal, 2021, 69: 101971[2021-01-20].https://pubmed.ncbi.nlm.nih.gov/33524824/. DOI: 10.1016/j.media.2021.101971.
34. Zhang YJ. A survey on evaluation methods for image segmentation[J]. Pattern Recogn, 1996, 29(8): 1335-1346. DOI: 10.1016/0031-3203(95)00169-7.
35. 李建軍, 徐亮, 彭曉燕, 等. 遠程眼科單張眼底像質量標準(征求意見稿)[J]. 眼科, 2015(1): 11-12. DOI: 10.13281/j.cnki.issn.1004-4469.2015.01.005.Li JJ, Xu L, Peng XY, et al. Quality standard for single fundus images in teleophthalmology (draft for comments)[J]. Ophthalmol CHN, 2015(1): 11-12. DOI: 10.13281/j.cnki.issn.1004-4469.2015.01.005.
36. 中華醫學會眼科學分會眼底病學組, 中國醫師協會眼科醫師分會眼底病專業委員會. 我國糖尿病視網膜病變篩查的圖像采集及閱片指南(2017年)[J]. 中華眼科雜志, 2017, 53(12): 890-896. DOI: 10.3760/cma.j.issn.0412-4081.2017.12.003.Fundus Disease Group of Ophthalmology Branch of Chinese Medical Association, Fundus Disease Professional Committee of Ophthalmologist Branch of Chinese Medical Doctor Association. Guidelines for image acquisition and reading of diabetic retinopathy screening in my country (2017)[J]. Chin J Ophthalmol, 2017, 53(12): 890-896. DOI: 10.3760/cma.j.issn.0412-4081.2017.12.003.
37. 周志華. 機器學習[M]. 北京: 清華大學出版社, 2016: 25.Zhou ZH. Machine learning[M]. Beijing: Tsinghua University Press, 2016: 25.
38. 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, 2016, 316(22): 2402-2410. DOI: 10.1001/jama.2016.17216.
39. 國家藥品監督管理局醫療器械技術審評中心. 人工智能醫療器械注冊審查指導原則 [EB/OL]. (2022-03-09)[2022-06-16]. https://www.cmde.org.cn/flfg/zdyz/zdyzwbk/20220309091014461.html.Center for Medical Device Evalution. NMPA. Guidelines for the registration review of artificial intelligence medical devices[EB/OL]. (2022-03-09)[2022-06-16]. https://www.cmde.org.cn/flfg/zdyz/zdyzwbk/20220309091014461.html.
40. 邵志強. 抽樣調查中樣本容量的確定方法[J]. 統計與決策, 2012, 22: 12-14. DOI: 10.13546/j.cnki.tjyjc.2012.22.002.Shao ZQ. The method of determining sample size in a sampling survey [J]. Statistics & Decision. 2012, 22: 12-14. DOI: 10.13546/j.cnki.tjyjc.2012.22.002.
41. 國家食品藥品監督管理總局. 醫療器械臨床試驗質量管理規范[EB/OL]. (2021-09-28)[2022-06-16]. https://www.nmpa.gov.cn/xxgk/fgwj/bmgzh/20160323141701747.html?type=pc&m=.National Medical Products Administration. Practice for quality management of clinical trials of medical devices[EB/OL]. (2021-09-28)[2022-06-16].https://www.nmpa.gov.cn/xxgk/fgwj/bmgzh/20160323141701747.html?type=pc&m=.
42. 國家藥品監督管理局醫療器械技術審評中心. 深度學習輔助決策醫療器械軟件審評要點及相關說明[EB/OL]. (2021-09-28)[2022-06-16]. https://www.cmde.org.cn/xwdt/zxyw/20190628151300923.html.Center for Medical Device Evalution. NMPA. Key points of deep learning assisted decision making medical device software review and related description. [EB/OL]. (2021-09-28)[2022-06-16]. https://www.cmde.org.cn/xwdt/zxyw/20190628151300923.html.
43. 曹葭, 姚勇, 傅東紅, 等. 無錫市50歲及以上人群年齡相關性黃斑變性流行病學調查[J]. 中國實用眼科雜志, 2013, 31(4): 494-498. DOI: 3760/cma. j. issn. 1006-4443.2013. 04.032.Cao J, Yao Y, Fu DH, et al. Prevalence study of age-related macular degeneration over the age of 50's in Wuxi[J]. Chin J Pract Ophthalmol, 2013, 31(4): 494-498. DOI: 10.3760/cma.j.issn.1006-4443.2013.04.032.
44. 楊倩, 韓毳, 劉寧, 等. 免散瞳數碼眼底照相在眼底黃斑部疾病篩查中的應用[J]. 眼科新進展, 2012, 32(5): 473-475. DOI: 10.13389/j.cnki.rao.2012.05.010.Yang Q, Han C, Liu N, et al. Application of non-mydriatic digital fundus photography in fundus macular disease screening[J]. Rec Adv Ophthalmol, 2012, 32(5): 473-475. DOI: 10.13389/j.cnki.rao.2012.05.010.
45. Jonas JB, Xu L, Wang YX. The Beijing eye study[J]. Acta ophthalmologica, 2009, 87(3): 247-261. DOI: 10.1111/j.1755-3768.2008.01385.x.
46. Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning[J]. Big Data, 2019, 6(1): 1-48. DOI: 10.1186/s40537-019-0197-0.
47. Padilla R, Netto SL, Da Silva EA. A survey on performance metrics for object-detection algorithms[C]. 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), Wuhan, 2020: 237-242.
48. Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Trans Pattern Anal Mach Intell, 2017, 39(6): 1137-1149. DOI: 10.1109/TPAMI.2016.2577031.
49. 中華醫學會健康管理學分會, 《中華健康管理學雜志》編輯委員會. 健康體檢主檢報告撰寫專家共識[J]. 中華健康管理學雜志, 2020, 14(1): 8-11. DOI: 10.3760/cma.j.issn.1674-0815.2020.01.003.Chinese Society of Health Management, The Editorial Board of Chinese Journal of Heatlth Management. Expert consensus on the chief physician report for health checkup[J]. Chin J Health Manage, 2020, 14(1): 8-11. DOI: 10.3760/cma.j.issn.1674-0815.2020.01.003.
50. 國家食品藥品監督管理總局. 中華人民共和國醫藥行業標準: 眼科儀器眼底照相機[S]. 北京: 中國標準出版社, 2008.National Medical Products Administration. People's Republic of China Pharmaceutical Industry Standard: ophthalmic instruments fundus camera[S]. Beijing: China Standards Press, 2008.
51. 宋琳琳, 李志清, 馬文江, 等. 運用云醫療遠程平臺構建糖尿病視網膜病變分級診療模式[J]. 現代醫院管理, 2020, 18(3): 17-20. DOI: 10.3969/j.issn.1672-4232.2020.03.005.Song LL, Li ZQ, Ma WJ, et al. Establishment of a hierarchical diagnosis and treatment model for diabetic retinopathy by cloud medical remote platform[J]. Modern Hospital Management, 2020, 18(3): 17-20. DOI: 10.3969/j.issn.1672-4232.2020.03.005.
52. 譚丹華, 萬里飛, 鄒溢輝. 醫院信息系統HIS和及其應用[J]. 中國醫療器械信息, 2007, 13(9): 39-40. DOI: 10.3969/j.issn.1006-6586.2007.09.011.Tan DH, Wan LF, Zou YH. Hospital information system and its application[J]. China Medical Device Information, 2007, 13(9): 39-40. DOI: 10.3969/j.issn.1006-6586.2007.09.011.
53. 李貴祥, 劉國祥, 李剛榮, 等. 大型綜合性醫院 PACS 系統設計與實施[J]. 中國醫院管理, 2005, 25(1): 46-48. DOI: 10.3969/j.issn.1001-5329.2005.01.019.Li GX, Liu GX, Li GR, et al. The design and implementation of PACS system in large-scale comprehensive hospitals[J]. Chinese Hospital Management, 2005, 25(1): 46-48. DOI: 10.3969/j.issn.1001-5329.2005.01.019.
54. Long M, Zhu H, Wang J, et al. Unsupervised domain adaptation with residual transfer networks[C]. 30th International Conference on Neural Information Processing Systems, New York: Curran Associates Inc. , 2016: 136-144.
55. Ganin Y, Lempitsky V. Unsupervised domain adaptation by backpropagation[C]. The 32 nd International Conference on Machine Learning, Lille, 2015: 1180-1189.

Chinese Journal of Ocular Fundus Diseases

The standardized design and application guidelines:a primary-oriented artificial intelligence screening system of the lesion sign in the macular region based on fundus color photography

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content