Diffusion Tensor Registration Using Probability Kernels and Discrete Optimization

Abstract

In this report, we propose a novel diffusion tensor registration algorithm based on a discrete optimization approach in a Reproducing Kernel Hilbert Space (RKHS) setting. Our approach encodes both the diffusion information and the spatial localization of tensors in a probabilistic framework. The diffusion probabilities are mapped to a RKHS, where we define… (More)

Topics

Cite this paper

@inproceedings{Sotiras2009DiffusionTR, title={Diffusion Tensor Registration Using Probability Kernels and Discrete Optimization}, author={Aristeidis Sotiras and Nikos Paragios and Jean-François Deux and Mezri Maatouk and Alain Rahmouni and Guillaume Bassez}, year={2009} }