人工智能在辅助检测早期食管癌中的应用进展  

Application of artificial intelligence-assisted endoscopic detection of early esophageal cancer

作　　者：李晴[1] 刘冰熔[1] Qing Li;Bing-Rong Liu(Department of Gastroenterology,The First Affiliated Hospital of Zhengzhou University,Zhengzhou 450000,Henan Province,China)

机构地区：[1]郑州大学第一附属医院消化内科,河南郑州450000

出　　处：《世界华人消化杂志》2021年第24期1389-1395,共7页World Chinese Journal of Digestology

基　　金：河南省杰出外籍科学家工作室项目,No.GZS2020006.

摘　　要：近年来人工智能(artificial intelligence,AI)结合内窥镜在诊断早期食管癌(esophageal cancer,EC)中崭露头角并取得满意的结果.由于EC进展快、预后差,其早期发现和诊断对改善患者预后具有重要价值.目前AI已应用于早期EC的筛查,并显示出其优势;值得注意的是,它的准确性高于缺乏经验的内镜医师.在中国,早期EC的发现依赖于内窥镜医生的专业知识,并且不可避免地受到其经验差异的影响.AI的优秀影像学识别能力非常适合于早期EC的检测和诊断,帮助医生更好地进行内镜检查,从而减少漏诊.本文综述了AI在早期EC(包括鳞状细胞癌和腺癌)的内镜检测领域中的应用及进展,重点探讨了AI在评估不同类型内镜图像时的诊断性能,如敏感性、特异性等.In recent years,artificial intelligence(AI)combined with endoscopy has made an appearance in the diagnosis of early esophageal cancer(EC)and achieved satisfactory results.Due to the rapid progression and poor prognosis of EC,the early detection and diagnosis of EC are of great value for patient prognosis improvement.AI has been applied in the screening of early EC and has shown advantages;notably,it is more accurate than less-experienced endoscopists.In China,the detection of early EC depends on endoscopist expertise and is inevitably subject to interobserver variability.The excellent imaging recognition ability of AI is very suitable for the diagnosis and recognition of EC,thereby reducing the missed diagnosis and helping physicians to perform endoscopy better.This paper reviews the application and relevant progress of AI in the field of endoscopic detection of early EC(including squamous cell carcinoma and adenocarcinoma),with a focus on diagnostic performance of AI to identify different types of endoscopic images,such as sensitivity and specificity.

关 键 词：人工智能 早期食管癌 食管鳞状细胞癌 内镜诊断 

分 类 号：R735.1[医药卫生—肿瘤]