人工智能辅助早产儿视网膜病变诊疗新进展

doi:10.6040/j.issn.1673-3770.0.2022.374

摘要/Abstract

摘要： 早产儿视网膜病变(retinopathy of prematurity, ROP)是导致儿童致盲的主要原因之一,早期ROP筛查和诊断高度依赖眼科专科医生,而随着现代医学影像技术的飞速发展和远程医疗的兴起,人工智能(artificial intelligence, AI)在ROP领域也得到了进一步应用。近年来,基于卷积神经网络、深度学习的AI在眼科筛查检测、诊疗领域得到更广泛深入地应用,其在ROP的临床诊疗方面尤引人注目,有望提高基层儿科和眼科医生对ROP早期诊断、规范治疗等方面的能力,同时降低主管医生之间的主观差异。论文概述AI在ROP自动筛查检测、诊断及预测的研究现状、存在的不足及面临的挑战,进一步了解其在ROP临床应用新动态和新进展。

关键词: 早产儿视网膜病变, 人工智能, 深度学习, 自动筛查, 诊断, 预测

Abstract: Retinopathy of prematurity(ROP)is one of the main causes of blindness in children, while early screening and diagnosis of ROP are highly dependent on ophthalmologists. With the rapid development of modern medical imaging technology and the rise of telemedicine, artificial intelligence(AI)has also been further applied in the field of ROP. In recent years, AI based on neural convolutional network and deep learning has been applied in the field of eye screening, disease detection, diagnosis and treatment, especially for the clinical diagnosis and treatment of ROP. It is expected that AI will aid primary pediatricians and ophthalmologists in early diagnosis and standardized treatment of ROP, and reduce the subjective differences among first-line doctors. This review summarizes the current status, shortcomings, and challenges faced by AI in automated ROP screening, diagnosis, and prediction, which enables the further understanding of new trends and progressment made by its clinical application in ROP.

Key words: Retinopathy of prematurity, Artificial intelligence, Deep learning, Automated screening, Diagnosis, Prediction

中图分类号:

R779.7

杜曰山一,王鲜,张国明. 人工智能辅助早产儿视网膜病变诊疗新进展[J]. 山东大学耳鼻喉眼学报, 2023, 37(3): 157-162.

DU Yueshanyi, WANG Xian, ZHANG Guoming. Progress in the diagnosis and treatment of retinopathy of prematurity using artificial intelligence[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2023, 37(3): 157-162.

参考文献

[1] Solebo AL, Teoh L, Rahi J. Epidemiology of blindness in children[J]. Arch Dis Child, 2017, 102(9): 853-857. doi:10.1136/archdischild-2016-310532
[2] Li JP O, Liu HR, Ting DSJ, et al. Digital technology, tele-medicine and artificial intelligence in ophthalmology: a global perspective[J]. Prog Retin Eye Res, 2021, 82: 100900. doi:10.1016/j.preteyeres.2020.100900
[3] Wu T, Zhang L, Tong Y, et al. Retinopathy of prematurity among very low-birth-weight infants in China: incidence and perinatal risk factors[J]. Invest Ophthalmol Vis Sci, 2018, 59(2): 757-763. doi:10.1167/iovs.17-23158
[4] 黎晓新. 我国早产儿视网膜病变特点和筛查指南[J]. 中华眼底病杂志, 2004(6): 384-386. LI Xiaoxin. Characteristics and screening guidelines of retinopathy of prematurity in China[J]. Chinese Journal of Ocular Fundus Diseases, 2004(6): 384-386.
[5] Du XL, Li WB, Hu BJ. Application of artificial intelligence in ophthalmology[J]. Int J Ophthalmol, 2018, 11(9): 1555-1561. doi:10.18240/ijo.2018.09.21
[6] 刘潇逸, 项毅帆, 杨扬帆, 等. 婴幼儿眼病的人工智能应用[J]. 眼科学报, 2022, 37(3): 214-221. LIU Xiaoyi, XIANG Yifan, YANG Yangfan, et al. Artificial intelligence application for infantile eye diseases[J]. Eye Science, 2022, 37(3): 214-221.
[7] 华红利, 李松, 陶泽璋. 人工智能在鼻咽癌诊疗中的研究进展[J]. 山东大学耳鼻喉眼学报, 2022, 36(2): 113-119. doi: 10.6040/j.issn.1673-3770.0.2021.175 HUA Hongli, LI Song, TAO Zezhang. Research progress of artificial intelligence in the diagnosis and treatment of nasopharyngeal carcinoma[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2022, 36(2): 113-119. doi: 10.6040/j.issn.1673-3770.0.2021.175
[8] 朱志玲, 李松, 管国芳. 人工智能在耳鼻咽喉头颈外科的运用及展望[J]. 山东大学耳鼻喉眼学报, 2020, 34(2): 115-120. doi: 10.6040/j.issn.1673-3770.0.2019.598 ZHU Zhiling, LI Song, GUAN Guofang. Application and prospect of artificial intelligence in otolaryngology[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2020, 34(2): 115-120. doi: 10.6040/j.issn.1673-3770.0.2019.598
[9] 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
[10] De Fauw J, Ledsam JR, Romera-Paredes B, et al. Clinically applicable deep learning for diagnosis and referral in retinal disease[J]. Nat Med, 2018, 24(9): 1342-1350. doi:10.1038/s41591-018-0107-6
[11] Ting DSW, Cheung CYL, Lim G, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes[J]. JAMA, 2017, 318(22): 2211-2223. doi:10.1001/jama.2017.18152
[12] 林浩添, 李龙辉, 陈睛晶. 儿童眼病的人工智能研究进展[J]. 山东大学学报(医学版), 2020, 58(11): 11-16. doi:10.6040/j.issn.1671-7554.0.2020.1173 LIN Haotian, LI Longhui, CHEN Jingjing. Research progress of artificial intelligence in childhood eye diseases[J]. Journal of Shandong University(Health Science), 2020, 58(11): 11-16. doi:10.6040/j.issn.1671-7554.0.2020.1173
[13] Wallace DK, Zhao ZE, Freedman SF. A pilot study using “ROPtool” to quantify plus disease in retinopathy of prematurity[J]. J Am Assoc Pediatr Ophthalmol Strabismus, 2007, 11(4): 381-387. doi:10.1016/j.jaapos.2007.04.008
[14] Heneghan C, Flynn J, O'Keefe M, et al. Characterization of changes in blood vessel width and tortuosity in retinopathy of prematurity using image analysis[J]. Med Image Anal, 2002, 6(4): 407-429. doi:10.1016/S1361-8415(02)00058-0
[15] Rabinowitz MP, Grunwald JE, Karp KA, et al. Progression to severe retinopathy predicted by retinal vessel diameter between 31 and 34 weeks of postconception age[J]. Arch Ophthalmol, 2007, 125(11): 1495-1500. doi:10.1001/archopht.125.11.1495
[16] Brown JM, Campbell JP, Beers A, et al. Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks[J]. JAMA Ophthalmol, 2018, 136(7): 803-810. doi:10.1001/jamaophthalmol.2018.1934
[17] Choi RY, Brown JM, Kalpathy-Cramer J, et al. Variability in plus disease identified using a deep learning-based retinopathy of prematurity severity scale[J]. Ophthalmol Retina, 2020, 4(10): 1016-1021. doi:10.1016/j.oret.2020.04.022
[18] Campbell JP, Kim SJ, Brown JM, et al. Evaluation of a deep learning-derived quantitative retinopathy of prematurity severity scale[J]. Ophthalmology, 2021, 128(7): 1070-1076. doi:10.1016/j.ophtha.2020.10.025
[19] Taylor S, Brown JM, Gupta K, et al. Monitoring disease progression with a quantitative severity scale for retinopathy of prematurity using deep learning[J]. JAMA Ophthalmol, 2019, 137(9): 1022-1028. doi:10.1001/jamaophthalmol.2019.2433
[20] Gupta K, Campbell JP, Taylor S, et al. A quantitative severity scale for retinopathy of prematurity using deep learning to monitor disease regression after treatment[J]. JAMA Ophthalmol, 2019, 137(9): 1029-1036. doi:10.1001/jamaophthalmol.2019.2442
[21] Bellsmith KN, Brown J, Kim SJ, et al. Aggressive posterior retinopathy of prematurity: clinical and quantitative imaging features in a large North American cohort[J]. Ophthalmology, 2020, 127(8): 1105-1112. doi:10.1016/j.ophtha.2020.01.052
[22] Campbell JP, Chiang MF, Chen JS, et al. Artificial intelligence for retinopathy of prematurity: validation of a vascular severity scale against international expert diagnosis[J]. Ophthalmology, 2022, 129(7): e69-e76. doi:10.1016/j.ophtha.2022.02.008
[23] Chiang MF, Quinn GE, Fielder AR, et al. International classification of retinopathy of prematurity, third edition[J]. Ophthalmology, 2021, 128(10): e51-e68. doi:10.1016/j.ophtha.2021.05.031
[24] International Committee for the Classification of Retinopathy of Prematurity. The international classification of retinopathy of prematurity revisited[J]. Arch Ophthalmol, 2005, 123(7): 991-999. doi:10.1001/archopht.123.7.991
[25] 郭宝, 张德勇. 康柏西普联合激光治疗急进性早产儿视网膜病变[J]. 山东大学耳鼻喉眼学报, 2018, 32(6): 92-97. doi:10.6040/j.issn.1673-3770.0.2018.272 GUO Bao, ZHANG Deyong. Clinical study of compaq combined with laser in the treatment of retinopathy of prematurity[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2018, 32(6): 92-97. doi:10.6040/j.issn.1673-3770.0.2018.272
[26] Zhao JF, Lei BY, Wu ZQ, et al. A deep learning framework for identifying zone I in RetCam images[J]. IEEE Access, 2019, 7: 103530-103537. doi:10.1109/ACCESS.2019.2930120
[27] Zhang RG, Zhao JF, Chen GZ, et al. Aggressive Posterior Retinopathy of Prematurity Automated Diagnosis via a Deep Convolutional Network[C] //International Workshop on Ophthalmic Medical Image Analysis. Cham: Springer, 2019: 165-172.10.1007/978-3-030-32956-3_20
[28] Agrawal R, Kulkarni S, Walambe R, et al. Assistive framework for automatic detection of all the zones in retinopathy of prematurity using deep learning[J]. J Digit Imaging, 2021, 34(4): 932-947. doi:10.1007/s10278-021-00477-8
[29] Peng YY, Chen ZY, Zhu WF, et al. Automatic zoning for retinopathy of prematurity with semi-supervised feature calibration adversarial learning[J]. Biomed Opt Express, 2022, 13(4): 1968-1984. doi:10.1364/BOE.447224
[30] Ng WY, Zhang SH, Wang ZR, et al. Updates in deep learning research in ophthalmology[J]. Clin Sci(Lond), 2021, 135(20): 2357-2376. doi:10.1042/CS20210207
[31] Peng YY, Zhu WF, Chen ZY, et al. Automatic staging for retinopathy of prematurity with deep feature fusion and ordinal classification strategy[J]. IEEE Trans Med Imaging, 2021, 40(7): 1750-1762. doi:10.1109/TMI.2021.3065753
[32] Attallah O. DIAROP: automated deep learning-based diagnostic tool for retinopathy of prematurity[J]. Diagnostics(Basel), 2021, 11(11): 2034. doi:10.3390/diagnostics11112034
[33] Hu JJ, Chen YY, Zhong J, et al. Automated analysis for retinopathy of prematurity by deep neural networks[J]. IEEE Trans Med Imaging, 2019, 38(1): 269-279. doi:10.1109/TMI.2018.2863562
[34] Wang JY, Ju R, Chen YY, et al. Automated retinopathy of prematurity screening using deep neural networks[J]. EBioMedicine, 2018, 35: 361-368. doi:10.1016/j.ebiom.2018.08.033
[35] Zhang YS, Wang L, Wu ZQ, et al. Development of an automated screening system for retinopathy of prematurity using a deep neural network for wide-angle retinal images[J]. IEEE Access, 2018, 7: 10232-10241. doi:10.1109/ACCESS.2018.2881042
[36] Wu QW, Hu YJ, Mo ZY, et al. Development and validation of a deep learning model to predict the occurrence and severity of retinopathy of prematurity[J]. JAMA Netw Open, 2022, 5(6): e2217447. doi:10.1001/jamanetworkopen.2022.17447
[37] Iu LPL, Yip WWK, Lok JYC, et al. Prediction model to predict type 1 retinopathy of prematurity using gestational age and birth weight(PW-ROP)[J]. Br J Ophthalmol, 2022: bjophthalmol-2021-320670. doi:10.1136/bjophthalmol-2021-320670
[38] Coyner AS, Chen JS, Singh P, et al. Single-examination risk prediction of severe retinopathy of prematurity[J]. Pediatrics, 2021, 148(6): e2021051772. doi:10.1542/peds.2021-051772
[39] Schmidt-Erfurth U, Sadeghipour A, Gerendas BS, et al. Artificial intelligence in retina[J]. Prog Retin Eye Res, 2018, 67: 1-29. doi:10.1016/j.preteyeres.2018.07.004

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed