胶囊内镜中人工智能的应用现状

Application status of artificial intelligence in capsule endoscopy

胶囊内镜(CE)是检测小肠病变的主要手段,然而一次检查产生约6万张图像,筛选病变图像耗时、枯燥,且受医师经验和专业技术水平影响,易造成漏诊。近年来,人工智能(AI)逐渐深入医学领域,以卷积神经网络(CNN)为代表的深度学习(DL)模型对病灶具有快速识别能力,可在有效降低漏诊率的同时提高病变诊断率。本文就AI技术在CE图像识别中的应用现状作一综述,为其在CE领域的持续发展提供借鉴。

Capsule endoscopy(CE)is the main method for detecting small intestinal lesions.However,a single examination produces about 60000 images,which is time-consuming and tedious to screen images of lesions.It is also influenced by the experience and professional technical level of physicians,which can easily lead to missed diagnosis.In recent years,artificial intelligence(AI)has gradually penetrated the medical field.The deep learning(DL)model represented by convolutional neural network(CNN)has fast recognition ability for lesions,which can effectively reduce the missed diagnosis rate and improve the diagnosis rate of lesions.This article reviews the application status of AI technology in CE for image recognition,providing reference for its continuous development in the field of CE.