Effect of spatial alignment transformations in PCA and ICA of functional neuroimages.

by: AS Lukic, MN Wernick, Y Yang, LK Hansen, K Arfanakis, SC Strother

IEEE Trans Med Imaging, Vol. 26, No. 8. (August 2007), pp. 1058-1068.

View FullText article

Pubmed, Hubmed

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

gracev, xinian

Find related articles with these CiteULike tags

alignment, fmri, ica, pca, principal-axes-tranform

Abstract

It has been previously observed that independent component analysis (ICA), if applied to data pooled in a particular way, may lessen the need for spatial alignment of scans in a functional neuroimaging study. In this paper, we seek to determine analytically the conditions under which this observation is true, not only for spatial ICA, but also for temporal ICA and for principal component analysis (PCA). In each case, we find conditions that the spatial alignment operator must satisfy to ensure invariance of the results. We illustrate our findings using functional magnetic-resonance imaging (fMRI) data. Our analysis is applicable to both intersubject and intrasubject spatial normalization.

@article{citeulike:1706935, abstract = {It has been previously observed that independent component analysis (ICA), if applied to data pooled in a particular way, may lessen the need for spatial alignment of scans in a functional neuroimaging study. In this paper, we seek to determine analytically the conditions under which this observation is true, not only for spatial ICA, but also for temporal ICA and for principal component analysis (PCA). In each case, we find conditions that the spatial alignment operator must satisfy to ensure invariance of the results. We illustrate our findings using functional magnetic-resonance imaging (fMRI) data. Our analysis is applicable to both intersubject and intrasubject spatial normalization.}, address = {Predictek Inc., Chicago, IL 60616, USA.}, author = {Lukic, A. S. and Wernick, M. N. and Yang, Y. and Hansen, L. K. and Arfanakis, K. and Strother, S. C. }, citeulike-article-id = {1706935}, issn = {0278-0062}, journal = {IEEE Trans Med Imaging}, keywords = {fmri, ica}, month = {August}, number = {8}, pages = {1058--1068}, posted-at = {2007-09-29 03:02:28}, priority = {2}, title = {Effect of spatial alignment transformations in PCA and ICA of functional neuroimages.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/17695126}, volume = {26}, year = {2007} }

RIS record

TY - JOUR ID - citeulike:1706935 L3 - citeulike-article-id:1706935 TI - Effect of spatial alignment transformations in PCA and ICA of functional neuroimages. JF - IEEE Trans Med Imaging VL - 26 IS - 8 SP - 1058 EP - 1068 AD - Predictek Inc., Chicago, IL 60616, USA. SN - 0278-0062 N2 - It has been previously observed that independent component analysis (ICA), if applied to data pooled in a particular way, may lessen the need for spatial alignment of scans in a functional neuroimaging study. In this paper, we seek to determine analytically the conditions under which this observation is true, not only for spatial ICA, but also for temporal ICA and for principal component analysis (PCA). In each case, we find conditions that the spatial alignment operator must satisfy to ensure invariance of the results. We illustrate our findings using functional magnetic-resonance imaging (fMRI) data. Our analysis is applicable to both intersubject and intrasubject spatial normalization. KW - fmri KW - ica AU - Lukic, AS AU - Wernick, MN AU - Yang, Y AU - Hansen, LK AU - Arfanakis, K AU - Strother, SC PY - 2007/08// UR - http://view.ncbi.nlm.nih.gov/pubmed/17695126 ER -

RIS BibTeX