Abstract
The independent component analysis (ICA) is a data-centric approach that provides a more flexible framework for the analysis of functional magnetic resonance imaging (fMRI), a tool utilized in both research and clinical arenas. The ICA facilitates the analysis of fMRI data in its complex form by eliminating the need to explicitly model the phase behavior. The ICA has been successfully used in fMRI applications that proved challenging for the regression-type approaches. Such applications are identification of various signal types in the spatial or temporal domain, analysis of multi-subject fMRI data and finally, the analysis of complex-valued fMRI data. The main advantage of using ICA is the ability to model cognitive processes for which detailed a priori models of brain.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 136-139 |
| Number of pages | 4 |
| Journal | IEEE Signal Processing Magazine |
| Volume | 24 |
| Issue number | 5 |
| DOIs | |
| State | Published - 2007 |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering
- Applied Mathematics
Cite this
Complex ICA of brain imaging data. / Adali, Tülay; Calhoun, Vince Daniel.
In: IEEE Signal Processing Magazine, Vol. 24, No. 5, 2007, p. 136-139.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Complex ICA of brain imaging data
AU - Adali, Tülay
AU - Calhoun, Vince Daniel
PY - 2007
Y1 - 2007
N2 - The independent component analysis (ICA) is a data-centric approach that provides a more flexible framework for the analysis of functional magnetic resonance imaging (fMRI), a tool utilized in both research and clinical arenas. The ICA facilitates the analysis of fMRI data in its complex form by eliminating the need to explicitly model the phase behavior. The ICA has been successfully used in fMRI applications that proved challenging for the regression-type approaches. Such applications are identification of various signal types in the spatial or temporal domain, analysis of multi-subject fMRI data and finally, the analysis of complex-valued fMRI data. The main advantage of using ICA is the ability to model cognitive processes for which detailed a priori models of brain.
AB - The independent component analysis (ICA) is a data-centric approach that provides a more flexible framework for the analysis of functional magnetic resonance imaging (fMRI), a tool utilized in both research and clinical arenas. The ICA facilitates the analysis of fMRI data in its complex form by eliminating the need to explicitly model the phase behavior. The ICA has been successfully used in fMRI applications that proved challenging for the regression-type approaches. Such applications are identification of various signal types in the spatial or temporal domain, analysis of multi-subject fMRI data and finally, the analysis of complex-valued fMRI data. The main advantage of using ICA is the ability to model cognitive processes for which detailed a priori models of brain.
UR - http://www.scopus.com/inward/record.url?scp=85032751204&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85032751204&partnerID=8YFLogxK
U2 - 10.1109/SP.2007.904742
DO - 10.1109/SP.2007.904742
M3 - Article
AN - SCOPUS:85032751204
VL - 24
SP - 136
EP - 139
JO - IEEE Signal Processing Magazine
JF - IEEE Signal Processing Magazine
SN - 1053-5888
IS - 5
ER -