基于人工智能的数字X线机自助检查系统的设计  

Design of Digital X-ray Machine Self Examination System Based on Artificial Intelligence

作　　者：杨欣 陈碧 王辉 罗江 曾轩 朱昱昊 陈丽惠 池显辰 YANG Xin;CHEN Bi;WANG Hui;LUO Jiang;ZENG Xuan;ZHU Yuhao;CHEN Lihui;CHI Xianchen(College of Medical Imaging,Xuzhou Medical University,Xuzhou 221000,China)

机构地区：[1]徐州医科大学医学影像学院,江苏徐州221000

出　　处：《计算机测量与控制》2022年第3期151-155,共5页Computer Measurement &Control

基　　金：2021年江苏省大学生创新训练计划省级一般项目(202110313090Y)。

摘　　要：为了实现数字X线机检查的体位识别智能化与摆位自助化,采用自主研发的基于堆叠沙漏网络的体位识别装置、应用动作相关关系模型的体位判断装置和加入语音提示功能的数字X线机“自助检查”装置,解决了如今影像摄片体位精准度不高、影像科技术人员数量不足、传统摄片耗时较长等问题;经多次实验结果表明,系统将原本人均将近6分钟的摄影时间缩短到大约三分半,将甲级片出片率的不足40%提升到将近80%,进而将误诊率减少30%,同时能够有效地减少医患接触,减低院内感染的风险,系统实现了缩短摄片时间、提高摄影质量、降低院内感染的目标。In order to realize the intelligent position recognition and self-help positioning of digital X-ray machine examination,the self-developed position recognition device based on stacked hourglass network,the position judgment device applying action correlation model and the “self-service examination” device of digital X-ray machine with voice prompt function are adopted to solve the problems,the position accuracy of image photography is low,the technicians in the imaging department is insufficient,and the traditional photography takes a long time.The experimental results show that the original photography time is reduced from nearly 6 minutes to about 3.5 minutes,the first-grade film productive rate increases from less than 40% to nearly 80%,and then the misdiagnosis rate reduces by 30%.At the same time,it can effectively reduce the contact between doctors and patients and the nosocomial infective risk.The system is realized by shortening the photography time,improving the photography quality and achieving the goal of reducing nosocomial infection.

关 键 词：人工智能 体位识别 摆位不当 堆叠沙漏网络 计算机视觉技术 

分 类 号：Q81[生物学—生物工程]