北京生物医学工程

基于图像识别的血管介入器械追踪方法

Instrument tracking methods of vascular intervention based on image recognition

作者：周国敬梁世超李振锋梅玉倩熊江陈端端

单位：北京理工大学生命学院(北京100081)  中国人民解放军总医院血管外科(北京100853) 通信作者:梅玉倩。E-mail:mei.yuqian@bit.edu.cn

分类号：R318. 04

出版年·卷·期（页码）：2022·41·1（90-96）

摘要：

血管疾病已成为威胁人类健康的首要疾病，微创介入手术是其主要治疗方法。但其手术过程较为依赖医生经验，如何量化介入手术操作经验,从而形成手术操作知识体系，服务于术者操作和手术机器人控制,是当前血管介入领域研究的热点。针对这一问题，对手术操作过程中植介入器械的追踪是量化手术操作的基础,亦是研究手术器械输送过程运动学关键参数的必要条件，本文针对血管介入手术过程中基于图像识别算法的器械追踪方法开展总结性研究。首先，针对血管介入手术过程中器械追踪的相关技术进行系统总结和阐述;其次,针对基于图像识别算法的血管介入器械追踪方法,根据其追踪过程是否具有检测环节，分为“生成式”追踪和“判别式”追踪两类进行总结和阐述，重点归纳了基于机器视觉和深度学习的相关算法及其流程;最后，本文针对血管介入操作过程的器械追踪方法进行了较全面的总结，提出考虑到临床应用研究对时效性和准确性兼顾的需求，以“判别式”追踪为核心的算法更适合于血管介入手术器械追踪，并具有嵌入到手术机器人的潜力，为相关领域的科研工作者提供参考，并对后续研究方向做以展望。

The vascular disease has become the leading disease that threatens human lives and health, and the minimally invasive intervention is the principal therapeutic method. However, operations of the type are highly dependent on surgeon experience. Currently, it is a hot point to quantify the surgical operation experience in order to construct a surgical operation knowledge system, which provides services for operators and the control of surgical robots. In response to this challenge, tracking of implanted interventional instruments during surgical operations is the basis for the quantification and is also a necessary condition for studying key kinematics parameters in the course of surgical instrument delivery. This article conducts a summary study on the instrument tracking methods based on image recognition algorithm among endovascular interventional procedures. First, systematically elaboration and summary on relevant technique of instrument tracking methods for vascular interventional operation are conducted, after which instrument tracking methods of vascular intervention based on image recognition algorithm are divided by the existence of a detection link into two categories, including “generative" tracking and u discriminativew tracking and the related algorithms and flowcharts based on machine vision and deep learning are mainly achieved. Finally, this article provides a comprehensive summary of the instrument tracking methods during vascular interventional procedures. We conclude that the algorithm with u discriminatoryw tracking as the core is more suitable for vascular intervention surgical instrument tracking considering the timeliness and accuracy demand in clinical application research, which also has the potential to be embedded in surgical robots and provides a reference for scientific researchers in related fields. Furthermore, prospects for follow-up research directions are delineated.

参考文献：

[1]中国心血管健康与疾病报告编写组.中国心血管健康与疾病报告2019概要[J].中国循环杂志,2020,35(9):833-854.

The?Writing Committee of the Report on Cardiovascular Health and Diseases in China. Report on cardiovascular health and diseases in China 2019: an updated summary?[ J ] . Chinese Circulation Journal，2020,35(9):833-854.

[2] Fattori R, Cao P, de Rango P, et al. Interdisciplinary expert consensus document on management of type B aortic dissection [J]. Journal of the American College of Cardiology, 2013, 61(16): 1661-78.

[3] Jian G , Xiaoliang J , Shuxiang G . Study of the operational safety of a vascular interventional surgical robotic system[J]. Micromachines, 2018, 9(3):119-137.

[4] Bao X , Guo S , Xiao N , et al. A cooperation of catheters and guidewires-based novel remote-controlled vascular interventional robot[J]. Biomedical Microdevices, 2018, 20(1):20-38.

[5] Toossi MTB , Mehrpouyan M , Nademi H , et al. Preliminary results of an attempt to predict over apron occupational exposure of cardiologists from cardiac fluoroscopy procedures based on DAP (dose area product) values[J]. Australasian Physical & Engineering Sciences in Medicine, 2015, 38(1):83-91.

[6] Matthews I, Ishikawa T, Baker S. The template update problem[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2004,26(6):810-815.

[7] Comaniciu?D，Ramesh V，Meer?P, et al. Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003,25(5):564-577.

[8] Hu HW，Ma B，Wu YW, et al. Kernel regression based online boosting tracking[J]. Journal of Information Science and Engineering: JISE, 2015, 31(1): 267-282.

[9] Yang F , Lu H , Yang MH . Robust visual tracking via multiple kernel boosting with affinity constraints[J]. IEEE Transactions on Circuits & Systems for Video Technology, 2014, 24(2):242-254.

[10] Ma YL , Alhrishy M , Ananth Narayan S , et al. A novel real-time computational framework for detecting catheters and rigid guidewires in cardiac catheterization procedures[J]. Medical Physics, 2018, 45(11):5066-5079.

[11] Honnorat N , Régis Vaillant, Paragios N .

Graph-Based Geometric-Iconic Guide-Wire Tracking[C]// Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention，?2011,14(Pt 1):9-16.

[12] Chang PL , Rolls A , Praetere HD , et al. Robust catheter and guidewire tracking using B-spline tube model and pixel-wise posteriors[J]. IEEE Robotics & Automation Letters, 2017, 1(1):303-308.

[13] Chen BJ , Wu Z , Sun S , et al. Guidewire tracking using a novel sequential segment optimization method in interventional X-ray videos[C]// 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). Prague ：IEEE, 2016:103-106.

[14] Wang P , Chen T , Zhu Y , et al. Robust guidewire tracking in fluoroscopy[C]// IEEE Conference on Computer Vision & Pattern Recognition.?Miami, FL：IEEE, 2009:691-698.

[15]Yang?H,Jiang?X，Gao?S. Adaptive compressive tracking algorithm based on SIFT features[C]// ?IEEE Conference on Robot, Vision and Signal Processing (RVSP).?Taiwan：Kaohsiung, 2015:78-81.

[16] Vandini A, Glocker B, Hamady M, et al. Robust guidewire tracking under large deformations combining segment-like features (SEGlets) [J]. Medical Image Analysis, 2017, 38:150-164.

[17] Mehmood R, Iqbal N, Tahir A, et al. Real time 3D representation and tracking of guidewire for image guided cardiovascular interventions [J]. Advances in Experimental Medicine and Biology，2017, 989:165-176.

[18] Wang C , Wang W . A method for guide wire tracking in X-Ray angiographic images based on open active contours[C]// IEEE International Conference on Signal Processing. Hong Kong：IEEE, 2016:624-627.

[19] Zeng Y , Xiao N , Guo S , et al. Catheter tracking based on multi-scale filter and direction-oriented method[C]// 2018 IEEE International Conference on Mechatronics and Automation (ICMA). Changchun:IEEE, 2018:620-625.

[20] Shi P, Guo S, Zhang L, et al. Guidewire tracking based on visual algorithm for endovascular interventional robotic system [C] // 2019 IEEE International Conference on Mechatronics and Automation (ICMA). Tianjin：IEEE, 2019:2235-2239.

[21] Zhou YJ , Xie XL , Zhou XH , et al. Pyramid attention recurrent networks for real-time guidewire segmentation and tracking in intraoperative X-ray fluoroscopy[J]. Computerized Medical Imaging and Graphics, 2020, 83:101734.

[22] Wang L, Xie XL, Gao ZJ,?et?al. Guide-wire detecting using a modified cascade classifier in interventional radiology[C]// Engineering in Medicine & Biology Society. Orlando：IEEE, 2016:1240-1243.

[23] Ambrosini P , Ruijters D , Niessen WJ , et al. Fully automatic and real-time catheter segmentation in X-ray fluoroscopy[C]// ?Lecture Notes in Computer Science.?Quebec City：20th International Conference,2017:577-585.

[24] Li D , Barbu A . Training a CNN for Guidewire Detection[C]// 2019 IEEE International Conference on Image Processing (ICIP). Taipei：IEEE, 2019:2214-2218.

[25] Ma YL , Alhrishy M , Panayiotou M , et al. Real-time guiding catheter and guidewire detection for congenital cardiovascular interventions[C]// International Conference on Functional Imaging and Modeling of the Heart. Functional Imaging and Modelling of the Heart.?Toronto, ON, Canada :9th International Conference, 2017:172-182.

[26] Ullah I , Chikontwe P , Park SH . Guidewire tip tracking using u-net with shape and motion constraints[C]// 2019 International Conference on Artificial Intelligence in Information and Communication, Okinawa, Japan, ICAIIC:2019:215-217.

[27] Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.

[28] Ma H , Smal I , Daemen J , et al. Dynamic coronary roadmapping via catheter tip tracking in X-ray fluoroscopy with deep learning based bayesian filtering[J]. Medical Image Analysis, 2020, 61:101634.

[29] Gherardini M, Mazomenos E, Menciassi A, et al. Catheter segmentation in X-ray fluoroscopy using synthetic data and transfer learning with light U-nets [J]. Computer Methods and Programs in Biomedicine, 2020, 192:105420.

[30] Ambrosini?P, Ruijters?D, Niessen?WJ, et al. Fully automatic and real-time catheter segmentation in X-ray fluoroscopy[C]// 2017 International Conference on Medical Image Computing and Computer-Assisted Intervention.?Lima, Peru :MICCAI, 2017:577–585.

[31] Baur C, Albarqouni S, Demirci S, et al. CathNets: detection and single-view depth prediction of catheter electrodes [C]// 2016 International Conference on Medical Imaging & Virtual Reality(MIVR).?Bern, Switzerland:?Medical Imaging and Augmented Reality ,2016:38-49.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录