Diffeomorphic Demons: Description

This non-linear registration algorithm is a fast and efficient way of retrieving dense displacement between two image volumes.

Image registration is classically performed by op- timizing a similarity criterion over a given spatial transformation space. Even if this problem is considered as almost solved for linear registration, we show that some tools that have recently been developed in the field of vision-based robot control can outperform classical solu- tions. The adequacy of these tools for linear image registration leads us to revisit non-linear registration and allows us to provide interesting theo- retical roots to the different variants of Thirion’s demons algorithm. This analysis predicts a theoretical advantage to the symmetric forces variant of the demons algorithm. We show that, on controlled experiments, this advantage is confirmed, and yields a faster convergence. [2]


More information on this website.


Classical Circle to C registration example. With the same set of parameters the additive demons fails to converge and shows foldings in the registration results whereas the diffeomorphic demons converges with a smooth invertible transformation.


  1. Tom Vercauteren, Xavier Pennec, Aymeric Perchant, and Nicholas Ayache. Diffeomorphic Demons: Efficient Non-parametric Image Registration. NeuroImage, 45(1, Supp.1):S61-S72, March 2009. Note: PMID: 19041946. [bibtex-entry]

  2. Tom Vercauteren, Xavier Pennec, Ezio Malis, Aymeric Perchant, and Nicholas Ayache. Insight Into Efficient Image Registration Techniques and the Demons Algorithm. In Proc. Information Processing in Medical Imaging (IPMI'07), volume 4584 of Lecture Notes in Computer Science, Kerkrade, The Netherlands, pages 495-506, July 2007. Springer-Verlag. Note: PMID: 17633724. [bibtex-entry]

  3. Monica Hernandez, Salvador Olmos, and Xavier Pennec. Comparing algorithms for diffeomorphic registration: Stationary LDDMM and Diffeomorphic Demons. In X. Pennec and S. Joshi, editors, Proc. of the International Workshop on the Mathematical Foundations of Computational Anatomy (MFCA-2008), September 2008. [bibtex-entry]

// //