Latency (in)sensitive ICA
Group independent component analysis of fMRI data
in the temporal frequency domain
V.D. Calhoun,
a,b,c,
* T. Adali,
e
J.J. Pekar,
d,f
and G.D. Pearlson
a,b,c
a
Olin Neuropsychiatry Research Center, Institute of Living, Hartford, CT 06106, USA
b
Department of Psychiatry, Yale University, New Haven, CT 06520, USA
c
Department of Psychiatry, Johns Hopkins University, Baltimore, MD 21205, USA
d
Department of Radiology, Johns Hopkins University, Baltimore, MD 21205, USA
e
University of Maryland Baltimore County, Dept. of CSEE, Baltimore, MD 21250, USA
f
E.M. Kirby Research Center for Functional Brain Imaging, Kennedy Krieger Institute, Baltimore, MD 21205, USA
Received 8 May 2003; revised 27 June 2003; accepted 3 July 2003
Abstract
Independent component analysis (ICA), a data-driven approach utilizing high-order statistical moments to find maximally independent
sources, has found fruitful application in functional magnetic resonance imaging (fMRI). A limitation of the standard fMRI ICA model is
that a given component’s time course is required to have the same delay at every voxel. As spatially varying delays (SVDs) may be found
in fMRI data, using an ICA model with a fixed temporal delay for each source will have two implications. Larger SVDs can result in the
splitting of regions with different delays into different components. Second, smaller SVDs can result in a biased ICA amplitude estimate
due to only a slight delay difference. We propose a straightforward approach for incorporating this prior temporal information and removing
the limitation of a fixed source delay by performing ICA on the amplitude spectrum of the original fMRI data (thus removing latency
information). A latency map is then estimated for each component using the resulting component images and the raw data. We show that
voxels with similar time courses, but different delays, are grouped into the same component. Additionally, when using traditional ICA, the
amplitudes of motor areas are diminished due to systematic delay differences between visual and motor areas. The amplitudes are more
accurately estimated when using a latency-insensitive ICA approach. The resulting time courses, the component maps, and the latency maps
may prove useful as an addition to the collection of methods for fMRI data analysis.
© 2003 Elsevier Inc. All rights reserved.
Keywords: fMRI; Functional; Brain; Independent component analysis; ICA
Introduction
Independent component analysis (ICA) is a data-driven
approach that can extract components and time courses of
interest from fMRI data (McKeown et al., 1998). Indepen-
dent component analysis for fMRI has been shown to be
useful for characterizing data sets for which a specific a
priori model is not available (Calhoun et al., 2002) or even
to generate or improve upon models of neuronal function
(Seifritz et al., 2002). However, a limitation of ICA models
previously applied to fMRI is that a given component’s
associated time course is modeled to be identical (except for
magnitude) for every voxel in the brain. Considerable vari-
ability of hemodynamic delays has been observed across
different brain locations (Saad et al., 2001). Such observa-
tions can only be captured by a model that allows for
spatially varying delays (SVDs). If they are instead modeled
with a standard ICA approach, a large SVD can result in
regions being split into different components. Smaller
* Corresponding author. Olin Neuropsychiatry Research Center, Insti-
tute of Living, 200 Retreat Ave., Hartford, CT 06106, USA. Fax: +1-860-
545-7797.
E-mail address: vince.calhoun@yale.edu (V.D. Calhoun).
NeuroImage 20 (2003) 1661–1669 www.elsevier.com/locate/ynimg
1053-8119/$ – see front matter © 2003 Elsevier Inc. All rights reserved.
doi:10.1016/S1053-8119(03)00411-7