深度卷积神经网络用于小肠胶囊内镜检查诊断的研究进展  

Application of deep convolution neural networks in the diagnosis of small bowel diseases with wireless capsule endoscopy

作　　者：曾于珍 蒋蔚茹[1] 丁伟群[1] 邱志兵[1] 陈坚[1] TSENG Yujen;JIANG Weiru;DING Weiqun;QIU Zhibing;CHEN Jian(Department of Gastroenterology,Huashan Hospital,Fudan University,Shanghai 200040,China)

机构地区：[1]复旦大学附属华山医院消化内科,上海200040

出　　处：《上海医药》2020年第23期3-5,38,共4页Shanghai Medical & Pharmaceutical Journal

基　　金：复旦大学附属华山医院院级启动基金资助项目(2020QD008)。

摘　　要：无线胶囊内镜是诊断小肠疾病的主要手段,但存在内镜图像分析耗时、耗力的问题。本文介绍人工智能深度学习、尤其是深度卷积神经网络在小肠胶囊内镜检查自动辅助诊断方面的应用进展,包括对小肠溃疡及糜烂、血管扩张、消化道出血、小肠寄生虫病等多种疾病的诊断价值。Wireless capsule endoscopy(WCE)is the main method for diagnosing small bowel diseases,however,there are problems of time-and labor-consuming in endoscopic image analysis.This article introduces the application progress of artificial intelligence deep learning,especially deep convolutional neural networks in the automatic auxiliary diagnosis by small bowel capsule endoscopy,including the diagnostic value of such diseases as small intestinal ulcers and erosions,intestinal hemangiectasis,gastrointestinal bleeding and small intestinal parasites.

关 键 词：无线胶囊内镜 深度卷积神经网络 小肠疾病 

分 类 号：TP391.5[自动化与计算机技术—计算机应用技术] R574.5[自动化与计算机技术—计算机科学与技术]