深度学习技术在提升结直肠息肉性质鉴别准确率中的应用  

Deep learning for the improvement of the accuracy of colorectal polyp classification

作　　者：宫德馨 张军[1,2] 周巍 吴练练[1,2] 胡珊 于红刚 Gong Dexin;Zhang Jun;Zhou Wei;Wu Lianlian;Hu Shan;Yu Honggang(Department of Gastroenterology,Renmin Hospital of Wuhan University,Wuhan 430060,China;Hubei Key Laboratory of Digestive Disease,Wuhan 430060,China;Wuhan EndoAngel Medical Technology Co.,Ltd.,Wuhan 430000,China)

机构地区：[1]武汉大学人民医院消化内科,430060 [2]消化疾病湖北省重点实验室,武汉430060 [3]武汉楚精灵医疗科技有限公司,430000

出　　处：《中华消化内镜杂志》2021年第10期801-805,共5页Chinese Journal of Digestive Endoscopy

基　　金：国家自然科学基金(81672387);湖北省重大科技创新项目(2018-916-000-008);湖北省消化疾病微创诊疗医学临床研究中心项目(2018BCC337)。

摘　　要：目的探讨采用深度学习技术提升内镜医师在窄带光成像(narrow band imaging, NBI)下判断结直肠息肉性质准确率的价值。方法收集武汉大学人民医院消化内镜中心结直肠息肉的NBI非放大图片并分为3个数据集, 数据集1(2018年1月—2020年10月, 1 846张非腺瘤性与2 699张腺瘤性息肉的NBI非放大图片)用来训练和验证结直肠息肉性质鉴别系统;数据集2(2018年1月—2020年10月, 210张非腺瘤性息肉和288张腺瘤性息肉的NBI非放大图片)用来比较内镜医师及该系统息肉分型的准确性, 同时比较4名消化内镜初学者在该系统的辅助下判断息肉性质的准确性是否有提升;数据集3(2020年11月—2021年1月, 141张非腺瘤性息肉和203张腺瘤性息肉的NBI非放大图片)用来前瞻性测试该系统。结果该系统在数据集2中判断结直肠息肉的准确率为90.16%(449/498), 优于内镜医师。消化内镜初学者在有该系统的辅助下, 息肉分型准确率显著提升。在前瞻性研究中, 该系统的准确率为89.53%(308/344)。结论本研究开发的基于深度学习的结直肠息肉性质鉴别系统能够显著提升内镜医师初学者的息肉分型准确率。Objective To evaluate deep learning in improving the diagnostic rate of adenomatous and non-adenomatous polyps.Methods Non-magnifying narrow band imaging(NBI)polyp images obtained from Endoscopy Center of Renmin Hospital,Wuhan University were divided into three datasets.Dataset 1(2699 adenomatous and 1846 non-adenomatous non-magnifying NBI polyp images from January 2018 to October 2020)was used for model training and validation of the diagnosis system.Dataset 2(288 adenomatous and 210 non-adenomatous non-magnifying NBI polyp images from January 2018 to October 2020)was used to compare the accuracy of polyp classification between the system and endoscopists.At the same time,the accuracy of 4 trainees in polyp classification with and without the assistance of this system was compared.Dataset 3(203 adenomatous and 141 non-adenomatous non-magnifying NBI polyp images from November 2020 to January 2021)was used to prospectively test the system.Results The accuracy of the system in polyp classification was 90.16%(449/498)in dataset 2,superior to that of endoscopists.With the assistance of the system,the accuracy of colorectal polyp diagnosis was significantly improved.In the prospective study,the accuracy of the system was 89.53%(308/344).Conclusion The colorectal polyp classification system based on deep learning can significantly improve the accuracy of trainees in polyp classification.

关 键 词：机器学习 腺瘤性息肉 结直肠肿瘤 窄带光成像 

分 类 号：R735.34[医药卫生—肿瘤]