人工智能超声内镜胆胰识别系统有效性的交叉试验  

Effectiveness of artificial intelligence-endoscopic ultrasound biliary and pancreatic recognition system:a crossover study

作　　者：陈柏儒 姚理文 张丽辉 卢姿桦 吴慧玲[1] 于红刚[1] Chen Boru;Yao Liwen;Zhang Lihui;Lu Zihua;Wu Huiling;Yu Honggang(Department of Gastroenterology,Renmin Hospital of Wuhan University,Hubei Key Laboratory of Digestive Diseases,Hubei Clinical Research Center for Minimally Invasive Diagnosis and Treatment of Digestive Diseases,Wuhan 430060,China)

机构地区：[1]武汉大学人民医院消化内科消化系统疾病湖北省重点实验室、湖北省消化疾病微创诊治医学临床研究中心,武汉430060

出　　处：《中华消化内镜杂志》2023年第10期778-783,共6页Chinese Journal of Digestive Endoscopy

基　　金：湖北省卫生健康委员会创新团队项目(WJ2021C003)。

摘　　要：目的探究人工智能超声内镜(artificial intelligence-endoscopic ultrasound,AI-EUS)胆胰识别系统用于辅助识别超声内镜检查术(endoscopic ultrasonography,EUS)图像的有效性。方法从武汉大学人民医院消化内科数据库前瞻性地纳入2019年12月—2020年8月期间因怀疑有胆胰系统疾病而接受EUS检查的受试者。28例受试者的28个视频用于胰腺标准站的识别;29例受试者的29个视频用于胆管标准站的识别。8名武汉大学人民医院消化内科的新手内镜医师在有AI-EUS胆胰识别系统辅助下和无辅助下,分别阅读了57例EUS视频。比较有AI-EUS胆胰识别系统与无AI-EUS胆胰识别系统辅助时,内镜医师对EUS胰腺和胆管标准站点识别的准确率。结果无AI-EUS辅助时,新手内镜医师对胰腺标准站识别准确率为67.2%(903/1344),有AI-EUS辅助时,准确率提高至78.4%(1054/1344);胆管标准站识别准确率由无辅助时的56.4%(523/928)提高至有辅助时的73.8%(685/928)。结论AI-EUS胆胰识别系统可提高内镜医师对胆胰系统超声内镜图像识别的准确率,可在临床工作中辅助诊断。Objective To explore the effectiveness of the artificial intelligence-endoscopic ultrasound(AI-EUS)biliary and pancreatic recognition system in assisting the recognition of EUS images.Methods Subjects who received EUS due to suspicious biliary and pancreatic diseases from December 2019 to August 2020 were prospectively collected from the database of Department of Gastroenterology,Renmin Hospital of Wuhan University.Pancreatic EUS images of 28 subjects were included for recognition of pancreas standard station.EUS images of bile duct of 29 subjects were included for recognition of bile duct standard station.Eight new endoscopists from the Gastroenterology Department of Renmin Hospital of Wuhan University read the 57 EUS videos with and without the assistance of AI-EUS biliary and pancreatic recognition system.Accuracy of endoscopists'identification of biliary and pancreatic standard sites with and without the assistance of AI-EUS was compared.Results The accuracy of pancreas standard station identification of the new endoscopists increased from 67.2%(903/1344)to 78.4%(1054/1344)with the assistance of AI-EUS.The accuracy of bile duct standard station identification increased from 56.4%(523/928)to 73.8%(685/928).Conclusion AI-EUS biliary and pancreatic recognition system can improve the accuracy of EUS images recognition of biliary and pancreatic system,which can assist diagnosis in clinical work.

关 键 词：超声检查 胆管疾病 胰腺疾病 深度学习 交叉试验 

分 类 号：R445.1[医药卫生—影像医学与核医学] R57[医药卫生—诊断学]