基于深度学习的内镜超声胆管扫查辅助分站系统构建

Development of auxiliary substation system for endoscopic ultrasound bile duct scanning based on deep learning

目的构建基于深度学习的人工智能内镜超声(endoscopic ultrasonography,EUS)胆管扫查辅助分站系统,以期辅助医师学习多站成像技术,提高操作水平。方法回顾性收集武汉大学人民医院和武汉协和医院2016年5月—2020年10月522例EUS视频资料,基于视频截取图像,获得来自武汉大学人民医院的3000张白光胃镜,31003张超声胃镜图像和来自武汉协和医院的799张超声胃镜图像,用于EUS胆管扫查系统的模型训练和模型测试。模型包括:白光胃镜图像过滤模型,标准站图像与非标准站图像区分模型和EUS胆管扫查标准图像分站模型,用以将标准图像分为肝窗、胃窗、球窗、降窗。然后从测试集中随机抽取110张图像进行人机大赛,比较专家、高级内镜医师与人工智能模型对胆管扫查多站成像每个站点识别的准确度。结果白光胃镜图像过滤模型准确率为100.00%(1200/1200),标准站图像与非标准站图像区分模型准确率为93.36%(2938/3147),EUS胆管扫查标准图像分站模型在内部测试集中各分类的准确率分别为肝窗97.23%(1687/1735),胃窗96.89%(1681/1735),球窗98.73%(1713/1735),降窗97.18%(1686/1735);外部测试集中准确率分别为肝窗89.61%(716/799),胃窗92.74%(741/799),球窗90.11%(720/799),降窗92.24%(737/799)。人机大赛中,模型分站的正确率为89.09%(98/110),高于内镜医师[85.45%(94/110),74.55%(82/110),85.45%(94/110)],接近专家水平[92.73%(102/110),90.00%(99/110)]。结论本研究构建了一种基于深度学习的EUS胆管扫查系统,可以较为准确地实时辅助内镜医师进行标准多站扫查,提高EUS完整性及操作质量。

Objective To construct a deep learning-based artificial intelligence endoscopic ultrasound(EUS)bile duct scanning substation system to assist endoscopists in learning multi-station imaging and improve their operation skills.Methods A total of 522 EUS videos in Renmin Hospital of Wuhan University and Wuhan Union Hospital from May 2016 to October 2020 were collected,and images were captured from these videos,including 3000 white light images and 31003 EUS images from Renmin Hospital of Wuhan University,and 799 EUS images from Wuhan Union Hospital.The pictures were divided into training set and test set in the EUS bile duct scanning system.The system included filtering model of white light gastroscopy images(model 1),distinguishing model of standard station images and non-standard station images(model 2)and substation model of EUS bile duct scanning standard images(model 3),which were used to classify the standard images into liver window,stomach window.duodenal bulb window.and duodenal descending window.Then 110 pictures were randomly selected from the lest set for a man-machine competition to compare the accuracy of muli-station imaging by experts,advanced endoscopists and the arifcial itelligence model.Results The accuracies of model 1 and model 2 were 100.00%(1200/1200)and 93.36%(2938/3147)respectively.Those of model 3 on the internal validation dalaset in each clasification were 97.23%(1687/1735)in liver window,96.89%(1681/1735)in stomach window,98.73%(1713/1735)in duodenal bulb window,and 97.18%(1686/1735)in duodenal descending window.And those on the external validation dataset were 89.61%(716/799)in liver window,92.74%(741/799)in stomach window.90.11%(720/799)in duodenal bulb window.and 92.24%(737/799)in duodenal descending window.In the man-machine competition,the accuracy of the substation model was 89.09%(98/110),which was higher than that of senior endoscopists[85.45%(94/110),74.55%(82/110).and 85.45%(94/110)]and close to the level of experts[92.73%(102/110)and 90.00%(99/110)].Conclusion The deep learning-based EUS bile duct scanning system constructed in the current study can assist endoscopists to perform standard multi-station scaning in real time more accurately and improve the completeness and quality of EUS.