CLC number: TP391.4
On-line Access: 2024-08-27
Received: 2023-10-17
Revision Accepted: 2024-05-08
Crosschecked: 2015-09-09
Cited: 0
Clicked: 6356
Yu Liu, Bo Zhu. Deformable image registration with geometric changes[J]. Frontiers of Information Technology & Electronic Engineering, 2015, 16(10): 829-837.
@article{title="Deformable image registration with geometric changes",
author="Yu Liu, Bo Zhu",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="16",
number="10",
pages="829-837",
year="2015",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1500045"
}
%0 Journal Article
%T Deformable image registration with geometric changes
%A Yu Liu
%A Bo Zhu
%J Frontiers of Information Technology & Electronic Engineering
%V 16
%N 10
%P 829-837
%@ 2095-9184
%D 2015
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1500045
TY - JOUR
T1 - Deformable image registration with geometric changes
A1 - Yu Liu
A1 - Bo Zhu
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 16
IS - 10
SP - 829
EP - 837
%@ 2095-9184
Y1 - 2015
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1500045
Abstract: geometric changes present a number of difficulties in deformable image registration. In this paper, we propose a global deformation framework to model geometric changes whilst promoting a smooth transformation between source and target images. To achieve this, we have developed an innovative model which significantly reduces the side effects of geometric changes in image registration, and thus improves the registration accuracy. Our key contribution is the introduction of a sparsity-inducing norm, which is typically L1 norm regularization targeting regions where geometric changes occur. This preserves the smoothness of global transformation by eliminating local transformation under different conditions. Numerical solutions are discussed and analyzed to guarantee the stability and fast convergence of our algorithm. To demonstrate the effectiveness and utility of this method, we evaluate it on both synthetic data and real data from traumatic brain injury (TBI). We show that the transformation estimated from our model is able to reconstruct the target image with lower instances of error than a standard elastic registration model.
The paper represents a novel algorithm for image registration with geometric changes. A sparse model is designed to provide different level of constraints on local deformations. Also, a new energy optimization scheme is introduced to preserve the topology and uniquely describe the correspondence between images, and a numerical dual technique is applied to speed up the convergence and enhance the stability. The authors show experimental results that suggest that their algorithm outperforms the traditional elastic image registration on the registration accuracy and processing time.
[1]Bajcsy, R., Broit, C., 1982. Matching of deformed images. Proc. 6th Int. Conf. on Pattern Recognition, p.351-353.
[2]Beck, A., Teboulle, M., 2008. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imag. Sci., 2(1):183-202.
[3]Beg, M.F., Miller, M.I., Trouvé, A., et al., 2005. Computing large deformation metric mappings via geodesic flows of diffeomorphisms. Int. J. Comput. Vis., 61(2):139-157.
[4]Chambolle, A., 2004. An algorithm for total variation minimization and applications. J. Math. Imag. Vis., 20(1):89-97.
[5]Christensen, G.E., Johnson, H.J., 2001. Consistent image registration. IEEE Trans. Med. Imag., 20(7):568-582.
[6]Christensen, G.E., Rabbitt, R.D., Miller, M.I., 1996. Deformable templates using large deformation kinematics. IEEE Trans. Image Process., 5(10):1435-1447.
[7]Hall, E.L., 1979. Computer Image Processing and Recognition. Academic Press, New York, USA.
[8]Herbin, M., Venot, A., Devaux, J.Y., et al., 1989. Automated registration of dissimilar images: application to medical imagery. Comput. Vis. Graph. Image Process., 47(1):77-88.
[9]Hernandez, M., Olmos, S., Pennec, X., 2008. Comparing algorithms for diffeomorphic registration: stationary LDDMM and diffeomorphic demons. Proc. 2nd MICCAI Workshop on Mathematical Foundations of Computational Anatomy, p.24-35.
[10]Lucas, B.D., Kanade, T., 1981. An iterative image registration technique with an application to stereo vision. Proc. 7th Int. Joint Conf. on Artificial Intelligence, p.121-130.
[11]Luck, J., Little, C., Hoff, W., 2000. Registration of range data using a hybrid simulated annealing and iterative closest point algorithm. Proc. IEEE Int. Conf. on Robotics and Automation, p.3739-3744.
[12]Niethammer, M., Hart, G.L., Pace, D.F., et al., 2011. Geometric metamorphosis. Proc. 14th Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, p.639-646.
[13]Richard, F.J.P., Samson, A.M.M., 2007. Metropolis-Hasting techniques for finite-element-based registration. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.1-6.
[14]Rudin, L.I., Osher, S., Fatemi, E., 1992. Nonlinear total variation based noise removal algorithms. Phys. D, 60(1-4):259-268.
[15]Trouvé, A., Younes, L., 2005. Metamorphoses through Lie group action. Found. Comput. Math., 5(2):173-198.
[16]Zhang, M., Singh, N., Fletcher, P.T., 2013. Bayesian estimation of regularization and atlas building in diffeomorphic image registration. Proc. 23rd Int. Conf. on Information Processing in Medical Imaging. p.37-48.
Open peer comments: Debate/Discuss/Question/Opinion
<1>