Please use this identifier to cite or link to this item:
|Title:||Geodesic regression on orientation distribution functions with its application to an aging study|
|Keywords:||Orientation distribution function|
|Citation:||Du, J., Goh, A., Kushnarev, S., Qiu, A. (2014-02-15). Geodesic regression on orientation distribution functions with its application to an aging study. NeuroImage 87 : 416-426. ScholarBank@NUS Repository. https://doi.org/10.1016/j.neuroimage.2013.06.081|
|Abstract:||In this paper, we treat orientation distribution functions (ODFs) derived from high angular resolution diffusion imaging (HARDI) as elements of a Riemannian manifold and present a method for geodesic regression on this manifold. In order to find the optimal regression model, we pose this as a least-squares problem involving the sum-of-squared geodesic distances between observed ODFs and their model fitted data. We derive the appropriate gradient terms and employ gradient descent to find the minimizer of this least-squares optimization problem. In addition, we show how to perform statistical testing for determining the significance of the relationship between the manifold-valued regressors and the real-valued regressands. Experiments on both synthetic and real human data are presented. In particular, we examine aging effects on HARDI via geodesic regression of ODFs in normal adults aged 22. years old and above. © 2013 Elsevier Inc.|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on May 20, 2018
checked on May 11, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.