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.
YANG Keke, LUO Yang, ZHAO Yiwen, ZHAO Xingang, SONG Guoli. 2D/3D Hierarchical Registration Based on Principal Direction Fourier Transform Operator[J]. ROBOT, 2021, 43(3): 296-307.
 Citation: YANG Keke, LUO Yang, ZHAO Yiwen, ZHAO Xingang, SONG Guoli. 2D/3D Hierarchical Registration Based on Principal Direction Fourier Transform Operator[J]. ROBOT, 2021, 43(3): 296-307.

## 2D/3D Hierarchical Registration Based on Principal Direction Fourier Transform Operator

• 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On6）降到On2），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．

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.

/

• 分享
• 用微信扫码二维码

分享至好友和朋友圈