一种面向多模态手术轨迹的快速无监督分割方法  

Fast Unsupervised Approach for Multi-modality Surgical Trajectory Segmentation

作　　者：邵振洲 赵红发 渠瀛[4] 施智平[1,3] 关永 袁慧梅[1] SHAO Zhen-zhou;ZHAO Hong-fa;QU Ying;Sill Zhi-ping;GUAN Yong;YUAN Hui-mei(Information Engineering College,Capital Normal University,Beijing 100048,China;Beijing Key Laboratory of Light Industrial Robot and Safety Verification,Capital Normal University,Beijing 100048,China;Beijing Advanced Innovation Center for Imaging Technology,Capital Normal University,Beijing 100048,China;Department of Electrical Engineering and Computer Science,The University of Tennessee,Tennessee 37996,USA)

机构地区：[1]首都师范大学信息工程学院,北京100048 [2]首都师范大学轻型工业机器人与安全验证北京市重点实验室,北京100048 [3]成像技术北京市高精尖创新中心,北京100048 [4]田纳西大学诺克斯维尔分校工程学院,田纳西美国37996

出　　处：《小型微型计算机系统》2018年第10期2296-2302,共7页Journal of Chinese Computer Systems

基　　金：北京市教委科研计划一般项目(KM201710028017)资助;北京市教委科研基地建设项目(TJSHG201310028014)资助;北京市优秀人才培养青年骨干个人项目(2014000020124G135)资助;国家自然科学基金项目(61702348;61772351;61572331;61472468;61602325;61373034)资助;国家科技支撑计划项目(2015BAF13B01)资助;国际科技合作计划项目(2011DFG13000)资助;北京市科委项目(Z141100002014001)资助;北京市属高等学校创新团队建设与教师职业发展计划项目(IDHT20150507)资助.

摘　　要：基于视频和机器人运动学数据的多模态手术轨迹分割是机器人辅助微创手术中的一类基本任务,用于生成低复杂度的子任务进行学习和技能评估等.然而由于手术视频的高维特征空间,传统的特征提取方法存在效率低下、难以提取有效特征的缺陷.此外,传统轨迹分割方法未对运动学轨迹进行去噪处理,分割结果易受噪声影响.为此,本文提出了一种基于手术视频和机器人运动学数据的快速手术轨迹无监督分割方法.一方面,采用堆叠卷积自编码器方法对手术视频进行无监督的低维特征提取,提高特征提取的效率;另一方面,利用小波变换对手术运动学轨迹进行多尺度去噪处理,平滑短程轨迹,减少噪声对分割结果的影响.最后,采用非参混合模型实现手术轨迹的分割.实验表明,本文提出的手术轨迹分割方法能够在保证准确性的前提下,基于视觉和运动学特征的分割速度相较于基于深度学习转移状态聚类(TSC-DL)提高了10倍.As the key task in robot-assisted mirfimally invasive surgery, the multi-modality trajectory segmentation with videos and ki- nematics sources is commonly used to generate the subtasks with low complexity for the skill learning and assessment. However, due to the high-dimensional features of surgical videos, traditional feature extraction approaches are inefficient to extract effective features. In addition, the segmentation results are susceptible to the noise in the raw kinematic data. To address above problems, this paper proposes a fast unsupervised method for surgical trajectory segmentation by the fusion of surgical video and kinematic data. On the one hand,the low-dimensional features are extracted from surgical video based on the stacking convolutional auto-encoder to improve the efficiency of feature extraction. On the other hand, the kinematic data are firstly filtered at multiple scales using wavelet transform to get rid of the noise. A nonparametric mixture model is finally employed to segment the surgical trajectory. Experimental results show that the proposed method improves the efficiency compared to TSC-DL by 10 times with the accuracy of segmentation guaranteed.

关 键 词：机器人辅助微创手术 轨迹分割 堆叠卷积自编码 小波平滑 深度学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]