人工智能在白内障诊断领域的应用进展  

The application progress of artificial intelligence in cataract diagnosis

作　　者：谢家兴 李学民[2] 敖明昕[2] Xie Jiaxing;Li Xuemin;Ao Mingxin(Peking University Health Science Center,Beijing 100191,China;Department of Ophthalmology,Beijing Key Laboratory of Restoration of Damaged Ocular Nerve,Peking University Third Hospital,Beijing 100191,China)

机构地区：[1]北京大学医学部,100191 [2]北京大学第三医院眼科,眼部神经损伤的重建保护与康复北京市重点实验室,100191

出　　处：《中华眼科医学杂志（电子版）》2023年第6期361-365,共5页Chinese Journal of Ophthalmologic Medicine(Electronic Edition)

基　　金：北京市自然科学基金项目(7202229)。

摘　　要：近年来,伴随社会人口老龄化进程白内障的患病率不断攀升.为缓解医疗资源配置的不足,基于裂隙灯显微镜图像、彩色眼底图像以及相干光断层扫描图像的人工智能白内障辅助诊断技术在白内障筛查和分级诊断中发挥了应用效能.其中,经典的机器学习算法依据特征被应用于图像分类,通过集成学习或融合特征的方法可综合图像信息提升分类性能,深度学习算法可自动从原始图像中提取隐含特征.目前,人工智能技术已基本具备了对白内障的规模化筛查与诊断能力.本文中笔者就近年来人工智能在白内障诊断领域的应用进展进行综述.In recent years,with the aging of the population,the incidence of cataracts has been continuously increasing.To alleviate the shortage of medical resource allocation,artificial intelligence cataract assisted diagnosis technology based on slit lamp microscopy images,color fundus images,and coherent light tomography images has played an application role in cataract screening and grading diagnosis.Among them,classic machine learning algorithms are applied to image classification based on features.By integrating learning or fusing features,classification performance can be improved by integrating image information.Deep learning algorithms can automatically extract hidden features from the original image.At present,artificial intelligence technology has basically had the capability of screening and diagnosis for cataracts on a large scale.The application progress of artificial intelligence in the field of cataract diagnosis in recent years was reviewed in this paper.

关 键 词：白内障 人工智能 深度学习 裂隙灯显微镜图像 眼底图像 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] R776.1[自动化与计算机技术—控制科学与工程]