基于EM-GRA方法的机器人辅助手术操作技能评价  

Evaluation of Robot-Assisted Surgery Skills Based on EM-GRA

作　　者：邢元[1,2] 牛顺康 金奎 梁科 张冲[4] 赵頔 Xing Yuan;Niu Shunkang;Jin Kui;Liang Ke;Zhang Chong;Zhao Di(School of Mechanical Engineering,Tianjin University,Tianjin 300350,China;Key Laboratory of Mechanism Theory and Equipment Design of Ministry of Education,Tianjin University,Tianjin 300350,China;Rocket Force Characteristic Medical Center of PLA,Beijing 100088,China;Medical College of Soochow University,Suzhou 215123,China)

机构地区：[1]天津大学机械工程学院,天津300350 [2]天津大学机构理论与装备设计教育部重点实验室,天津300350 [3]解放军火箭军特色医学中心,北京100088 [4]苏州大学医学院,苏州215123

出　　处：《天津大学学报（自然科学与工程技术版）》2021年第6期636-644,共9页Journal of Tianjin University：Science and Technology

基　　金：国家科技支撑计划资助项目(2017YFC0110401);国家自然科学基金资助项目(51721003).

摘　　要：机器人辅助微创外科手术技术将传统微创外科手术的床旁操作方式转化为基于人机系统的遥操作方式,为外科医生带来了新的挑战.作为该系统中最重要的控制环节,医生的操作技能水平将直接决定整个机器人系统的运动性能,并对手术质量与疗效起到决定性的作用.目前,机器人操作技术的培训与评估主要依靠专家的主观判断,因此,如何从医生进行机器人操作所表现出来的运动特征中有效识别出其技能水平,为医务人员在机器人辅助微创外科手术培训及操作技能评价方面提供公正、客观的理论指导,对研究和改进机器人系统控制方法、帮助医务人员提高手术操作技能、确保手术操作的规范性和安全性方面具有十分重要的作用.本文使用了一种基于EM-GRA方法的机器人辅助微创外科手术操作技能评价方法,以“MicroHand S”机器人系统作为应用平台,简要地阐述了人机操作下的控制策略,并在此基础上构建了机器人操作技能评价模型,采集不同实验人员进行设定实验任务时机器人末端执行器输出的运动特征参数进行分析处理.通过与专家打分结果的相关性分析验证了指标的有效性,使用熵值法(entropy method,EM)确定各评价指标的权重,然后结合灰色关联分析(gray relation analysis,GRA)计算医生的最终得分与薄弱指标增长空间.最终实验结果表明,该评价模型指标与专家打分具有相关性,可有效识别出不同操作人员的水平差异和薄弱点,从而验证了该评价方法的可行性.Robot-assisted minimally invasive surgery(RMIS)transforms traditional minimally invasive bedside surgical procedures into man-machine-based teleoperation methods,which introduced challenges to surgeons.As the most important element in controlling the system,the surgeons’operating skill directly regulates the robot motion performance,revealing operation quality and clinical effect.Currently,training and evaluation for robotic operation primarily rely on the experts’subjective judgement.Hence,it is important to effectively identify the surgeons’skill level according to their motion characteristic when operating the robot and provide fair and objective theoretical instructions for training and evaluating operation skill of robot-assisted minimally invasive surgery,which plays an important role in studying and improving robotic control methods,further helping surgeons improve their skill and ensuring operation safety and standardization.This study uses a skill evaluation method for robot-assisted minimally invasive surgery based on entropy method-grey relation analysis(EM-GRA),using the “MicroHand S” system as the researchplatform. The control policy under man-machine operation is described,and based on which,the evaluation mode ofoperation skill is established. Collect the motion characteristic parameters of the end of the robot instrument whendifferent surgeons perform experimental tasks for analysis and processing. The strong correlation with the expert’sscoring results verifies the effectiveness of the metrics,using the entropy method(EM)to determine the weight ofeach evaluation metrics and then combining the grey relation analysis(GRA)to calculate the doctor’s final score andgrowth space of the weak metrics. Findings show that the evaluation model metrics is correlated with expert scoring,which can effectively identify the level differences and weak points of different operators,thus verifying the feasibilityof the evaluation method.

关 键 词：技能评价 统计分析 “MicroHand S”系统 机器人手术培训 

分 类 号：TP242.3[自动化与计算机技术—检测技术与自动化装置]