Metamorphic image registration using a semi-Lagrangian scheme

In this paper, we propose an implementation of both Large Deformation Diffeomorphic Metric Mapping (LDDMM) and Metamorphosis image registration using a semi-Lagrangian scheme for geodesic shooting. We propose to solve both problems as an inexact matching providing a single and unifying cost function. We demonstrate that for image registration the use of a semi-Lagrangian scheme is more stable than a standard Eulerian scheme. Our GPU implementation is based on PyTorch, which greatly simplifies and accelerates the computations thanks to its powerful automatic differentiation engine. It will be freely available at https://github.com/antonfrancois/Demeter metamorphosis.

[1]  Josep Marco-Pallarés,et al.  Analysis of automated methods for spatial normalization of lesioned brains , 2012, NeuroImage.

[2]  Karl J. Friston,et al.  Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation , 2011, NeuroImage.

[3]  Nicholas Ayache,et al.  A Log-Euclidean Framework for Statistics on Diffeomorphisms , 2006, MICCAI.

[4]  Paul Dupuis,et al.  Variational problems on ows of di eomorphisms for image matching , 1998 .

[5]  Laurent Younes,et al.  Metamorphosis of images in reproducing kernel Hilbert spaces , 2014, Adv. Comput. Math..

[6]  Brian B. Avants,et al.  Lagrangian frame diffeomorphic image registration: Morphometric comparison of human and chimpanzee cortex , 2006, Medical Image Anal..

[7]  L. Younes.  Shapes and Diffeomorphisms , 2010 .

[8]  Alain Trouvé,et al.  The Euler-Poincare theory of Metamorphosis , 2008, ArXiv.

[9]  Daniel Rueckert,et al.  Diffeomorphic 3D Image Registration via Geodesic Shooting Using an Efficient Adjoint Calculation , 2011, International Journal of Computer Vision.

[10]  Alain Trouvé,et al.  Local Geometry of Deformable Templates , 2005, SIAM J. Math. Anal..

[11]  Chen Chong,et al.  Image reconstruction through metamorphosis , 2018 .

[12]  Christos Davatzikos,et al.  GLISTR: Glioma Image Segmentation and Registration , 2012, IEEE Transactions on Medical Imaging.

[13]  John Ashburner,et al.  A fast diffeomorphic image registration algorithm , 2007, NeuroImage.

[14]  Alain Trouvé,et al.  Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms , 2005, International Journal of Computer Vision.

[15]  Alexander Efremov,et al.  A Computational Realization of a Semi-Lagrangian Method for Solving the Advection Equation , 2014, J. Appl. Math..

[16]  M. Sdika,et al.  Nonrigid registration of multiple sclerosis brain images using lesion inpainting for morphometry or lesion mapping , 2009, Human brain mapping.

[17]  Marc Niethammer,et al.  Low-Rank Atlas Image Analyses in the Presence of Pathologies , 2015, IEEE Transactions on Medical Imaging.

[18]  Alain Trouvé,et al.  Geodesic Shooting for Computational Anatomy , 2006, Journal of Mathematical Imaging and Vision.