Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2010, Vol. 11 Issue (7): 495-503    DOI: 10.1631/jzus.C0910658
    
Multi-affine registration using local polynomial expansion
Yuan-jun Wang1,2, Gunnar Farneb?ck2, Carl-Fredrik Westin*,2
1 Digital Medical Research Center, Shanghai Medical School, Fudan University, Shanghai 200032, China 2 Lab of Mathematics in Imaging, Brigham and Women\'s Hospital, Harvard Medical School, Boston 02115, MA, USA
Download:   PDF(0KB)
Export: BibTeX | EndNote (RIS)      

Abstract  In this paper, we present a non-linear (multi-affine) registration algorithm based on a local polynomial expansion model. We generalize previous work using a quadratic polynomial expansion model. Local affine models are estimated using this generalized model analytically and iteratively, and combined to a deformable registration algorithm. Experiments show that the affine parameter calculations derived from this quadratic model are more accurate than using a linear model. Experiments further indicate that the multi-affine deformable registration method can handle complex non-linear deformation fields necessary for deformable registration, and a faster convergent rate is verified from our comparison experiment.

Key wordsDeformable registration      Polynomial expansion      Least squares      Multi-affine      Normalized convolution     
Received: 30 October 2009      Published: 06 July 2010
CLC:  TP391.4  
Fund:  Project  supported  by  the  joint  PhD  Program  of  the  China Scholarship Council (CSC), the US National Institutes of Health
(NIH)  (Nos.   R01MH074794  and  P41RR013218),  and  the  Na-tional Natural Science Foundation of China (No.  60972102)
Cite this article:

Yuan-jun Wang, Gunnar Farneb?ck, Carl-Fredrik Westin. Multi-affine registration using local polynomial expansion. Front. Inform. Technol. Electron. Eng., 2010, 11(7): 495-503.

URL:

http://www.zjujournals.com/xueshu/fitee/10.1631/jzus.C0910658     OR     http://www.zjujournals.com/xueshu/fitee/Y2010/V11/I7/495


Multi-affine registration using local polynomial expansion

In this paper, we present a non-linear (multi-affine) registration algorithm based on a local polynomial expansion model. We generalize previous work using a quadratic polynomial expansion model. Local affine models are estimated using this generalized model analytically and iteratively, and combined to a deformable registration algorithm. Experiments show that the affine parameter calculations derived from this quadratic model are more accurate than using a linear model. Experiments further indicate that the multi-affine deformable registration method can handle complex non-linear deformation fields necessary for deformable registration, and a faster convergent rate is verified from our comparison experiment.

关键词: Deformable registration,  Polynomial expansion,  Least squares,  Multi-affine,  Normalized convolution 
[1] Ping Yang, Chao-peng Wu, Yi-lu Guo, Hong-bo Liu, Hui Huang, Hang-zhou Wang, Shu-yue Zhan, Bang-yi Tao, Quan-quan Mu, Qiang Wang, Hong Song. Parameter estimation in exponential models by linear and nonlinear fitting methods[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(3): 434-444.
[2] Jia-yin Song, Wen-long Song, Jian-ping Huang, Liang-kuan Zhu. Segmentation and focus-point location based on boundary analysis in forest canopy hemispherical photography[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(8): 741-749.
[3] Rong Jiao, Lu-ping Xu, Hua Zhang, Cong Li. Orbit determination using incremental phase and TDOA of X-ray pulsar[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(6): 543-552.
[4] Qiang Liu, Jia-chen Ma. Subspace-based identification of discrete time-delay system[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(6): 566-575.
[5] Bang-hua Yang, Liang-fei He, Lin Lin, Qian Wang. Fast removal of ocular artifacts from electroencephalogram signals using spatial constraint independent component analysis based recursive least squares in brain-computer interface[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(6): 486-496.
[6] Gurmanik Kaur, Ajat Shatru Arora, Vijender Kumar Jain. Using hybrid models to predict blood pressure reactivity to unsupported back based on anthropometric characteristics[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(6): 474-485.
[7] Hua-juan Huang, Shi-fei Ding, Zhong-zhi Shi. Primal least squares twin support vector regression[J]. Front. Inform. Technol. Electron. Eng., 2013, 14(9): 722-732.
[8] Shun-wai Zhang, Feng-fan Yang, Lei Tang. An LDPC coded cooperative MIMO scheme over Rayleigh fading channels with unknown channel state information[J]. Front. Inform. Technol. Electron. Eng., 2013, 14(1): 30-41.
[9] Yang-ming Guo, Cong-bao Ran, Xiao-lei Li, Jie-zhong Ma. Adaptive online prediction method based on LS-SVR and its application in an electronic system[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(12): 881-890.
[10] Qing-chao Wang, Jian-zhong Zhang. Wiener model identification and nonlinear model predictive control of a pH neutralization process based on Laguerre filters and least squares support vector machines[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(1): 25-35.