人工智能技术辅助早产儿视网膜病变诊疗专家共识(2025)

doi:10.6040/j.issn.1673-3770.0.2024.381

摘要/Abstract

摘要： 早产儿视网膜病变(retinopathy of prematurity, ROP)是发生在早产及低出生体质量儿的视网膜血管增殖性致盲眼病,及时进行眼底筛查和诊疗是ROP防治的关键。随着人工智能(artificial intelligence, AI)技术在眼科领域的不断探索,AI技术在ROP自动筛查、诊断及指导治疗等方面均开始展开研究。但目前在ROP领域的AI技术研究,尚未有较为一致的规范。为了更好地规范和促进AI技术在ROP诊断和管理中的应用,提高AI模型诊断ROP的准确性,同时推动跨学科协作,并提升培训和教育水平,从而为患儿眼健康做出重要贡献。经过认真及充分的讨论,我们形成此专家共识意见,可为眼科医师及科研工作者在开发ROP相关的AI技术方面提供参考。

关键词: 早产儿视网膜病变, 人工智能, 眼底图像, 致盲眼病

Abstract: Retinopathy of prematurity(ROP)is a proliferative blinding retinal disease that occurs in premature infants and those with low birth weight. Timely screening and treatment are critical for the prevention and management of ROP. With the ongoing exploration of artificial intelligence(AI)in ophthalmology, AI has shown potential in areas such as automated screening, diagnosis, and treatment guidance for ROP. However, there is currently no unified standard for AI applications in this field. To better standardize and promote the application of AI in ROP diagnosis and management, enhance the accuracy of AI models in diagnosing ROP, encourage interdisciplinary collaboration, and improve training and education-ultimately contributing to the eye health of infants-we formulated this expert consensus. It serves as a valuable reference for ophthalmologists and researchers in the development and application of AI technologies for ROP.

Key words: Retinopathy of prematurity, Artificial intelligence, Fundus image, Blinding eye disease

中图分类号:

R779.7

张国明,魏文斌,林浩添,迟玮,张少冲,赵培泉,雷柏英,陈有信,王雨生,何明光,梁建宏,卢海,陆方,黄欣,梁小玲,赵欣予,吴桢泉,余震,崔凯璇,刘亚玲,项道满,陈长征,张自峰,林铎儒,于珊珊,孙悦,檀韬,陈燕先,彭婕,董力,程湧,朱雪梅,杨鹏,陈少滨. 人工智能技术辅助早产儿视网膜病变诊疗专家共识(2025)[J]. 山东大学耳鼻喉眼学报, 2025, 39(2): 1-5.

ZHANG Guoming, WEI Wenbin, LIN Haotian, CHI Wei, ZHANG Shaochong, ZHAO Peiquan, LEI Baiying, CHEN Youxin, WANG Yusheng, HE Mingguang, LIANG Jianhong, LU Hai, LU Fang, HUANG Xin, LIANG Xiaoling, ZHAO Xinyu, WU Zhenquan, YU Zhen, CUI Kaixuan, LIU Yaling, XIANG Daoman, CHEN Changzheng, ZHANG Zifeng, LIN Duoru, YU Shanshan, SUN Yue, TAN Tao, CHEN Yanxian, PENG Jie, DONG Li, CHENG Yong, ZHU Xuemei, YANG Peng, CHEN Shaobin. Expert consensus on AI-assisted diagnosis and treatment of retinopathy of prematurity(2025)[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2025, 39(2): 1-5.

参考文献

[1] 海峡两岸医药卫生交流协会眼科专业委员会小儿视网膜学组,中华医学会眼科学分会眼底病学组. 早产儿视网膜病变玻璃体腔注射抗血管内皮生长因子药物治疗的专家共识[J]. 中华眼底病杂志, 2021, 37(11): 836-840. doi:10.3760/cma.j.cn511434-20210916-00530
[2] Good WV. Retinopathy of prematurity incidence in children[J]. Ophthalmology, 2020, 127(4S): S82-S83. doi:10.1016/j.ophtha.2019.11.026
[3] 中华医学会儿科学分会眼科学组. 早产儿视网膜病变治疗规范专家共识[J]. 中华眼底病杂志, 2022, 38(1): 10-13. doi:10.3760/cma.j.cn511434-20211119-00647
[4] 中国妇幼保健协会儿童眼保健专业委员会儿童眼病筛查学组. 关于新生儿眼底筛查的专家共识[J]. 中国斜视与小儿眼科杂志, 2018, 26(3): 1-3. doi:10.3969/j.issn.1005-328X.2018.03.001
[5] 林浩添, 吴晓航. 加快基于眼科图像数据库的眼病人工智能辅助诊断平台建设[J]. 中华实验眼科杂志, 2018, 36(8): 577-580. doi:10.3760/cma.j.issn.2095-0160.2018.08.001 LIN Haotian, WU Xiaohang. Accelerating the construction of artificial intelligence diagnostic platform based on ophthalmic imaging database[J]. Chinese Journal of Experimental Ophthalmology, 2018, 36(8): 577-580. doi:10.3760/cma.j.issn.2095-0160.2018.08.001
[6] 王雅丛, 耿韶辉, 李艳涛, 等. Retcam-3检查足月新生儿视网膜出血分级的初步探讨[J]. 山东大学耳鼻喉眼学报, 2015, 29(6): 78-81,83. doi:10.6040/j. issn.1673-3770.0.2015.274 WANG Yacong, GENG Shaohui, LI Yantao, et al. An investigation of the standard of classification of retinal hemorrhage in full-term normal delivery newborns according to digital wide-angle retinal imaging device RetCam-3[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2015, 29(6): 78-81,83. doi:10.6040/j. issn.1673-3770.0.2015.274
[7] 涂勤, 唐兰, 鄢晓丽. 数字眼底拍摄同质化培训应用效果探讨[J]. 中国继续医学教育, 2022, 14(16): 121-125. doi:10.3969/j.issn.1674-9308.2022.16.031 TU Qin, TANG Lan, YAN Xiaoli. Application effect of homogenization training in digital fundus photograph[J]. China Continuing Medical Education, 2022, 14(16): 121-125. doi:10.3969/j.issn.1674-9308.2022.16.031
[8] 晏丕松, 项毅帆, 李强, 等. 眼科数据中心和智能服务云平台的建设思路[J]. 眼科学报, 2021, 36(1): 97-103. doi:10.3978/j.issn.1000-4432.2021.01.19 YAN Pisong, XIANG Yifan, LI Qiang, et al. Establishment of ophthalmic data center and intelligent service cloud platform[J]. Journal of East China Normal University(Educational Sciences), 2021, 36(1): 97-103. doi:10.3978/j.issn.1000-4432.2021.01.19
[9] 潘建东,黄崇斌,陈峰,等. 新生儿视网膜出血及其相关影响因素观察分析[J]. 中华眼底病杂志, 2013, 29(3): 280-283. doi:10.3760/cma.j.issn.1005-1015.2013.03.012 PAN Jiandong, HUANG Chongbin, CHEN Feng, et al. Retinal hemorrhage in newborns and associated factors[J]. Chinese Journal of Ocular Fundus Diseases, 2013, 29(3): 280-283. doi:10.3760/cma.j.issn.1005-1015.2013.03.012
[10] 田汝银, 张国明, 谢昊, 等. 标准方位眼底摄像技术在早产儿视网膜病变远程筛查中的应用[J]. 眼科新进展, 2019, 39(6): 568-570. doi:10.13389/j.cnki.rao.2019.0131 TIAN Ruyin, ZHANG Guoming, XIE Hao, et al. Application of standard azimuth fundus camera technique in remote screening of retinopathy of prematurity[J]. Recent Advances in Ophthalmology, 2019, 39(6): 568-570. doi:10.13389/j.cnki.rao.2019.0131
[11] Chiang MF, Quinn GE, Fielder AR, et al. International classification of retinopathy of prematurity, third edition[J].Ophthalmology, 2021, 128(10): 51-68. doi:10.1016/j.ophtha.2021.05.031
[12] 中华医学会眼科学分会眼底病学组,中国医师协会眼科医师分会眼底病专委会. 中国早产儿视网膜病变分类和治疗专家共识(2023年)[J]. 中华眼底病杂志, 2023, 39(9): 720-727. doi:10.3760/cma.j.cn511434-20230815-00346
[13] Zhao XY, Chen SB, Zhang SF, et al. A fundus image dataset for intelligent retinopathy of prematurity system[J]. Sci Data, 2024, 11(1): 543. doi:10.1038/s41597-024-03362-5
[14] Bongini M, Rigutini L, Trentin E. Recursive neural networks for density estimation over generalized random graphs[J]. IEEE Trans Neural Netw Learn Syst, 2018, 29(11): 5441-5458. doi:10.1109/TNNLS.2018.2803523
[15] Li LH, Lin DR, Lin ZZ, et al. DeepQuality improves infant retinopathy screening[J]. NPJ Digit Med, 2023, 6(1): 192. doi:10.1038/s41746-023-00943-3
[16] Zhao XY, Lin ZZ, Yu SS, et al. An artificial intelligence system for the whole process from diagnosis to treatment suggestion of ischemic retinal diseases[J]. Cell Rep Med, 2023, 4(10): 101197. doi:10.1016/j.xcrm.2023.101197
[17] Sarki R, Ahmed K, Wang H, et al. Image preprocessing in classification and identification of diabetic eye diseases[J]. Data Sci Eng, 2021, 6(4): 455-471. doi:10.1007/s41019-021-00167-z
[18] Liang XH, Li LP, Liu YY, et al. ECG_SegNet: an ECG delineation model based on the encoder-decoder structure[J]. Comput Biol Med, 2022, 145: 105445. doi:10.1016/j.compbiomed.2022.105445
[19] Hsu WY, Lin WY. Ratio-and-Scale-Aware YOLO for Pedestrian Detection[J]. IEEE Trans Image Process, 2021, 30: 934-947. doi: 10.1109/TIP.2020.3039574
[20] Ren SQ, He KM, 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
[21] van de Ruit M, Billeter M, Eisemann E. An efficient dual-hierarchy t-SNE minimization[J]. IEEE Trans Vis Comput Graph, 2022, 28(1): 614-622. doi:10.1109/TVCG.2021.3114817
[22] He T, Guo JX, Chen N, et al. MediMLP: using grad-CAM to extract crucial variables for lung cancer postoperative complication prediction[J]. IEEE J Biomed Health Inform, 2020, 24(6): 1762-1771. doi:10.1109/JBHI.2019.2949601
[23] Lin DR, Xiong JH, Liu CX, et al. Application of Comprehensive Artificial intelligence Retinal Expert(CARE)system: a national real-world evidence study[J]. Lancet Digit Health, 2021, 3(8): e486-e495. doi:10.1016/S2589-7500(21)00086-8

相关文章 14

[1]	沈嘉琪,李潇飒,毕燕龙,张敬法. 人工智能在DME筛查、诊断和预后中的应用[J]. 山东大学耳鼻喉眼学报, 2024, 38(5): 153-159.
[2]	谢玉林,雷大鹏. 人工智能在头颈部鳞状细胞癌淋巴结转移的病理研究进展[J]. 山东大学耳鼻喉眼学报, 2024, 38(3): 124-129.
[3]	胡亚柔,赵欣予,吴桢泉,范梓欣,余震,刘亚玲,陈婷毅,曾键,张国明. 早产儿屈光状态与眼部生物特征的研究进展[J]. 山东大学耳鼻喉眼学报, 2024, 38(3): 144-150.
[4]	吴丽丽,曲毅. OCTA在病理性近视脉络膜新生血管应用及其在人工智能的研究进展[J]. 山东大学耳鼻喉眼学报, 2024, 38(2): 144-149.
[5]	张一彤,李青香,石争浩,尚磊,袁钰淇,曹子讷,麻莉娜,刘海琴,任晓勇,施叶雯. 阻塞性睡眠呼吸暂停儿童睡眠结构研究及睡眠结构判读模型建立[J]. 山东大学耳鼻喉眼学报, 2023, 37(6): 126-132.
[6]	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.
[7]	刘佳钰,樊慧明,邹游,陈始明. 人工智能在鼻咽癌诊断与治疗中的应用研究进展[J]. 山东大学耳鼻喉眼学报, 2023, 37(2): 135-142.
[8]	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.
[9]	王迪,程金章,于丹. 基于机器学习的人工智能技术在耳鼻喉科临床诊疗中的应用进展[J]. 山东大学耳鼻喉眼学报, 2021, 35(6): 125-131.
[10]	冉宏运,蒋可可，张杰. 早产儿视网膜病变患儿屈光影响因素研究进展[J]. 山东大学耳鼻喉眼学报, 2021, 35(5): 118-124.
[11]	陈海兵, 卫亚楠, 许晓泉, 陈曦. 基于XGBoost人工智能结合CT构建甲状腺癌颈部淋巴结转移预测模型[J]. 山东大学耳鼻喉眼学报, 2020, 34(3): 40-45.
[12]	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.
[13]	邱昌余,周俊,庄德恩,杨晴,陆美萍,程雷. 人工智能技术在辅助耳鼻咽喉科医师了解过敏性鼻炎患者需求中的应用[J]. 山东大学耳鼻喉眼学报, 2019, 33(3): 88-94.
[14]	梅芳，陈志钧. 超低和极低出生体质量儿早产儿视网膜病变及其影响因素[J]. 山东大学耳鼻喉眼学报, 2013, 27(4): 76-78.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed