基于B样条自由形变三维医学图像非刚性配准研究

doi:10.7517/j.issn.1674-0475.2014.02.200

影像科学与光化学 ›› 2014, Vol. 32 ›› Issue (2): 200-208.DOI: 10.7517/j.issn.1674-0475.2014.02.200

基于B样条自由形变三维医学图像非刚性配准研究

冯兆美^1,2,3, 党军¹, 崔崤峣¹, 焦阳¹

1. 中国科学院苏州生物医学工程技术研究所, 江苏苏州 215163;
2. 中国科学院长春光学精密机械与物理研究所, 吉林长春 130000;
3. 中国科学院大学, 北京 100049

收稿日期:2013-09-17 修回日期:2013-11-06 出版日期:2014-03-15 发布日期:2014-03-15
通讯作者: 崔崤峣

B-spline Free-form Deformation Based 3-D Non-rigid Registration of Medical Images

FENG Zhaomei^1,2,3, DANG Jun¹, CUI Yaoyao¹, JIAO Yang¹

1. Suzhou Institute Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou 215163, Jiangsu, P.R. China;
2. Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130000, Jilin, P.R. China;
3. University of Chinese Academy of Sciences, Beijing 100049, P.R. China

Received:2013-09-17 Revised:2013-11-06 Online:2014-03-15 Published:2014-03-15

摘要/Abstract

摘要：

医学超声成像具有成本低、实时成像等优势，基于超声的多模态配准在临床诊断、病情监测、外科手术等应用上具有较大的意义。三维医学图像能够清晰地显示病变大小、形态，提供相对完整的人体组织的三维结构信息。本文采用基于B样条自由形变模型的非刚性配准方法对三维超声图像和计算机断层扫描图像（Computed Tomography，CT）进行配准，利用薄板样条能量约束项解决三维图像配准过程中的图像交叉与重叠问题。此外，使用仿体数据以及临床数据验证算法性能，通过感兴趣区域的相对重叠率，互信息值和程序运行时间这三个指标对算法精度和速度进行评价。其中Demons方法平均耗时1896 s，本文改进算法平均耗时195 s，运行效率提高8.7倍；算法改进前后的感兴趣区域重叠率分别是89.58%和91.35%，精度提高2.0%。实验结果表明此算法能够对超声和CT图像进行配准并获得较好的结果。

关键词: 非刚性图像配准, 互信息, 自由形变模型, 超声图像, CT图像

Abstract:

Ultrasound imaging has been widely used because of its inherent advantages compared with others imaging modalities. It plays a positive role in clinical diagnosis, monitoring and surgery. Three-dimensional medical images could clearly show the size, shape of the lesion and provide relatively complete three-dimensional structure information of human tissue. In this paper, a non-rigid registration based on B-spline free form deformation for three-dimensional ultrasound (US) and Computed Tomography Compared (CT) was studied with thin-plate spline energy constraint solving image cross and overlap. In addition, we took relative overlap, mutual information and computation time as evaluation criteria to evaluate the performance of nonrigid registration algorithm for breast phantom images and clinical images. The demons method took an average of 1896 seconds, the improved algorithm took an average of 195 seconds, the efficiency increased by 8.7 times. The relative overlap was 89.58 percent of the original algorithm and the relative overlap was 91.35 percent of the improved algorithm, the accuracy was increased by 2.0 percent. The experiment results showed that the algorithm could achieve better registration results.

Key words: non-rigid registration, mutual information, free form deformation, ultrasound image, CT image

冯兆美, 党军, 崔崤峣, 焦阳. 基于B样条自由形变三维医学图像非刚性配准研究[J]. 影像科学与光化学, 2014, 32(2): 200-208.

FENG Zhaomei, DANG Jun, CUI Yaoyao, JIAO Yang. B-spline Free-form Deformation Based 3-D Non-rigid Registration of Medical Images[J]. Imaging Science and Photochemistry, 2014, 32(2): 200-208.

参考文献

[1] Brown L G. A survey of image registration techniques[J]. ACM Computing Surveys (CSUR), 1992, 24(4): 325-376.
[2] 田捷, 戴晓倩, 杨飞. 医学成像与医学图像处理教程[M]. 北京:清华大学出版社, 2013.152-229. Tian J, Dai X Q, Yang F. Medical Imaging and Medical Images Processing[M]. Beijing: Tsinghua University Press, 2013. 187-189.
[3] Wein W, Brunke S, Khamene A, et al. Automatic ct-ultrasound registration for diagnostic imaging and image-guided intervention[J]. Medical Image Analysis, 2008, 12(5): 577-585.
[4] 卢振泰, 陈武凡.基于主成分分析的三维医学图像快速配准算法[J].南方医科大学学报, 2008, 28(9):1591-1593. Lu Z T, Chen W F. A fast 3-d medical image registration algorithm using principal component analysis[J]. Journal of Southern Medical University, 2008, 28(9): 1591-1593.
[5] Rueckert D, Sonoda L I, Hayes C, et al. Nonrigid registration using free-form deformations: application to breast MR images[J]. IEEE Transactions on Medical Imaging, 1999, 18(8): 712-721.
[6] Roche A, Pennec X, Malandain G, et al. Rigid registration of 3-d ultrasound with MR images: a new approach combining intensity and gradient information[J]. IEEE Transactions on Medical Imaging, 2001, 20(10): 1038-1049.
[7] Tanner C, Karssemeijer N, Székely G. Deformation models for registering MR and 3d ultrasound breast images[C]. IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2011.582-585.
[8] Holden M. A review of geometric transformations for nonrigid body registration[J]. IEEE Transactions on Medical Imaging, 2008, 27(1): 111-128.
[9] Pluim J P W, Maintz J B A, Viergever M A. Mutual-information-based registration of medical images: a survey[J]. IEEE Transactions on Medical Imaging, 2003, 22(8): 986-1004.
[10] Zou X L, Navon M, Berger M, et al. Numerical experience with limited-memory quasi-newton and truncated newton methods[J]. SIAM Journal on Optimization, 1993, 3(3): 582-608.
[11] Mattes D, Haynor D R, Vesselle H, et al. Pet-ct image registration in the chest using free-form deformations[J]. IEEE Transactions on Medical Imaging, 2003, 22(1): 120-128.
[12] Rueckert D, Aljabar P, Heckemann R A, et al. Diffeomorphic registration using b-splines[C]. Medical Image Computing and Computer-assisted Intervention Miccai 2006. 2006, Springer. p. 702-709.
[13] Xie Z Y, Farin G E. Image registration using hierarchical b-splines[J]. IEEE Transactions on Visualization and Computer Graphics, 2004, 10(1): 85-94.
[14] Maes F, Collignon A, Vandermeulen D, et al. Multimodality image registration by maximization of mutual information[J]. IEEE Transactions on Medical Imaging, 1997, 16(2): 187-198.
[15] Nocedal J. Updating quasi-newton matrices with limited storage[J]. Mathematics of Computation, 1980, 35(151): 773-782.
[16] Likar B, Pernu F. A hierarchical approach to elastic registration based on mutual information[J].Image and Vision Computing, 2001, 19(1): 33-44.
[17] Klein S, Staring M, Pluim J P W. Evaluation of optimization methods for non-rigid medical image registration using mutual information and b-splines[J]. IEEE Transactions on Image Processing, 2007, 16(12): 2879-2890.
[18] Christensen G E, Geng X J, Kuhl J G, et al. Introduction to the non-rigid image registration evaluation project[R]. Biomedical Image Registration, 2006. Springer. 128-135.
[19] Vercauteren T, Pennec X, Perchant A, et al. Diffeomorphic demons: efficient non-parametric image registration[J]. NeuroImage, 2009, 45(1): S61-S72.

基于B样条自由形变三维医学图像非刚性配准研究

B-spline Free-form Deformation Based 3-D Non-rigid Registration of Medical Images

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价