基于几何特征不变量的快速3D医学图像配准

doi:10.16182/j.issn1004731x.joss.19-FZ0402E

系统仿真学报 ›› 2020, Vol. 32 ›› Issue (11): 2105-2111.doi: 10.16182/j.issn1004731x.joss.19-FZ0402E

基于几何特征不变量的快速3D医学图像配准

顾菊平^1,2, 程天宇², 王建平¹, 华亮¹, 赵凤申¹, 蒋凌¹

1.南通大学电气工程学院,江苏南通 226019;
2.南京理工大学自动化学院,江苏南京 210094

收稿日期:2019-05-06 修回日期:2019-08-02 出版日期:2020-11-18 发布日期:2020-11-17

Fast 3D Medical Image Registration Based on Geometric Feature Invariants

Gu Juping^1,2, Cheng Tianyu², Wang Jianping¹, Hua Liang¹, Zhao Fengshen¹, Jiang Ling¹

1. School of Electrical Engineering,Nantong University,Nantong 226019,China;
2. School of Automation,Nanjing University of Science and Technology,Nanjing 210094,China

Received:2019-05-06 Revised:2019-08-02 Online:2020-11-18 Published:2020-11-17
About author:Gu Juping (1971-),female,Nantong,Jiangsu,Doctor,Professor,research direction:motor and its control,medical image processing.
Supported by:
National Natural Science Foundation (61673226),Major Natural Science Research Project of Jiangsu Higher Education Institutions (18KJA470003)

摘要/Abstract

摘要： 针对颅部三维医学图像配准计算量大、配准效率低等问题,提出了一种基于几何特征空间约束的快速配准方法。提取三维轮廓点云,提出了一种基于点云集最优拟合环的特征构造方法,并以每个特征环和每个层的质心用作特征量,通过使用迭代最近点(Iterative Closest Point, ICP)方法完成快速配准。实验结果表明,与传统的ICP算法相比,该方法计算量小,配准精度高,配准速度快。它是一种有效的实时三维配准方法。

关键词: 3D医学图像, 快速配准, 几何特征不变量, 迭代最近点

Abstract: Aiming at the of large amount of computational data and low registration efficiency in 3D cranial medical image registration, a fast registration method based on geometric feature space constraints is proposed. The algorithm extracts three-dimensional contour point clusters, and proposes a feature construction method based on the optimal fitting ring of point clusters. The feature rings and the centroids of each layer are used as feature quantities, and the fast registration is completed by using Iterative Closest Point (ICP) method. The experimental results show that the method has less computation amount, high satisfactory registration accuracy and much faster registration speed than the traditional ICP algorithm. It is an effective real-time three-dimensional registration method.

Key words: 3D medical image, fast registration, geometric feature invariants, iterative closest point

中图分类号:

TP301.6

顾菊平, 程天宇, 王建平, 华亮, 赵凤申, 蒋凌. 基于几何特征不变量的快速3D医学图像配准[J]. 系统仿真学报, 2020, 32(11): 2105-2111.

Gu Juping, Cheng Tianyu, Wang Jianping, Hua Liang, Zhao Fengshen, Jiang Ling. Fast 3D Medical Image Registration Based on Geometric Feature Invariants[J]. Journal of System Simulation, 2020, 32(11): 2105-2111.

参考文献

[1] Patel M I,Thakar V K,Shah S K.Image Registration of Satellite Images with Varying Illumination Level Using HOG Descriptor Based SURF[J].Procedia Computer Science(S1877-0509),2016,93:382-388.
[2] Cao W M,Lyu F F,He Z H,et al.Multi-modal Medical Image Registration Based on Feature Spheres in Geometric Algebra[J].IEEE Access(S2169-3536),2018,6:21164-21172.
[3] Aganj I,Fischl B.Multimodal image registration through simultaneous segmentation[J].IEEE Signal Processing Letters(S1070-9908),2017,24(11):1661-1665.
[4] Woo J,Stone M,Prince J L.Multimodal Registration Via Mutual Information Incorporating Geometric and Spatial Context[J].IEEE Transactions on Image Processing(S1057-7149),2015,24(2):757-769.
[5] Li F,Hitchens C,Stoddart D.A performance Evaluation Method to Compare the Multi-view Point Cloud Data Registration Based on ICP Algorithm and Reference Marker[J].Journal of Modern Optics(S0950-0340),2018,65(1):30-37.
[6] Wu Z,Chen H,Du S,et al.Correntropy Based Scale ICP Algorithm for Robust Point Set Registration[J].Pattern Recognition(S0031-3203),2019,93(9):14-24.
[7] Pradhan S,Patra D.Enhanced Mutual Information Based Medical Image Registration[J].Iet Image Processing(S1751-9659),2016,10(5):418-427.
[8] Almhdie A,Deriche M.3D Registration Using a New Implementation of the ICP Aalgorithm Based on a Comprehensive Lookup Matrix:Application to Medical Imaging[J].Pattern Recognition Letters(S0167-8655),2007,28(12):1523-1533.
[9] Du S Y,Liu J,Bi B,et al.New Iterative Closest Point Algorithm for Isotropic Scaling Registration of Point Sets with Noise[J].Journal of Visual Communication and Image Representation(S1047-3203),2016,38:207-216.
[10] Hua L,Cheng T Y,Gu J P.3D Medical Image Registration Based on Clifford Relative Invariant and Region of Interest[J].Journal of Graphics(S2095-302X),2017,38(1):90-96.

基于几何特征不变量的快速3D医学图像配准

Fast 3D Medical Image Registration Based on Geometric Feature Invariants

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价