TY - JOUR

T1 - Strategies for reducing large fMRI data sets for independent component analysis

AU - Wang, Ze

AU - Wang, Jiongjiong

AU - Calhoun, Vince

AU - Rao, Hengyi

AU - Detre, John A.

AU - Childress, Anna R.

N1 - Funding Information:
This research was supported by NIH grants NS045839, HD39621, DA015149, RR02305, MH072576, and NSF grant BCS0224007.

PY - 2006/6

Y1 - 2006/6

N2 - In independent component analysis (ICA), principal component analysis (PCA) is generally used to reduce the raw data to a few principal components (PCs) through eigenvector decomposition (EVD) on the data covariance matrix. Although this works for spatial ICA (sICA) on moderately sized fMRI data, it is intractable for temporal ICA (tICA), since typical fMRI data have a high spatial dimension, resulting in an unmanageable data covariance matrix. To solve this problem, two practical data reduction methods are presented in this paper. The first solution is to calculate the PCs of tICA from the PCs of sICA. This approach works well for moderately sized fMRI data; however, it is highly computationally intensive, even intractable, when the number of scans increases. The second solution proposed is to perform PCA decomposition via a cascade recursive least squared (CRLS) network, which provides a uniform data reduction solution for both sICA and tICA. Without the need to calculate the covariance matrix, CRLS extracts PCs directly from the raw data, and the PC extraction can be terminated after computing an arbitrary number of PCs without the need to estimate the whole set of PCs. Moreover, when the whole data set becomes too large to be loaded into the machine memory, CRLS-PCA can save data retrieval time by reading the data once, while the conventional PCA requires numerous data retrieval steps for both covariance matrix calculation and PC extractions. Real fMRI data were used to evaluate the PC extraction precision, computational expense, and memory usage of the presented methods.

AB - In independent component analysis (ICA), principal component analysis (PCA) is generally used to reduce the raw data to a few principal components (PCs) through eigenvector decomposition (EVD) on the data covariance matrix. Although this works for spatial ICA (sICA) on moderately sized fMRI data, it is intractable for temporal ICA (tICA), since typical fMRI data have a high spatial dimension, resulting in an unmanageable data covariance matrix. To solve this problem, two practical data reduction methods are presented in this paper. The first solution is to calculate the PCs of tICA from the PCs of sICA. This approach works well for moderately sized fMRI data; however, it is highly computationally intensive, even intractable, when the number of scans increases. The second solution proposed is to perform PCA decomposition via a cascade recursive least squared (CRLS) network, which provides a uniform data reduction solution for both sICA and tICA. Without the need to calculate the covariance matrix, CRLS extracts PCs directly from the raw data, and the PC extraction can be terminated after computing an arbitrary number of PCs without the need to estimate the whole set of PCs. Moreover, when the whole data set becomes too large to be loaded into the machine memory, CRLS-PCA can save data retrieval time by reading the data once, while the conventional PCA requires numerous data retrieval steps for both covariance matrix calculation and PC extractions. Real fMRI data were used to evaluate the PC extraction precision, computational expense, and memory usage of the presented methods.

KW - Cascade recursive least squared networks

KW - Independent component analysis

KW - Principal component analysis

KW - fMRI

UR - http://www.scopus.com/inward/record.url?scp=33646846954&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646846954&partnerID=8YFLogxK

U2 - 10.1016/j.mri.2005.12.013

DO - 10.1016/j.mri.2005.12.013

M3 - Article

C2 - 16735180

AN - SCOPUS:33646846954

SN - 0730-725X

VL - 24

SP - 591

EP - 596

JO - Magnetic Resonance Imaging

JF - Magnetic Resonance Imaging

IS - 5

ER -