人工智能在息肉样脉络膜血管病变诊疗中的研究进展  

Research progress of artificial intelligence in the diagnosis and treatment of polypoidal choroidal vasculopathy

作　　者：杨玉婷 廖兴明 马红婕 Yang Yuting;Liao Xingming;Ma Hongjie(Aier Eye Hospital,Jinan University,Guangzhou 510071,Guangdong Province,China;Department of Ophthalmology,the First Affiliated Hospital of Jinan University,Guangzhou 510630,Guangdong Province,China;Jinan University,Guangzhou 510632,Guangdong Province,China;Aier Academy of Ophthalmology,Central South University,Changsha 410004,Hunan Province,China)

机构地区：[1]暨南大学附属爱尔眼科医院,中国广东省广州市510071 [2]暨南大学附属第一医院眼科,中国广东省广州市510630 [3]暨南大学,中国广东省广州市510632 [4]中南大学爱尔眼科研究院,中国湖南省长沙市410004

出　　处：《国际眼科杂志》2025年第3期416-421,共6页International Eye Science

基　　金：湖南省自然科学基金项目(No.2023JJ70012);广州市科技计划项目(No.202201020026)。

摘　　要：息肉样脉络膜血管病变(PCV)是新生血管性年龄相关性黄斑变性(nARMD)的重要亚型,是导致严重视力下降的主要黄斑病变之一,准确区分nARMD亚型有助于指导临床治疗方案及预测疾病转归。近年来,人工智能(AI)广泛应用于眼科疾病的诊疗与研究,利用机器学习或深度学习结合检查图像进行疾病分类、病灶分割和定量评估等。文章对近年来AI通过多种检查图像对PCV的鉴别诊断、分割量化生物标志物及预测基因型、抗VEGF治疗反应和短期发生玻璃体积血风险等方面进行回顾,总结其在临床实际应用中的困难与挑战,并展望未来AI在PCV应用中的优势及发展趋势,为其进一步应用研究提供更多信息,从而提高PCV诊断率,优化治疗方案,改善患者的视力预后。Polypoidal choroidal vasculopathy(PCV)is one of the important subtypes of neovascular age-related macular degeneration(nARMD),which causes severe vision loss.It is necessary to distinguish PCV from other nARMD subtypes to guide the clinical treatment plans and predict disease outcomes.In recent years,artificial intelligence(AI)has been widely used in the diagnosis and research of ophthalmic diseases.By utilizing machine learning or deep learning combined with examination images in disease classification,lesion segmentation,and quantitative assessment,etc.This article reviews the recent applications of AI in the differential diagnosis of PCV through various examination images,the segmentation and quantification of biomarkers,as well as the prediction of genotype,response to anti-vascular endothelial growth factor(VEGF)therapy,and the short-term risk of vitreous hemorrhage.It summarizes the difficulties and challenges in clinical practice of AI and looks forward to the advantages and development trends of AI in PCV applications in the future.The article aims to provide more information for further research and application,thereby improving the diagnostic rate of PCV,optimizing treatment plans,and improving patients’visual prognosis.

关 键 词：息肉样脉络膜血管病变 人工智能 机器学习 深度学习 卷积神经网络 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程] R773.4[医药卫生—眼科]