Fukuda Tomohiro, Tanaka Yoshihiro, Fujiwara Michitaka, Sano Akihito
Department of Electrical and Mechanical Engineering, Graduate School of Engineering, Nagoya Institute of Technology, Nagoya, Japan.
Japan Society for the Promotion of Science, Tokyo, Japan.
Front Robot AI. 2018 Jun 19;5:71. doi: 10.3389/frobt.2018.00071. eCollection 2018.
Tactile sensory input of surgeons is severely limited in minimally invasive surgery, therefore manual palpation cannot be performed for intraoperative tumor detection. Computer-aided palpation, in which tactile information is acquired by devices and relayed to the surgeon, is one solution for overcoming this limitation. An important design factor is the method by which the acquired information is fed back to the surgeon. However, currently there is no systematic method for achieving this aim, and it is possible that a badly implemented feedback mechanism could adversely affect the performance of the surgeon. In this study, we propose an assistance algorithm for intraoperative tumor detection in laparoscopic surgery. Our scenario is that the surgeon manipulates a sensor probe, makes a decision based on the feedback provided from the sensor, while simultaneously, the algorithm analyzes the time series of the sensor output. Thus, the algorithm assists the surgeon in making decisions by providing independent detection results. A deep neural network model with three hidden layers was used to analyze the sensor output. We propose methods to input the time series of the sensor output to the model for real-time analysis, and to determine the criterion for detection by the model. This study aims to validate the feasibility of the algorithm by using data acquired in our previous psychophysical experiment. There, novice participants were asked to detect a phantom of an early-stage gastric tumor through visual feedback from the tactile sensor. In addition to the analysis of the accuracy, signal detection theory was employed to assess the potential detection performance of the model. The detection performance was compared with that of human participants. We conducted two types of validation, and found that the detection performance of the model was not significantly different from that of the human participants if the data from a known user was included in the model construction. The result supports the feasibility of the proposed algorithm for detection assistance in computer-aided palpation.
在微创手术中，外科医生的触觉感官输入受到严重限制，因此无法进行术中肿瘤检测的手动触诊。计算机辅助触诊是克服这一限制的一种解决方案，在这种方法中，触觉信息由设备获取并传递给外科医生。一个重要的设计因素是将获取的信息反馈给外科医生的方法。然而，目前尚无实现这一目标的系统方法，而且反馈机制实施不当可能会对外科医生的表现产生不利影响。在本研究中，我们提出了一种用于腹腔镜手术中术中肿瘤检测的辅助算法。我们设想的场景是，外科医生操纵一个传感器探头，根据传感器提供的反馈做出决策，与此同时，该算法分析传感器输出的时间序列。因此，该算法通过提供独立的检测结果来协助外科医生做出决策。使用具有三个隐藏层的深度神经网络模型来分析传感器输出。我们提出了将传感器输出的时间序列输入模型进行实时分析的方法，以及确定模型检测标准的方法。本研究旨在通过使用我们之前心理物理学实验中获取的数据来验证该算法的可行性。在该实验中，新手参与者被要求通过触觉传感器的视觉反馈来检测早期胃癌肿瘤的模型。除了分析准确性之外，还采用信号检测理论来评估模型的潜在检测性能。将检测性能与人类参与者的进行比较。我们进行了两种类型的验证，发现如果在模型构建中纳入来自已知用户的数据，模型的检测性能与人类参与者的没有显著差异。该结果支持了所提出的算法在计算机辅助触诊中用于检测辅助的可行性。
