基于角膜共聚焦显微镜的神经纤维人工智能分析方法  

Artificial Intelligence Analysis of Nerve Fibers Based on Corneal Confocal Microscopy

作　　者：吴俊[1] 费思佳 沈博[1] 张瀚文 黄剑锋 潘琦 赵建春 丁大勇 WU Jun;FEI Sijia;SHEN Bo;ZHANG Hanwen;HUANG Jianfeng;PAN Qi;ZHAO Jianchun;DING Dayong(School of Electronics and Information,Northwestern Polytechnical University,Xi’an 710072,China;Graduate School,Chinese Academy of Medical Sciences&Peking Union Medical College,Beijing 100730,China;Department of Ophthalmology,Beijing hospital,National Center of Gerontology/Institute of Geriatric Medicine,Chinese Academy of Medical Sciences,Beijing 100730,China;Department of Endocrinology,Beijing hospital,National Center of Gerontology/Institute of Geriatric Medicine,Chinese Academy of Medical Sciences,Beijing 100730,China;Vistel AI Lab,Visionary Intelligent Ltd.,Beijing 100872,China)

机构地区：[1]西北工业大学电子信息学院,西安710072 [2]中国医学科学院北京协和医学院研究生院,北京100730 [3]国家老年医学中心中国医学科学院老年医学研究院北京医院眼科,北京100730 [4]国家老年医学中心中国医学科学院老年医学研究院北京医院内分泌科,北京100730 [5]北京致远慧图科技有限公司人工智能实验室,北京100872

出　　处：《协和医学杂志》2021年第5期736-741,共6页Medical Journal of Peking Union Medical College Hospital

基　　金：国家重点研发计划(2020YFC2009006,2020YFC2009000);陕西省自然科学基础研究计划(2020JM-129);西北工业大学硕士研究生创意创新种子基金(CX2020162);西北工业大学国家级大学生创新创业训练计划(S202010699207,S202010699630)。

摘　　要：糖尿病周围神经病变(diabetic peripheral neuropathy,DPN)是糖尿病最常见的慢性并发症之一。基于临床症状体征以及电生理检查的传统DPN诊断方法主要用于检测大神经纤维病变,而DPN最早出现损伤的部位是小神经纤维。角膜共聚焦显微镜(corneal confocal microscopy,CCM)能够在高倍镜下分析角膜神经纤维的变化,是一种快速、可重复、定量测量小神经纤维病变的无创技术,可早期诊断DPN并前瞻性评估神经形态学改变,具有良好的应用前景。本文就CCM评估糖尿病神经病变的临床应用研究以及CCM相关人工智能分析方法进行综述,以期为临床诊疗提供借鉴。Diabetic peripheral neuropathy(DPN)is one of the most common chronic complications of diabetes.Traditional DPN diagnostic methods are based on clinical symptoms and signs as well as electrophysiological examination,which are mainly used to detect the lesions of large nerve fibers.However,the small nerve fibers are the earliest ones damaged in DPN.Corneal confocal microscopy(CCM)can analyze the changes of corneal nerve fibers under a high power microscope.It is a rapid,repeatable and quantitative noninvasive technique to measure small nerve fibers.It can diagnose DPN early and evaluate neuromorphological changes prospectively.It has a good application expectation.During this article,we summarized the role and limitations of DPN’s most reliable parameters of corneal nerve in evaluating diabetic autonomic neuropathy and diabetic micro-vascular complications.Further,we reviewed the clinical application of CCM in evaluating diabetic neuropathy and analysis methods of CCM related artificial intelligence,in order to provide references for clinical diagnosis and treatment.

关 键 词：人工智能 深度学习 角膜共聚焦显微镜 糖尿病周围神经病变 

分 类 号：R-1[医药卫生] R770.4