论文标题
机器人辅助手术中执行错误的运行时间检测
Runtime Detection of Executional Errors in Robot-Assisted Surgery
论文作者
论文摘要
尽管在手术机器人的设计和自动化技术方面的设计方面有重大发展，以便对手术技能进行客观评估，但在确保机器人辅助的微型侵入性手术（RMI）的安全性方面仍然存在挑战。本文提出了一个运行时监视系统，用于通过分析运动学数据在手术任务期间检测执行错误。提出的系统结合了双暹罗神经网络和外科手术环境的知识，包括手术任务和手势，它们的分布相似性以及常见的误差模式，以了解从小型训练数据集中的正常和错误手术轨迹之间的差异。与单个CNN和LSTM网络相比，我们使用介绍了不同级别的上下文知识和培训数据的单个CNN和LSTM网络评估了错误检测的性能，使用了拼图数据集的缝合和针刺传递任务的干lab证明。我们的结果表明，手势特定的任务非特异性暹罗网络获得了0.94（暹罗CNN）和0.95（Siamese-LSTM）的微F1得分，并且性能优于单个CNN（0.86）和LSTM（0.87）（0.87）。这些暹罗网络还优于非特异性任务特定任务特定的siamese-CNN和siamese-lstM模型，用于缝合和针的传递。
Despite significant developments in the design of surgical robots and automated techniques for objective evaluation of surgical skills, there are still challenges in ensuring safety in robot-assisted minimally-invasive surgery (RMIS). This paper presents a runtime monitoring system for the detection of executional errors during surgical tasks through the analysis of kinematic data. The proposed system incorporates dual Siamese neural networks and knowledge of surgical context, including surgical tasks and gestures, their distributional similarities, and common error modes, to learn the differences between normal and erroneous surgical trajectories from small training datasets. We evaluate the performance of the error detection using Siamese networks compared to single CNN and LSTM networks trained with different levels of contextual knowledge and training data, using the dry-lab demonstrations of the Suturing and Needle Passing tasks from the JIGSAWS dataset. Our results show that gesture specific task nonspecific Siamese networks obtain micro F1 scores of 0.94 (Siamese-CNN) and 0.95 (Siamese-LSTM), and perform better than single CNN (0.86) and LSTM (0.87) networks. These Siamese networks also outperform gesture nonspecific task specific Siamese-CNN and Siamese-LSTM models for Suturing and Needle Passing.
