|
|
|
| Performance Comparison of Optimization Methods for Medical Image Registration
|
| College of Computer Science and Technology, Hunan University of Arts and Science
Changde, Hunan 415000, China |
|
|
|
|
Abstract In the process of medical image registration, the registration function (also so-called similarity metric)
was taken as the objective function, and the multi-parameter optimization method as the tool for
obtaining the optimal transformation parameters. In this paper, by the use of the mutual information
as the registration function, the Powell method and the genetic algorithm were exerted to explore the
optimal transformation parameters respectively, and their optimizing performances were evaluated and
compared. The experimental results reveal that the Powell method can cater to both the mono- and
multi-modality medical image registrations. Unfortunately, however, the genetic algorithm is not adopted
for the medical image registration regardless of the registration accuracy or the running time and needs
to be significantly improved.
|
|
|
| Fund:Project supported by the key Scientific Research Fund of Hunan Provincial Education Department, P. R.
China (No. 13A064); the Construct Program of the key Discipline in Hunan University of Arts and Science; the
Doctor Scientific Research Startup Project Foundation of Hunan University of Arts and Science.
|
|
|
|
| Cite this article: |
|
Meisen Pan,Jianjun Jiang,Fen Zhang, et al. Performance Comparison of Optimization Methods for Medical Image Registration
[J]. Journal of Fiber Bioengineering and Informatics, 2014, 7(4): 507-516.
|
|
| [1] Lu ZT, Feng YQ, Feng QJ. Medical image registration based on principal phase congruency. ACTA
ELECTRONICA SINICA 2008; 36: 1974-1978.
[2] Feng YC, Li XF, Zhang XL, et al. A fast rigid registration algorithm for medical images. J Fiber
Bioeng Inform 2014; 7(3): 409-418.
[3] Nejati M, Pourghassem H. Multiresolution image registration in digital X-ray angiography with
intensity variation modeling. J MED SYST 2014; 38: 10-18.
[4] Ba·gc U, Udupa KJ, Li B. The role of intensity standardization in medical image registration.
Pattern Recogn Lett 2010; 31: 315-323.
[5] Geng XJ, Christensen EG, Gu H, Thomas JR. Implicit reference-based group-wise image registra-
tion and its application to structural and functional MRI. Neuroimage 2009; 47: 1341-1351.
[6] Pan MS, Jiang JJ, Rong QS. A modified medical image registration. Multimed Tools Appl 2014;
70: 1585-1615.
[7] Liu Y, Cheng HD, Huang JH. An e®ective non-rigid registration approach for ultrasound image
based on "demons" algorithm. J DIGIT IMAGING 2013; 26: 521-529.
[8] Paul V, William M, Wells I. Alignment by maximization of mutual information. Int J Comput
Vision 1997; 24: 137-154.
[9] Fei B, Wheaton A, Lee Z. Automatic MR volume registration and its evaluation for the pelvis and
prostate. Phys Med Biol 2002; 47: 823-838.
[10] Slomka PJ, mandel J, Downey D. Evaluation of voxel-based registration of 3-D power doppler
ultrasound and 3-D magnetic resonance angiographic images of carotid arteries. Ultrasound Med
Biol 2001; 27: 945-955.
[11] Liu W, Ribeiro E. Incremental variations of image moments for nonlinear image registration.
SIGNAL IMAGE VIDEO P 2014; 8: 423-432.
[12] Andersson JL, Sundin A, Valind S. A method for coregistration of PET and MR brain image. J
Nucl Med 1995; 36: 1307-1315.
[13] Borgefors G. Hierarchical chamfer matching: a parametric edge matching algorithm. IEEE T
Pattern Anal 1988; 10: 849-865.
[14] Pan MS, Tang JT, Yang XL. Medical Image Registration Based on SVD and Modi¯ed PSNR. J
Inf Sci Eng 2011; 27: 1761-1775.
[15] Pan MS, Tang JT, Yang XL. An algorithm for medical image tilt correction using B-spline and
moment invariants. ICIC Express Letters 2010; 4: 57-63.
[16] Pan MS, Tang JT, Yang XL. Tilt correction methods for CT and MR medical images. Biomed
Eng-App Bas C 2010; 22: 519-533.
[17] Powell MJD. An e±cient method for finding the minimum of a function of several variables without
calculating derivatives. Comput J 1964; 7: 155-162.
[18] Liu CG, Gong ZH, Zhu HJ, et al. A novel human detection algorithm based on foreground segmentation. J Fiber Bioeng Inform 2013; 6(3): 285-292.
[19] Barbel M, Gerard JP, Breukelen V, Rainer G, Berger MPF. Robustness of optimal design of fMRI
experiments with application of a genetic algorithm. NeuroImage 2010; 49: 2433-2443.
[20] Wang HF. HOG-NPE: A novel local description operator for face image recognition. J Fiber Bioeng
Inform 2014; 7(3): 419-427. |
|
|
|
2014, Vol. 7 
