Power Euclidean metrics for covariance matrices with application to diffusion tensor imaging
Methodology
2010-09-17 v1 Applications
Abstract
Various metrics for comparing diffusion tensors have been recently proposed in the literature. We consider a broad family of metrics which is indexed by a single power parameter. A likelihood-based procedure is developed for choosing the most appropriate metric from the family for a given dataset at hand. The approach is analogous to using the Box-Cox transformation that is frequently investigated in regression analysis. The methodology is illustrated with a simulation study and an application to a real dataset of diffusion tensor images of canine hearts.
Cite
@article{arxiv.1009.3045,
title = {Power Euclidean metrics for covariance matrices with application to diffusion tensor imaging},
author = {Ian L. Dryden and Xavier Pennec and Jean-Marc Peyrat},
journal= {arXiv preprint arXiv:1009.3045},
year = {2010}
}