cvpr cvpr2013 cvpr2013-194 cvpr2013-194-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Shihui Ying, Guorong Wu, Qian Wang, Dinggang Shen
Abstract: Recently, groupwise registration has been investigated for simultaneous alignment of all images without selecting any individual image as the template, thus avoiding the potential bias in image registration. However, none of current groupwise registration method fully utilizes the image distribution to guide the registration. Thus, the registration performance usually suffers from large inter-subject variations across individual images. To solve this issue, we propose a novel groupwise registration algorithm for large population dataset, guided by the image distribution on the manifold. Specifically, we first use a graph to model the distribution of all image data sitting on the image manifold, with each node representing an image and each edge representing the geodesic pathway between two nodes (or images). Then, the procedure of warping all images to theirpopulation center turns to the dynamic shrinking ofthe graph nodes along their graph edges until all graph nodes become close to each other. Thus, the topology ofimage distribution on the image manifold is always preserved during the groupwise registration. More importantly, by modeling , the distribution of all images via a graph, we can potentially reduce registration error since every time each image is warped only according to its nearby images with similar structures in the graph. We have evaluated our proposed groupwise registration method on both synthetic and real datasets, with comparison to the two state-of-the-art groupwise registration methods. All experimental results show that our proposed method achieves the best performance in terms of registration accuracy and robustness.
[1] J. Ashburner. A fast diffeomorphic image registration algorithm. NeuroImage, 38(1):95–1 13, 2007.
[2] T. Cootes, C. Twining, V. Petrovic, K. Babalola, and C. Taylor. Computing accurate correspondences across groups of images. IEEE Trans. Pattern Anal. Mach. Intell., 32(11): 1994–2005, 2010. 222333222977 Figure 7. Mean images by the three methods on longitudinal infant dataset. arD)o(cei%t67 6432150879AoGurB2SmpO?ReBmhtoadn4mehtIodrain6Number8102 ti%rDaco)ie(78 04965AoGu2rBmSoupOe?RthBmodean4 htIeordain6Number8102 t(rcD)eioa%564 028 AGou2rBmSouOpe?RhtmBoadn4mehtIordain6Number8102 (a) Evolution of Dice ratio on white matter (b) Evolution of Dice ratio on gray matter (c) Evolution of Dice ratio on CSF Figure 8. Evolution of Dice ratios of three brain tissues during the groupwise registration by three methods on longitudinal infant dataset.
[3] D. Cristinacce and T. Cootes. Facial motion analysis using clustered shortest path tree registration. Proc. MLVMA Workshop, pages 1994–2005, 2008.
[4] B. Davis, P. Fletcher, and E. Bullit. Population shape regression from random design data. Int. J. Comput. Vis., 90(2):255–266, 2010.
[5] S. Durrleman, P. Fillard, X. Pennec, A. Trouv ´e, and N. Ayache. Registration, atlas estimation and variability analysis of white matter fiber bundles modeled as currents. NeuroImage, 55(3): 1073–1090, 2011.
[6] P. Fletcher, S. Venkatasubramanian, and S. Joshi. The geometric median on riemannian manifolds with application to robust atlas estimation. NeuroImage, 45(1-S 1):S 143–S 152, 2009.
[7] V. Fonov, A. Evans, and K. Botteron. Unbiased average age-appropriate atlases for pediatric studies. NeuroImage, 54(1):313–327, 2011.
[8] S. Gerber, T. Tasdizen, P. Fletcher, S. Joshi, R. Whitaker, and ADNI. Manifold modeling for brain population analysis. Med. Ima. Anal., 14:643–653, 2010.
[9] J. Hamm, C. Davatzikos, , and R. Verma. Efficient large deformation registration via geodesics on a learned manifold of images. In: MICCAI, pages 680–687, 2009.
[10] S. Helgason. Differential Geometry, Lie Groups and Symmetric Space, Academic Press, 2001 .
[11] H. Jia, G. Wu, Q. Wang, and D. Shen. Absorb: atlas building by self-organized registration and bundling. In: IEEE Conf. Comput. Vis. Pattern Recog., pages 2785–2790, 2010.
[12] S. Joshi, B. Davis, M. Jomier, and G. Gerig. Unbiased diffeomorphic atlas construction for computational anatomy. NeuroImage, 23(S1):S151–S160, 2004.
[13] V. Noblet, C. Heinrich, F. Heitz, and J. Armspach. An efficient incremental strategy for constrained groupwise registration based on symmetric pairwise registration. Pattern Recog. Lett., 33(3):283–290, 2012.
[14] A. Toga and P. Thompson. The role of image registration in brain mapping. Ima. Vis. Comput., 19(1-2):3–24, 2001 .
[15] T. Vercauteren, X. Pennec, A. Perchant, and N. Ayache. Symmetric log-domain diffeomorphic registration: a demons-based approach. LNCS, 5341 :754–761, 2008.
[16] Q. Wang, L. Chen, P. Yap, G. Wu, and D. Shen. Groupwise registration based on hierarchical image clustering and atlas synthesis. Human Brain Mapping, 3 1:1128–1 140, 2010.
[17] G. Wu, H. Jia, Q. Wang, and D. Shen. Sharpmean: groupwise registration guided by sharp mean image and tree-based registration. NeuroImage, 56(4): 1968–1981, 2011.
[18] G. Wu, Q. Wang, D. Shen, and ADNI. Registration of longitudinal brain image sequences with implicit template and spatial-temporal heuristics. NeuroImage, 59(1):404–421, 2012.
[19] Y. Xie, J. Ho, and B. Vemuri. Image atlas construction via intrinsic averaging on the manifold of images. In: IEEE Conf. Comput. Vis. Pattern Recog., pages 2933–2939, 2010. 222333223088