Abstract
A common framework for 3-D image registration consists in minimizing a cost (or energy) function that expresses the pixel or voxel similarity of the images to be aligned. Standard cost functions, based on voxel similarity measures, are highly nonlinear, non-convex, exhibit many local minima and thus yield hard optimization problems. Local, deterministic optimization algorithms are known to be sensitive to local minima. Global optimization methods (like simulated annealing or evolutionary algorithms) yield better solutions often close to the optimal ones, but are time consuming. In this section we consider the parallelization of a general-purpose global optimization algorithm based on random sampling and evolutionary principles: the differential evolution algorithm. The inherent parallelism of evolutionary algorithms is used to devise a data-parallel implementation of differential evolution. The performances of the parallel version are assessed on a 3-D medical image registration problem. Besides yielding accurate registrations, parallel differential evolution exhibits fast convergence and a speedup almost growing linearly with respect to the number of processors.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bäck T (1996) Evolutionary algorithms in theory and practice. Oxford University Press
Brown LG (1992) A survey of image registration techniques. ACM Computing Survey 24(4):325–376
Christensen G, Miller M, Vannier M, Grenander U (1996) Individualizing neuroanatomical atlases using a massively parallel computer. IEEE Computer, January:32–38
van den Elsen PA, Paul EJD, Viergever MA (1993) Medical image matching — a review with classification. IEEE Engineering in Medicine and Biology 12(4):26–39
Fischer D, Kohlhepp P, Bulling F (1999) An evolutionary algorithm for the registration of 3D surface representations. Pattern Recognition 32:53–69
Geman D, Geman S (1984) Stochastic relaxation, Gibbs distribution, Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence 6:721–741
Glover F, Laguna M (1993) Tabu search. In: Reeves C (ed.), Modern heuristic techniques for combinatorial problems. Blackwell Scientific, Oxford
Heitz F, Perez P, Bouthemy P (1994) Multiscale minimization of global energy functions in some visual recovery problems. Computer Vision, Graphics and Image Processing 59(1):125–134
Hill DLG, Hawkes DJ (2000) Across-modality registration using intensity-based cost functions. In: Bankman IN (ed.), Handbook of medical imaging. Academic Press, New York, Chap. 34
Kirkpatrick S, Gelatt CD, Vecchi MP (1983) Optimization by simulated annealing. Science 220:671–680
Musse O, Heitz F, Armspach J-P (1999) 3D deformable image matching using multiscale minimization of global energy functions. In: IEEE international conference on computer vision pattern recognition, CVPR’99, Fort Collins, USA, June
Nikou C, Heitz F, Armspach J-P, Namer I-J, Grucker D (1998) Registration of MR/MR and MR/SPECT brain images by fast stochastic optimization of robust voxel similarity measures. Neuroimage 8:30–43
Salomon M (2001) Étude de la parallélisation de méthodes heuristiques d’optimisation combinatoire. Application au recalage d’images médicales. Ph.D. thesis, Université Louis Pasteur (Strasbourg I University)
Storn R (1996) On the usage of differential evolution for function optimization. In: Conference of the North American Fuzzy Information Processing Society (NAFIPS 1996), Berkeley, CA, pp 519–423
Storn R, Price K (1996) Minimizing the real functions of the ICEC’96 contest by differential evolution. In: IEEE international conference on evolutionary computation, Nagoya, Japan, May, pp 842–844
Tomassini M (1999) Parallel and distributed evolutionary algorithms. In: Miettinen K (ed.), Evolutionary algorithms in engineering and computer science. Wiley, New York, Chap. 7
Woods RP (2000a) Spatial transformation models. In: Bankman IN (ed.), Handbook of medical imaging. Academic Press, New York, Chap. 29
Woods RP (2000b) Within-modality registration using intensity-based cost functions. In: Bankman IN (ed.), Handbook of medical imaging. Academic Press, New York, Chap. 33
Woods RP, Mazziotta JC, Cherry SR (1993) MRI-PET registration with automated algorithm. Journal of Computerized Assisted Tomography 17(4):536–546
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Salomon, M., Perrin, GR., Heitz, F., Armspach, JP. (2005). Parallel Differential Evolution: Application to 3-D Medical Image Registration. In: Differential Evolution. Natural Computing Series. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-31306-0_12
Download citation
DOI: https://doi.org/10.1007/3-540-31306-0_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20950-8
Online ISBN: 978-3-540-31306-9
eBook Packages: Computer ScienceComputer Science (R0)