A Lagrangian Framework for Fast and Flexible Diffeomorphic Image RegistrationMS28

We present efficient solvers for diffeomorphic registration problems in the framework of Large Deformations Diffeomorphic Metric Mappings (LDDMM). We use an optimal control formulation in which the (stationary or instationary) velocity field of a hyperbolic PDE needs to be chosen in order to minimize the distance between the final state of the system (the transformed/transported template image) and the observation (the reference image). Our formulation is widely applicable as it allows solving mass- and intensity-preserving registration problems.

This presentation is part of Minisymposium “MS28 - Diffeomorphic Image Registration: Numerics, Applications, and Theory (2 parts)
organized by: Andreas Mang (Department of Mathematics, University of Houston) , George Biros (Institute for Computational Engineering and Sciences, University of Texas at Austin) .

Lars Ruthotto (Department of Mathematics and Computer Science, Emory University)
image registration, nonlinear optimization, partial differential equation models