Flows of diffeomorphisms for multimodal image registration

C. Chefd'hotel1, G. Hermosillo1, O. Faugeras1
1I.N.R.I.A. Sophia Antipolis, France

Tóm tắt

We present a theoretical and computational framework for nonrigid multimodal registration. We proceed by minimization of statistical similarity criteria (global and local) in a variational framework, and use the corresponding gradients to drive a flow of diffeomorphisms allowing large deformations. This flow is introduced through a new template propagation method, by composition of small displacements. Regularization is performed using fast filtering techniques. This approach yields robust matching algorithms offering a good computational efficiency. We apply this method to compensate distortions between EPI images (fMRI) and anatomical MRI volumes.

Từ khóa

#Image registration #Low pass filters #Robustness #Magnetic resonance imaging #Filtering #Chromium #Computational efficiency #Mutual information #Convergence #Fluid flow measurement

Tài liệu tham khảo

10.1109/42.836368 10.1016/S1361-8415(01)80026-8 10.1023/A:1011161132514 mumford, 1998, Pattern theory and vision, Lecture notes Centre Emile Borel roche, 1998, Multirnodal image registration by maximization of the correlation ratio, Technical report 3378 INRIA taylor, 1996, Partial Differential Equations 10.1016/S0262-8856(00)00055-X 10.1023/A:1008001603737 10.1016/S1361-8415(01)80004-9 10.1109/ICPR.1988.28260 cnorin, 1978, Product formulas and numerical algorithms, Communications on Pure and Applied Mathematics, 31, 205, 10.1002/cpa.3160310205 dupuis, 1998, Variational problems on flows of diffeomorphisms for image matching, Quarterly of Applied Malhematics, 56, 587, 10.1090/qam/1632326 10.1109/83.536892 10.1109/CVPR.2001.990458 grenander, 1998, Computational anatomy: an emerging discipline, Quarterly of Applied Mathematics, 56, 617, 10.1090/qam/1668732 10.1109/VLSM.2001.938877 bro-nielsen, 1996, Fast fluid registration of medical images, Visualization in Biomedical Computing, 267 10.1007/3-540-44745-8_35