基于主方向傅里叶变换算子的2D/3D分级配准

doi:10.13973/j.cnki.robot.200425

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (698 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
杨克克, 罗阳, 赵忆文, 赵新刚, 宋国立. 基于主方向傅里叶变换算子的2D/3D分级配准[J]. 机器人, 2021, 43(3): 296-307.DOI: 10.13973/j.cnki.robot.200425. YANG Keke, LUO Yang, ZHAO Yiwen, ZHAO Xingang, SONG Guoli. 2D/3D Hierarchical Registration Based on Principal Direction Fourier Transform Operator. ROBOT, 2021, 43(3): 296-307. DOI: 10.13973/j.cnki.robot.200425.

摘要目前的2D/3D医学图像配准方法的配准精度和效率存在矛盾，配准捕获范围小．为解决这些问题，本文提出一种基于主方向傅里叶变换算子的分级配准方法．首先，提出平面旋转平移不变性算子——主方向傅里叶变换算子．然后，提出基于主方向傅里叶变换算子的模板匹配初始化方法，可避免接近真值的初值需求，并显著扩大了捕获范围．最后，提出基于主方向傅里叶变换算子的分级配准框架，将配准搜索空间从O（n⁶）降到O（n²），在保证配准精度的情况下大幅提高配准效率．在配准实验中，本文方法的配准精度为0.68 mm ±0.28 mm，配准时间为16.87 s ±3.77 s，捕获范围大于100 mm．因此，所提出的基于主方向傅里叶变换算子的分级配准方法可以满足2D/3D图像配准在相关临床应用中精度、效率及捕获范围的需求．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	杨克克
	罗阳
	赵忆文
	赵新刚
	宋国立

关键词 ： 2D/3D配准, 配准框架, 主方向, 傅里叶变换, 力矩

Abstract：This paper aims to solve the problems of the contradiction between the registration accuracy and the efficiency, and also the small registration capture range in the current 2D/3D medical image registration research. A hierarchical registration method based on principal direction Fourier transform operator (PDFTO) is proposed. Firstly, an operator with invariance of in-plane rotation and translation, PDFTO, is proposed. Then, a PDFTO-based template matching initialization method is proposed, which can avoid the requirement of an initial value that should be close to the true value, and can significantly expand the capture range. Finally, a hierarchical registration framework based on PDFTO is proposed, which reduces the searching space of registration from O(n⁶) to O(n²), and greatly improves the efficiency of registration while ensuring the accuracy of registration. In the registration experiments, the registration accuracy of the proposed method is 0.68 mm ±0.28 mm, the registration time is 16.87 s ±3.77 s, and the capture range is larger than 100 mm. Therefore, the proposed PDFTO-based hierarchical registration method can meet the requirements for the accuracy, the efficiency and the capture range in 2D/3D image registration in related clinical applications.

Key words： 2D/3D registration registration framework principal direction Fourier transform moment

收稿日期: 2020-10-19 【基金专刊】 录用日期: 2021-04-09

TP391

基金资助:国家重点研发计划（2017YFB1303003）；国家自然科学基金（62073314，61821005）；中国科学院青年创新促进会（2019205）；中国博士后科学基金（2020M670815）．

通讯作者: 宋国立，songgl@sia.cn E-mail: songgl@sia.cn

作者简介: 杨克克（1996–），女，硕士生．研究领域：医学图像配准
罗阳（1989–），男，博士，副研究员．研究领域：机器人技术与系统
赵忆文（1972–），男，博士，研究员．研究领域：特种机器人，医疗机器人，智能机器人技术，机器人自主控制．

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.200425 或 https://robot.sia.cn/CN/Y2021/V43/I3/296

[1] Tang T S Y, Ellis R E, Fichtinger G. Fiducial registration from a single X-ray image: A new technique for fluoroscopic guidance and radiotherapy[M]//Lecture Notes in Computer Science, Vol.1935. Berlin, Germany: Springer, 2000: 502-511.
[2] Wang J, Schaffert R, Borsdorf A, et al. Dynamic 2-D/3-D rigid registration framework using point-to-plane correspondence model[J]. IEEE Transactions on Medical Imaging, 2017, 36(9): 1939-1954.
[3] Livyatan H, Yaniv Z, Joskowicz L. Gradient-based 2-D/3-D rigid registration of fluoroscopic X-ray to CT[J]. IEEE Transactions on Medical Imaging, 2003, 22(11): 1395-1406.
[4] 陈智强，王作伟，方龙伟，等. 基于机器学习和几何变换的实时2D/3D脊椎配准[J].自动化学报， 2018， 44(7)： 1183-1194. Chen Z Q, Wang Z W, Fang L W, et al. Real-time 2D/3D registration of vertebra via machine learning and geometric transformation[J]. Acta Automatica Sinica, 2018, 44(7): 1183-1194.
[5] Meng C, Wang Q, Guan S Y, et al. Weighted local mutual information for 2D-3D registration in vascular interventions [M]//Lecture Notes in Computer Science, Vol.11004. Berlin, Germany: Springer, 2018: 376-385.
[6] Meng C, Wang Q, Guan S Y, et al. 2D-3D registration with weighted local mutual information in vascular interventions[J]. IEEE Access, 2019, 7: 162629-162638.
[7] 王杨. 基于迭代回归的2D/3D多模态医学图像配准[D]. 成都：电子科技大学， 2020. Wang Y. 2D/3D multi-modal medical image registration based on iterative regression[D]. Chengdu: University of Electronic Science and Technology of China, 2020.
[8] 张冉，王雷，夏威，等. 2D/3D图像配准中的相似性测度和优化算法[J].激光与红外， 2014， 44(1)： 98-102. Zhang R, Wang L, Xia W, et al. Comparison of similarity measurement and optimization methods in 2D/3D image registration[J]. Laser & Infrared, 2014, 44(1): 98-102.
[9] Gui P, Ling W K, Zhang D Y, et al. Cross-cumulative residual entropy-based medical image registration via hybrid differential search algorithm[J]. International Journal of Imaging Systems and Technology, 2019, 29(4): 701-710.
[10] Chen S J, Shen H L, Li C G, et al. Normalized total gradient: A new measure for multispectral image registration[J]. IEEE Transactions on Image Processing, 2017, 27(3): 1297-1310.
[11] Karthick S, Maniraj S. Different medical image registration techniques: A comparative analysis[J]. Current Medical Imaging, 2019, 15(10): 911-921.
[12] Gòmez O, Ibanez O, Valsecchi A, et al. 3D-2D silhouette-based image registration for comparative radiography-based forensic identification[J]. Pattern Recognition, 2018, 83: 469-480.
[13] Esfandiari H, Anglin C, Guy P, et al. A comparative analysis of intensity-based 2D-3D registration for intraoperative use in pedicle screw insertion surgeries[J]. International Journal of Computer Assisted Radiology and Surgery, 2019, 14: 1725- 1739.
[14] Aksoy T, Špiclin Ž, Pernuš F, et al. Monoplane 3D-2D registration of cerebral angiograms based on multi-objective stratified optimization[J]. Physics in Medicine and Biology, 2017, 62(24). DOI: 10.1088/1361-6560/aa9474.
[15] Varnavas A, Carrell T, Penney G. Fully automated 2D-3D registration and verification[J]. Medical Image Analysis, 2015, 26(1): 108-119.
[16] Miao S. Effective image registration for motion estimation in medical imaging environments[D]. Vancouver, Canada: The University of British Columbia, 2016.
[17] Miao S, Wang Z J, Liao R. A CNN regression approach for real-time 2D/3D registration[J]. IEEE Transactions on Medical Imaging, 2016, 35(5): 1352-1363.
[18] Otake Y, Wang A S, Stayman J W, et al. Robust 3D-2D image registration: Application to spine interventions and vertebral labeling in the presence of anatomical deformation[J]. Physics in Medicine & Biology, 2013, 58(23). DOI: 10.1088/0031- 9155/58/23/8535.
[19] Kaiser M, John M, Heimann T, et al. 2D/3D registration of TEE probe from two non-orthogonal C-arm directions[M]//Lecture Notes in Computer Science, Vol.8673. Berlin, Germany: Springer, 2014: 283-290.
[20] Aksoy T, Unal G, Demirci S, et al. Template-based CTA to x-ray angio rigid registration of coronary arteries in frequency domain with automatic x-ray segmentation[J]. Medical Physics, 2013, 40(10). DOI: 10.1118/1.4819938.