Bibliography on Independent Component Analysis
in Functional Neuroimaging

Finn Årup Nielsen
CIMBI at DTU Informatics and NRU Rigshospitalet
Lyngby and Copenhagen, Denmark

  $Revision: 1.42 $
  $Date: 2009/03/19 21:39:06 $

Abstract:

References for independent component analysis (ICA) applied in functional neuroimaging are collected. Functional neuroimaging here includes functional magnetic resonance imaging (fMRI), positron emission tomography (PET), electroencephalography (EEG) and magnetoencephalography (MEG).

The original URL to this document is

PDF: http://www.imm.dtu.dk/~fn/bib/Nielsen2001BibICA.pdf
PostScript: http://www.imm.dtu.dk/~ fn/bib/Nielsen2001BibICA.ps
HTML: http://www.imm.dtu.dk/~fn/bib/Nielsen2001BibICA/.

This structured bibliography is part of a larger collection of bibliographies that was begun in 2001 see http://www.imm.dtu.dk/~ fn/bib/Nielsen2001Bib/. The bibliography is written in L^ATEX and BIBTeX and should be available both as HTML and PostScript.

The bibliography is probably far from complete, but new references are added whenever the author finds new material and has the time to add them. You can email the author if corrections are required or you have found some references that you fell ought to be included: fn@imm.dtu.dk.

Note that there is a index at the very end of this document.

Thanks to Evan D. Morris. Funding through Lundbeck Foundation, EU project MAPAWAMO, International Neuroimaging Consortium (INC) American HBM project and Danish THOR Center for Neuroinformatics.

General references

A general introduction is (Hyvärinen and Oja, 2000). A list of papers from the Third International Conference on Independent Component Analysis and Signal Separation (ICA2001) is available from http://ica2001.org.

Neuroimaging

Overviews of ICA for neuroimaging are available in (McKeown et al., 2003; Calhoun et al., 2003) for functional magnetic resonance imaging (fMRI), and Stone (2002) discuss ICA for EEG, fMRI and optical imaging.

Methods

Independent component analysis
- ``Bell and Sejnowski ICA'' (BS-ICA) -- ``Infomax'' (Bell and Sejnowski, 1995).
  - ``Maximum likelihood ICA'' (MacKay, 1999; Lee et al., 1999). (Usually) the same as infomax but developed from maximum likelihood rather than information theory with the sources as, e.g., hyperbolic secant distributions.
- ``Extended infomax'' (Lee et al., 1999) is able to model heavy- and light-tailed distributions.
- `Probabilistic ICA' (PICA) or `Noisy ICA' (Beckmann et al., 2001a), (Kolenda, 2002, section 3.3 and 3.6)
  
  $\displaystyle {\bf X} = {\bf S}{\bf A} + {\bf U}.$ (1)
  
  The noise is usually assumed to be isotropic Gaussian distributed ${\bf u} \sim {\cal N}({\bf0}, \sigma^2 {\bf I})$ . A silimiar noise assumption is made in `probabilistic principal component analysis' (PICA) -- a special factor analysis model -- where model selection can be based on AIC and test set (Hansen et al., 1999a,1997), Minka, Bishop, Zoubin G.
- FastICA (Hyvärinen and Oja, 2000; Hyvärinen, 1999)
- Mean field ICA (MF-ICA) (Højen-Sørensen et al., 2001,2002).
Decorrelation methods -- Dynamic component analysis (DCA)
- Molgedey-Schuster (MS-ICA) (Molgedey and Schuster, 1994). Probabilistic Molgedey-Schuster ICA: ICA with preliminary PCA and model selection with BIC (Hansen et al., 2001). Min/max autocorrelation factorization (MAF) is related to Molgedey-Schuster ICA (Molgedey and Schuster, 1994). MAF was originally described in (Green et al., 1988; Switzer and Green, 1984) and other descriptions are by Conradsen et al. (1986) and Nielsen (1994).
- Georgiev and Cichocki (2001)
- Dynamic component analysis (Attias and Schreiner, 1998,1997)
- `Hansen convolutive ICA' -- `Convolutive independent component analysis by prediction' (CICAP) (Hansen and Dyrholm, 2003; Hansen, 2003).

Methods in functional neuroimaging

Table 1: Independent component analysis in functional neuroimaging. sICA is spatial ICA, tICA is temporal ICA and stICA is spatiotemporal ICA.

Modality	ICA Type	Purpose	Reference
fMRI	sICA		(McKeown et al., 1998b)
fMRI	sICA		(McKeown et al., 1998a)
fMRI		Demonstration of estimation of noisy ICA with mean field approximation	(Hansen, 1998)
fMRI	tICA		(Biswal and Ulmer, 1999)
fMRI	stICA		(Muraki and Nakai, 1999)
fMRI		Comparison of different analysis methods	(Lange et al., 1999)
fMRI		Separate task and non-task	(Ulmer and Biswal, 2000)
fMRI	sICA(?)	Separation of task-related and head movement signal	(Netsiri et al., 2000)
fMRI			(Matsuo et al., 2000)
Dynamic PET	sICA (McKeown)	Determination of arterial input function	(Jang et al., 2000)
fMRI	sICA, tICA (FastICA)	Investigates sICA and tICA capability to separate paradigm signal	(Calhoun and Pekar, 2000)
fMRI	sICA with FastICA	Artifact detection: Gradient waveform corruption, bistable mean signal intensity change, Nyquist ghosting, high frequency, motion	(Beckmann et al., 2000a)
EEG			(Jung et al., 2001)
fMRI	sICA, tICA, stICA	Comparison of different ICA methods	(Caprihan and Anderson, 2001)
fMRI		Model selection	(Beckmann et al., 2001a)
fMRI	FastICA	Compares ICA with GLM modeling	(Beckmann et al., 2001b)
fMRI		Compared ICA with GLM modeling	(Calhoun et al., 2001b)
fMRI		Identification of motion artifacts	(Bannister et al., 2001)
fMRI	?	Group inference	(Calhoun et al., 2001a)
fMRI	sICA	Artifact detection	(Chuang and Chen, 2001)
fMRI	sICA infomax	Investigation of variation in the hemodynamic response function	(Duann et al., 2001a,2002a,2001b)
efMRI	stICA	with ``skewed probability density functions''	(Stone et al., 2002)
fMRI	Complex Infomax		(Calhoun et al., 2002c,a; Calhoun and Adali, 2002; Calhoun et al., 2002b)
pMRI			(Tasciyan et al., 2001)

Table 1 displays some of the `methods' papers in ICA for functional neuroimaging.

Hansen (1998) develops noisy ICA with a mean field approximation and applies it together with PCA on an fMRI data set.

fMRI ICA for multiple subjects

Multisubject data may be analyzed in a variety of ways (Calhoun et al., 2008; Schmitthort and Holland, 2004):

Pre-average data and then perform a single ICA (Schmitthort and Holland, 2004).
Perform single subject ICAs and then combine or correlate the subject specific independent component with each other (Calhoun et al., 2001b).
ICA with temporal concatenation. Here the subjects need to be in the same space, i.e., spatially normalized.
ICA with spatial concatenation. Here the design in the temporal dimension need to be the same, e.g., the stimulus need to occure at the same time point across subjects
Tensor-methods, e.g., PARAFAC.

A comparison on simulated data is reported in (Schmitthort and Holland, 2004).

Comparisons

Petersen et al. (2000) and Petersen (2000) compared spatial and temporal ICA with the infomax, DCA and Molgedey-Schuster (MS-ICA): MS-ICA was found to be much faster than BS-ICA and DCA and DCA much slower. BS-tICA and MS-sICA both had difficulties in separating the `interesting' component. Esposito et al. (2002) compared the Bell and Sejnowski (1995) algorithm with the Hyvärinen (1999).

Tools in functional neuroimaging

Table 2 display some of the programs that are in use for independent component analysis of brain signals.

Table 2: ICA tools in functional neuroimaginging.

Tool	Implementation	Description	Reference
AnalyzeFMRI	R	FastICA implementation(?)	http://www.stats.ox.ac.uk/~ marchini/software.html
BrainVoyager	Compiled for Windows, UNIX, Linux, Mac	``Cortex-based ICA''& http://www.brainvoyager.com/
EEGLAB	Matlab	EGG processing including ICA with GUI. Related to FMRLAB.	(Delorme and Makeig, 2003), http://www.sccn.ucsd.edu/eeglab/
FMRLAB	Matlab	Extended Infomax Algorithm	http://www.sccn.ucsd.edu/fmrlab/, (Bell and Sejnowski, 1995; Amari, 1999; Lee et al., 1999; Duann et al., 2002b)
GIFT	Matlab	``Group ICA of fMRI Toolbox''	(Egolf et al., 2004), http://icatb.sourceforge.net/
ICA:DTU toolbox	Matlab	Implements Bell and Sejnowski Maximum likelihood (Infomax) ICA and Mean Field ICA as well as Molgedey-Schuster ICA. With model selection.	http://mole.imm.dtu.dk/toolbox/ica/, (Kolenda et al., 2001; Hansen et al., 2000; Højen-Sørensen et al., 2002; Petersen et al., 2000; Hansen et al., 2001; Kolenda et al., 2000)
Lyngby	Matlab	The Bell-Sejnowski and Molgedey-Schuster algorithms are presently implemented	(Hansen et al., 1999b), http://hendrix.imm.dtu.dk/software/lyngby/
MELODIC	C	Part of FSL. Model order selection (number of sources). Inference on image map with mixture modelling	http://www.fmrib.ox.ac.uk/fsl/melodic2/ (Beckmann et al., 2001b; Beckmann and Smith, 2002a; Beckmann et al., 2001a,2000b,a; Beckmann and Smith, 2003,2002b)

Apart from those listed in the table there are other programs that is not specifically targeted for neuroimaging applications, e.g., ICALAB (http://www.bsp.brain.riken.jp/ICALAB/).

Application

Table 3: Application

Area	Type	Description	Reference
EEG	tICA		(Makeig et al., 1997)
Visual-Perception Task		GLM used in the same study	(Calhoun et al., 2001b)
ERP/EEG		ERP linked to phase resetting in the alpha rhythm	(Makeig et al., 2001,2002)
fMRI	Bell and Sejnowski ICA	Dynamic complex visual scences	(Zeki et al., 2003)

(Makeig et al., 2001,2002) used ICA to show that event-related potentials (ERPs) are linked to ``stationary'' EEG (alpha) activity of the brain through ``partial phase resetting of the EEG processes''.

A further ICA application is (Moritz et al., 2005).

Unclassified

(Shi et al., 2004).
(Arfanakis et al., 2000)
(Calhoun and Pekar, 2000): ```self-evident'' spatiotemporal components' .
(Calhoun et al., 2001c)
(Calhoun et al., 2001d)
V. D. Calhoun, T. Adali, G. D. Pearlson, ``Independent component analysis applied to fMRI data: A generative model for validating results,'' to appear Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology, Special Issue: Data Mining and Biomedical Applications of Neural Networks.
(Dodel et al., 2001)
(Esposito et al., 2001): rank ordering of ICs.
(Formisano et al., 2001,2004): Cortex-based ICA.
(Friston, 1998)
Gu H, Engelien W, Feng H, Silbersweig DA, Stern E, Yang Y. Mapping transient, randomly occurring neuropsychological events using independent component analysis. Neuroimage. 2001 Dec;14(6):1432-43. PMID: 11707099
(McKeown, 2000)
McKeown MJ, Sejnowski TJ. Independent component analysis of fMRI data: examining the assumptions. Hum Brain Mapp. 1998;6(5-6):368-72. PMID: 9788074
Moritz CH, Haughton VM, Cordes D, Quigley M, Meyerand E (2000): Whole-brain functional MR imaging activation from a finger-tapping task examined with independent component analysis. Am J Neuroradiol 21: 1629-1635
Suzuki K, Kiryu T, Nakada T. Fast and precise independent component analysis for high field fMRI time series tailored using prior information on spatiotemporal structure. Hum Brain Mapp. 2002 Jan;15(1):54-66. PMID: 11747100
Independent component analysis for noisy data - MEG data analysis S. Ikeda, K. Toyama NEURAL NETWORKS 13(10)
Consistency of Infomax ICA Decomposition of Functional Brain Imaging Data Jeng-Ren Duann, Tzyy-Ping Jung, Scott Makeig (Institute for Neural Computation, University of California San Diego), Terrence J. Sejnowski (Institute for Neural Computation, University of California San Diego, Computational Neurobiology Laboratory, The Salk Institute for Biological Studies), ICA2003
Independent Component Analysis of Auditory fMRI Responses Fabrizio Esposito (Second Division of Neurology - Second University of Naples, Italy), Elia Formisano (Department of Cognitive Neuroscience, Maastricht University, The Netherlands), Erich Seifritz (Department of Psychiatry - University of Basel, Switzerland), Raffaele Elefante (Department of Neurological Sciences, University of Naples, Italy), Rainer Goebel (Department of Cognitive Neuroscience, Maastricht University, The Netherlands), Francesco Di Salle (Department of Neurological Sciences, University of Naples, Italy), ICA2003
Combining ICA and Cortical Surface Reconstruction in Functional MRI Investigations of Human Brain Functions Elia Formisano (Department of Cognitive Neuroscience, Faculty of Psychology, Maastricht University, The Netherlands), Fabrizio Esposito (Second Division of Neurology - Second University of Naples, Italy), Francesco Di Salle (Department of Neurological Sciences, University of Naples, Italy), Rainer Goebel (Department of Cognitive Neuroscience, Faculty of Psychology, Maastricht University, The Netherlands), ICA2003
Independent Component Analysis with Joint Speedup and Supervisory Concept Injection: Applications to Brain fMRI Map Distillation Yasuo Matsuyama, Ryo Kawamura, Naoto Katsumata (Waseda University), ICA2003
Blind Identification of SEF Dynamics from MEG Data by using Decorrelation Method of ICA Kuniharu Kishida, Kenji Kato (Gifu University), Kazuhiro Shinosaki, Satoshi Ukai (Osaka University Graduate School of Medicine), ICA2003
Classification of Single Trial EEG Signals by a Combined Principal + Independent Component Analysis and Probabilistic Neural Network Approach Tetsuya Hoya, Gen Hori, Hovagim Bakardjian (BSI RIKEN), Tomoaki Nishimura, Taiji Suzuki (Dept. of Mathematical Engi., and Info. Physics Sch. of Engi., Univ. Tokyo), Yoichi Miyawaki, Arao Funase (BSI RIKEN), Jianting Cao (Dept. Elec. Engi., Saitama Institute of Technology), ICA2003
Deterministic and stochastic features of fMRI data: implications for data averaging. In ``Exploratory analysis and data modeling in functional neuroimaging'' 63-76, 2003, 0-262-19481-3. Martin J. McKeown

Bibliography

Amari, S. (1999).: Natural gradient learning for over- and under-complete bases in ICA.
Neural Computation, 11(8):1875-1883. PMID: 10578035.
Arfanakis, K., Cordes, D., Haughton, V. M., Moritz, C. H., Quigley, M. A., and Meyerand, M. E. (2000).: Combining independent component analysis and correlation analysis to probe interregional connectivity in fMRI task activation datasets.
Magnetic Resonance in Imaging, 18(8):921-930. PMID: 11121694.
Attias, H. and Schreiner, C. E. (1997).: Blind source separation and deconvolution by dynamic component analysis.
In Neural Networks for Signal Processing VII: Proceedings of the 1997 IEEE Workshop, pages 456-465.
Attias, H. and Schreiner, C. E. (1998).: Blind source separation and deconvolution: The dynamic component analysis algorithm.
Neural Computation, 10:1373-1424.
Bannister, P. R., Beckmann, C., and Jenkinson, M. (2001).: Exploratory motion analysis in fMRI using ICA.
NeuroImage, 13(6):S69.
Beckmann, C. F., Noble, J. A., and Smith, S. M. (2000a).: Artefact detection in FMRI data using independent component analysis.
In Fox and Lancaster (2000), page S614. ISSN 1053-8119 [ bibliotek.dk ] . Demonstrates artefact detection with sICA with FastICA in fMRI.
Beckmann, C. F., Noble, J. A., and Smith, S. M. (2001a).: Investigating the intrinsic dimensionality of FMRI data for ICA.
NeuroImage, 13(6):S76. http://www.apnet.com/www/journal/hbm2001/11384.html.
Beckmann, C. F., Noble, J. A., and Smith, S. M. (2001b).: Spatio-temporal accuracy of ICA for FMRI.
NeuroImage, 13(6):S75. http://www.apnet.com/www/journal/hbm2001/10671.html.
Beckmann, C. F. and Smith, S. M. (2002a).: Probabilistic extensions to independent component analysis for FMRI.
In NeuroImage, volume 16, San Diego. Organization for Human Brain Mapping, Academic Press.
Presented at the 8th International Conference on Functional Mapping of the Human Brain, June 2-6, 2002, Sendai, Japan. Available on CD-Rom.
Beckmann, C. F. and Smith, S. M. (2003).: Probabilistic ICA for FMRI -- noise and inference.
In Amari, S., Cichocki, A., Makino, S., and Murata, N., editors, Fourth Int. Symp. on Independent Component Analysis and Blind Signal Separation. ISBN 4990153108 [ bibliotek.dk | isbn.nu ] .
Beckmann, C. F. and Smith, S. S. (2002b).: Probabilistic independent component analysis in FMRI.
In Proceedings of the International Society of Magnetic Resonance in Medicine.
Beckmann, C. F., Tracey, I., Noble, J., and Smith, S. M. (2000b).: Combining ICA and GLM: A hybrid approach to FMRI analysis.
In Fox, P. T. and Lancaster, J. L., editors, Sixth Annual Meeting of the Organization For Human Brain Mapping, page S643, San Diego, California. Organization For Human Brain Mapping, Academic Press.
Bell, A. J. and Sejnowski, T. J. (1995).: An information maximisation approach to blind separation and blind deconvolution.
Neural Computation, 7(6):1129-1159. ftp://ftp.cnl.salk.edu/pub/tony/bell.blind.ps.Z. CiteSeer: http://citeseer.ist.psu.edu/bell95informationmaximization.html.
Biswal, B. B. and Ulmer, J. L. (1999).: Blind source separation of multiple signal sources of fMRI data sets using independent component analysis.
Journal of Computer Assisted Tomography, 23(2):265-271. PMID: 10096335. http://www.jcat.org/pt/re/jcat/abstract.00004728-199903000-00016.htm.
Calhoun, V. and Adali, T. (2002).: Complex infomax: Convergence and approximation of infomax with complex nonlinearities.
In 2002 IEEE International Workshop on Neural Networks for Signal Processing (NNSP 2002). IEEE Signal Processing Society. http://isp.imm.dtu.dk/cgi-bin/nnsp2002/view_abstract?idno=153.
Calhoun, V., Adali, T., Hansen, L. K., Larsen, J., and Pekar, J. (2003).: ICA of functional MRI data: an overview.
In Fourth International Symposium on Independent Component Analysis and Blind Source Separation, pages 281-288, Nara, Japan. http://www.kecl.ntt.co.jp/icl/signal/ica2003/cdrom/data/0219.pdf.
Calhoun, V., Adali, T., Pearlson, G., and Pekar, J. (2001a).: A method for making group inferences using independent component analysis of functional MRI data: Exploring the visual system.
NeuroImage, 13(6):S88. http://www.apnet.com/www/journal/hbm2001/9930.html. Briefly describes independent component analysis for multiple subjects.
Calhoun, V., Adali, T., Pearlson, G., and Pekar, J. (2002a).: A infomax method for performing ICA of fMRI data in the complex domain.
NeuroImage, 16(2):349. http://www.academicpress.com/journals/hbm2002/13822.html.
Presented at the 8th International Conference on Functional Mapping of the Human Brain, June 2-6, 2002, Sendai, Japan. Available on CD-Rom.
Calhoun, V., Adali, T., Pearlson, G., and Pekar, J. (2002b).: On complex infomax applied to functional MRI data.
In IEEE International Conference Acoustics, Speech and Signal Processing (ICASSP), 2002, Piscataway, New Jersey. IEEE Signal Processing Society, IEEE. http://www.csee.umbc.edu/~adali/pubs/IEEEpubs/icassp02calhoun.pdf. ISBN 0780374037 [ bibliotek.dk | isbn.nu ] .
Calhoun, V. and Pekar, J. (2000).: When and where are components independent? on the applicability of spatial- and temporal- ICA to functional MRI data.
In Fox and Lancaster (2000), page S682. ISSN 1053-8119 [ bibliotek.dk ] .
Calhoun, V. D., Adali, T., McGinty, V. B., Pekar, J. J., Watson, T. D., and Pearlson, G. D. (2001b).: fMRI activation in a visual-perception task: Network of areas detected using the general linear model and independent components analysis.
NeuroImage, 14(5):1080-1088. PMID: 11697939. http://www.idealibrary.com/links/doi/10.1006/nimg.2001.0921. ISSN 1053-8119 [ bibliotek.dk ] .
Calhoun, V. D., Adali, T., Pearlson, G. D., and Pekar, J. J. (2001c).: A method for making group inferences from functional mri data using independent component analysis.
Human Brain Mapping, 14(3):140-151. PMID: 11559959. http://download.interscience.wiley.com/cgi-bin/fulltext?ID=85010334&PLACEBO=IE.pdf&mode=pdf.
Calhoun, V. D., Adali, T., Pearlson, G. D., and Pekar, J. J. (2001d).: Spatial and temporal independent component analysis of functional MRI data containing a pair of task-related waveforms.
Human Brain Mapping, 13:43-53.
Calhoun, V. D., Adali, T., Pearlson, G. D., van Zijl, P. C. M., and Pekar, J. J. (2002c).: Independent component analysis of fMRI data in the complex domain.
Magnetic Resonance in Medicine, 48:180-192. http://www.csee.umbc.edu/~adali/pubs/others/MRM02.pdf.
Calhoun, V. D., Liu, J., and Adali, T. (2008).: In press.
Caprihan, A. and Anderson, L. K. (2001).: Evaluation of ICA methods for fMRI data analysis.
NeuroImage, 13(6, part 2):S89. http://www.apnet.com/www/journal/hbm2001/11403.html. Short description of comparison of different ICA methods for fMRI.
Chuang, K.-H. and Chen, J.-H. (2001).: Independent component analysis in the detection and correction of physiological artifacts in fMRI.
NeuroImage, 13(6):S94. http://www.apnet.com/www/journal/hbm2001/11196.html. Briefly describes spatial indenpendent component analysis for artifact detection.
Conradsen, K., Nielsen, B. K., and Thyrstedt, T. (1986).: A comparison of min/max autocorrelation factor analysis and ordinary factor analysis.
Technical report, IMSOR, Technical University of Denmark, Lyngby, Denmark.
Delorme, A. and Makeig, S. (2003).: EEGLAB: an open source toolbox for analysis of single-trial dynamics including indenpendent component analysis.
Journal of Neuroscience Methods. http://www.sccn.ucsd.edu/eeglab/download/eeglab_jnm03.pdf.
In press.
Dodel, S., Herrmann, J. M., and Geisel, T. (2001).: Is brain activity spatially or temporally correlated?
NeuroImage, 13(6):S110.
Duann, J.-R., Jung, T.-P., Kuo, W.-J., Yeh, T.-C., Makeig, S., Hsieh, J.-C., and Sejnowski, T. (2001a).: Blind decomposition reveals novel hemodynamics response features.
NeuroImage, 13(6):S111. http://www.apnet.com/www/journal/hbm2001/11613.html. Investigates the variation of the hemodynamic response in fMRI with Independent component analysis and find that it varies with site, subject and task and may vary widely from trial to trial.
Duann, J.-R., Jung, T.-P., Kuo, W.-J., Yeh, T.-C., Makeig, S., Hsieh, J.-C., and Sejnowski, T. (2002a).: Single-trial variability in event-related BOLD signals.
NeuroImage, 15(4):823-835. PMID: 11906223. DOI: 10.1006/nimg.2001.1049.
Duann, J.-R., Jung, T.-P., Kuo, W.-J., Yeh, T.-C., Makeig, S., Hsieh, J.-C., and Sejnowski, T. J. (2001b).: Measuring the variability of event-related bold signal.
In Lee, Jung, Makeig, S., and Sejnowski, T. J., editors, 3rd International Conference on INDEPENDENT COMPONENT ANALYSIS and BLIND SIGNAL SEPARATION. http://ica2001.ucsd.edu/index_files/pdfs/140-duann.pdf.
Duann, J.-R., Jung, T.-P., Makeig, S., and Sejnowski, T. J. (2002b).: fMRLAB: An ICA toolbox for fMRI data analysis.
In NeuroImage, volume 16. Elsevier. http://www.academicpress.com/www/journal/hbm2002/14973.html.
Presented at the 8th International Conference on Functional Mapping of the Human Brain, June 2-6, 2002, Sendai, Japan. Available on CD-Rom.
Egolf, E. A., Kiehl, K. A., and Calhoun, V. D. (2004).: Group ICA of fMRI toolbox GIFT.
NeuroImage, 22. http://icatb.sourceforge.net/Abstract_for_HBM.pdf.
Presented at the 10th Annual Meeting of the Organization for Human Brain Mapping, June 14-17, 2004, Budapest, Hungary. Available on CD-ROM.
Esposito, F., Formisano, E., Cirillo, S., Elefante, R., Tedeschi, G., Goebel, R., and Salle, F. D. (2001).: Criteria for the rank ordering of fMRI independent components.
NeuroImage, 13(6):S114.
Esposito, F., Formisano, E., Seifritz, E., Goebel, R., Morrone, R., Tedeschi, G., and Salle, F. D. (2002).: Spatial independent component analysis of functional MRI time-series: to what extent do results depend on the algorithm used?
Human Brain Mapping, 16(3):146-157. PMID: 12112768. http://www3.interscience.wiley.com/cgi-bin/abstract/93515228/.
Formisano, E., Esposito, F., Salle, F. D., and Goebel, R. (2001).: Cortex-based independent component analysis of fMRi time series.
NeuroImage, 13(6):S199.
Formisano, E., Esposito, F., Salle, F. D., and Goebel, R. (2004).: Cortex-based independent component analysis of fMRI time series.
Magnetic Resonance Imaging, 22(10):1493-1504.
Fox, P. T. and Lancaster, J. L., editors (2000).: Sixth International Conference on Functional Mapping of the Human Brain. NeuroImage, volume 11. Academic Press.
Friston, K. J. (1998).: Modes or models: a critique on independent component analysis for fMRI.
Trends in Cognitive Sciences, 2(10):373-375. Characterize independent component analysis as a data-led analysis in contrast to hypothesis driven analyses.
Georgiev, P. G. and Cichocki, A. (2001).: Blind source separation via symmetric eigenvalue decomposition.
In Proc. Sixth International Symposium on Signal Processing and its Applications, Shangri-La Hotel, Kuala Lumpur, Malaysia, Aug. 13-16, 2001, pages 17-20. http://www.bsp.brain.riken.jp/ICApub/Malaysiafin.pdf.
Green, A. A., Berman, M., Switzer, P., and Craig, M. D. (1988).: A transformation for ordering multispectral data in terms of image quality with implications for noise removal.
IEEE Transactions on Geoscience and Remote Sensing, 26(1):65-74.
Hansen, L. K. (1998).: Blind separation of noisy mixtures.
Draft, version 5.0, Informatics and Mathematical Modelling, Technical University of Denmark. http://isp.imm.dtu.dk/staff/lkhansen/mfica.ps.
Hansen, L. K. (2003).: ICA of fMRI based on a convolutive mixture model.
NeuroImage, 19(2). http://208.164.121.55/hbm2003/abstract/abstract840.htm.
Presented at the 9th International Conference on Functional Mapping of the Human Brain, June 19-22, 2003, New York, NY. Available on CD-Rom.
Hansen, L. K. and Dyrholm, M. (2003).: A prediction matrix approach to convolutive ICA.
In IEEE Workshop on Neural Networks and Signal Processing, Toulouse, France. http://isp.imm.dtu.dk/cgi-bin/nnsp2003/view_abstract?idno=139.
Hansen, L. K., Larsen, J., and Kolenda, T. (2000).: On independent component analysis for multimedia signals.
In Guan, L., Kung, S. Y., and Larsen, J., editors, Multimedia Image and Video Processing, chapter 7, pages 175-199. CRC Press. http://mole.imm.dtu.dk/thko_project/hansen.mmica.pdf. CiteSeer: http://citeseer.ist.psu.edu/hansen00independent.html. ISBN 0849334926 [ bibliotek.dk | isbn.nu ] .
Hansen, L. K., Larsen, J., and Kolenda, T. (2001).: Blind detection of independent dynamic components.
In Proceedings of ICASSP'2001, volume 5, pages 3197-3200. http://isp.imm.dtu.dk/publications/2001/hansen.icassp2001.pdf.
Hansen, L. K., Larsen, J., Nielsen, F. Å., Strother, S. C., Rostrup, E., Savoy, R., Svarer, C., and Paulson, O. B. (1999a).: Generalizable patterns in neuroimaging: How many principal components?
NeuroImage, 9(5):534-544. PMID: 10329293. DOI: 10.1006/nimg.1998.0425. http://www.sciencedirect.com/science/article/B6WNP-45FCP5S-22/2/5497508502c843a1f4aae8d11bdf3632.
Hansen, L. K., Nielsen, F. Å., Toft, P., Liptrot, M. G., Goutte, C., Strother, S. C., Lange, N., Gade, A., Rottenberg, D. A., and Paulson, O. B. (1999b).: ``lyngby'' -- a modeler's Matlab toolbox for spatio-temporal analysis of functional neuroimages.
In Rosen, B. R., Seitz, R. J., and Volkmann, J., editors, Fifth International Conference on Functional Mapping of the Human Brain, NeuroImage, volume 9, page S241. Academic Press. http://isp.imm.dtu.dk/publications/1999/hansen.hbm99.ps.gz. ISSN 1053-8119 [ bibliotek.dk ] .
Hansen, L. K., Nielsen, F. Å., Toft, P., Strother, S. C., Lange, N., Mørch, N. J. S., Svarer, C., Paulson, O. B., Savoy, R., Rosen, B. R., Rostrup, E., and Born, P. (1997).: How many principal components?
In Friberg, L., Gjedde, A., Holm, S., Lassen, N. A., and Nowak, M., editors, Third International Conference on Functional Mapping of the Human Brain, NeuroImage, volume 5, page S474. Academic Press. http://isp.imm.dtu.dk/publications/1997/HBM97.principal.poster474.ps.gz. ISSN 1053-8119 [ bibliotek.dk ] .
Højen-Sørensen, P., Hansen, L. K., and Winther, O. (2001).: Mean field implementation of Bayesian ICA.
In Proceedings of 3rd International Conference on Independent Component Analysis and Blind Signal Separation (ICA2001). http://www.imm.dtu.dk/pubdb/views/publication_details.php?id=612. CiteSeer: http://citeseer.ist.psu.edu/557466.html.
Højen-Sørensen, P. A. d. F. R., Winther, O., and Hansen, L. K. (2002).: Mean field approaches to independent component analysis.
Neural Computation, 14(4):889-918. http://isp.imm.dtu.dk/staff/winther/hojen.ica.pdf. CiteSeer: http://citeseer.ist.psu.edu/455328.html.
Hyvärinen, A. (1999).: Fast and robust fixed-point algorithms for independent component analysis.
IEEE Transactions on Neural Networks, 10(3):626-634. http://www.cs.helsinki.fi/u/ahyvarin/papers/TNN99new.pdf.
Hyvärinen, A. and Oja, E. (2000).: Independent component analysis: Algorithms and applications.
Neural Networks, 13(4-5):411-430. http://www.cis.hut.fi/~aapo/papers/IJCNN99_tutorialweb/.
Jang, M. J., Ahn, J. Y., Lee, D. S., Lee, J. S., Chung, J.-K., and Lee, M. C. (2000).: The use of independent component analysis for the noninvasive derivation of arterial input functiona from brain dynamic O-15 water PET.
NeuroImage, 11(5):S588. .
Jung, T.-P., Makeig, S., Westerfield, M., Townsend, J., Courchesne, E., and Sejnowski, T. J. (2001).: Analysis and visualization of single-trial event-related potentials.
Human Brain Mapping, 14:166-185.
Kolenda, T. (2002).: Adaptive tools in virtual environments.
PhD thesis, Informatics and Mathematical Modeling, Technical University of Denmark, Lyngby, Denmark.
IMM-PHD-2002-94. http://www.imm.dtu.dk/pubdb/views/publication_details.php?id=905.
Kolenda, T., Hansen, L. K., and Larsen, J. (2001).: Signal detection using ICA: Application to chat room topic spotting.
In ICA'2001, pages 540-545. http://isp.imm.dtu.dk/publications/2001/kolenda.ica2001.pdf.
Kolenda, T., Hansen, L. K., and Sigurdsson, S. (2000).: Independent components in text.
In Girolami, M., editor, Advances in Independent Component Analysis, Perspectives on Neural Computing, chapter 13. Springer Verlag, Berlin, Germany. http://www.imm.dtu.dk/pubdb/views/edoc_download.php/830/zip/imm830.zip. ISBN 1852332638 [ bibliotek.dk | isbn.nu ] .
Lange, N., Strother, S. C., Anderson, J. R., Nielsen, F. Å., Holmes, A. P., Kolenda, T., Savoy, R., and Hansen, L. K. (1999).: Plurality and resemblance in fMRI data analysis.
NeuroImage, 10(3):282-303. PMID: 10458943. DOI: 10.1006/nimg.1999.0472. http://www.sciencedirect.com/science/article/B6WNP-45FCP48-13/2/bd7e7f72099b83540609e24c627a2fc4.
Lee, T.-W., Girolami, M., and Sejnowski, T. J. (1999).: Independent component analysis using an extended infomax algorithm for mixed sub-gaussian and super-gaussian sources.
Neural Computation, 11(2):417-441. CiteSeer: http://citeseer.ist.psu.edu/lee97independent.html.
MacKay, D. J. C. (1999).: Maximum likelihood and covariant algorithm for independent component analysis.
Version 3.8. ftp://www.inference.phy.cam.ac.uk/pub/mackay/ica.ps.gz.
Makeig, S., Jung, T.-P., Bell, A. J., Ghahremani, D., and Sejnowski, T. J. (1997).: Blind separation of auditory event-related brain responses into independent components.
Proceedings of the National Academy of Sciences of the United States of America, 94(20):10979-10984. http://www.pnas.org/cgi/content/full/94/20/10979.
Makeig, S., Jung, T.-P., Westerfield, M., and Sejnowski, T. J. (2001).: Imaging event-related brain dynamics.
NeuroImaging, 13(6, part 2):S1309. http://www.apnet.com/www/journal/hbm2001/11612.html.
Makeig, S., Westerfield, M., Jung, T.-P., Enghoff, S., Townsend, J., Courchesne, E., and Sejnowski, T. J. (2002).: Dynamic brain sources of visual evoked responses.
Science, 295(5555):690-694. http://www.sciencemag.org/cgi/content/short/295/5555/690.
Matsuo, K., Muraki, S., Okada, T., Moriya, T., and Nakai, T. (2000).: Independent component analysis separated multiple task components in one fMRI time series.
NeuroImage, 5(5, part 2):S660.
McKeown, M. J. (2000).: Detection of consistently task-related activations in fMRI data with hybrid independent component analysis.
NeuroImage, 11(1):24-35. PMID: 10686114. DOI: 10.1006/nimg.1999.0518. http://defiant.ssc.uwo.ca/fmri/pdfs/NeuroImage_2000_Hybrid_ICA.pdf.
McKeown, M. J., Hansen, L. K., and Sejnowski, T. J. (2003).: Independent component analysis of functional MRI: what is signal and what is noise?
Current Opinion in Neurobiology, 13(5):620-629. DOI: 10.1016/j.conb.2003.09.012. http://www.sciencedirect.com/science/article/B6VS3-49KSYHS-3/2/33c893ac09a9a693d1a4fe11372a49da.
McKeown, M. J., Jung, T.-P., Makeig, S., Brown, G., Kindermann, S. S., Lee, T.-W., and Sejnowski, T. J. (1998a).: Spatially independent activity patterns in functional MRI data during the Stroop color-naming task.
Proceedings of the National academy of Sciences USA, 95:803-810. file://ftp.cnl.salk.edu/pub/jung/PNASfMRI.ps.Z.
McKeown, M. J., Makeig, S., Brown, G. B., Jung, T.-B., Kindermann, S. S., Bell, A. J., and Sejnowski, T. J. (1998b).: Analysis of fMRI data by blind separation into independent spatial components.
Human Brain Mapping, 6:160-188.
Molgedey, L. and Schuster, H. G. (1994).: Separation of a mixture of independent signals using time delayed correlations.
Physical Review Letters, 72(23):3634-3637. PMID: 10056251. http://www.theo-physik.uni-kiel.de/thesis/molgedey94.ps.gz. CiteSeer: http://citeseer.ist.psu.edu/molgedey94separation.html.
Moritz, C. H., Carew, J. D., McMillan, A. B., and Meyerand, M. E. (2005).: Independent component analysis applied to self-paced functional MR imaging paradigms.
NeuroImage, 25(1):181-192.
Muraki, S. and Nakai, T. (1999).: Time including independent component analysis of fMRI data.
NeuroImage, 9(6):S81. Apply tICA on fMRI.
Netsiri, C., Gustard, S., Carpenter, T. A., Williams, E. J., and Huang, C. L.-H. (2000).: Reliability of blind separation of non-smoothed fMRI data using ICA.
In Fox and Lancaster (2000), page S516. http://www.academicpress.com/www/journal/hbm2000/6392.html. ISSN 1053-8119 [ bibliotek.dk ] .
Nielsen, A. A. (1994).: Analysis of regularly and irregularly sampled spatial, multivariate and multi-temporal data.
PhD thesis, IMM, Technical University of Denmark, Lyngby, Denmark. http://www.imm.dtu.dk/~aa/phd/.
Petersen, K. S. (2000).: Signalseparation med uafhængig komponent analysis (ICA).
Master's thesis, Department of Mathematical Modelling, Technical University of Denmark, Lyngby, Denmark.
IMM-EKS-2000-3, In Danish.
Petersen, K. S., Hansen, L. K., Kolenda, T., Rostrup, E., and Strother, S. C. (2000).: On the independent components of functional neuroimages.
In Third International Conference on Independent Component Analysis and Blind Source Separation (ICA2000), pages 615-620. http://isp.imm.dtu.dk/staff/thko/hansen.ica2000.ps.gz. CiteSeer: http://citeseer.ist.psu.edu/petersen00independent.html.
Schmitthort, V. J. and Holland, S. K. (2004).: A comparison of three methods for generating group statistical inferences from independent component analysis of fMRI data.
Journal of Magnetic Resonance in Imaging, 19(3):365-368.
Shi, Z., Tang, L. P. H., and Tang, Y. (2004).: An improved gradient learning algorithm for spatial independent component analysis of functional MRI data.
Neural Information Processing -- Letters and Reviews, 5(1):1-8. http://www.nip-lr.info/V05N01/V05N01P1-1-8.pdf.
Stone, J. V. (2002).: Independent component analysis: An introduction.
Trends in Cognitive Sciences, 6(2):59-64. http://reviews.bmn.com/journals/atoz/latest?pii=S1364661300018131.
Stone, J. V., Porrill, J., and N. R. Porter, I. D. W. (2002).: Spatiotemporal independent component analysis of event-related fMRI data using skewed probability density functions.
NeuroImage, 15(2):407-421. PMID: 11798275.
Switzer, P. and Green, A. A. (1984).: Min/max autocorrelation factors for multivariate spatial imagery.
Technical Report 6, Department of Statistics, Stanford University, Stanford, California.
Tasciyan, T. A., Beckmann, C. F., Morris, E. D., and Smith, S. M. (2001).: ICA-based segmentation of the brain on perfusion data.
In 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society. http://www.indyrad.iupui.edu/public/emorris/abstracts/IEEE2001-abstract-126_TalinICA_Perf.pdf.
Ulmer, J. and Biswal, B. (2000).: The potential of independent component analysis to estimate signal waveforms from compromised FMRI data sets.
In Fox and Lancaster (2000), page S676. ISSN 1053-8119 [ bibliotek.dk ] . Demonstration of ICA to separate task-related from non-task related (hypercapnia) signals.
Zeki, S., Perry, R. J., and Bartels, A. (2003).: The processing of kinetic contours in the brain.
Cerebral Cortex, 13(2):189-202. PMID: 12507950. WOBIB: 52. ISSN 1047-3211 [ bibliotek.dk ] .

Index

AnalyzeFMRI: Tools in functional neuroimaging
BrainVoyager: Tools in functional neuroimaging
DCA: Methods
EEGLAB: Tools in functional neuroimaging
FMRLAB: Tools in functional neuroimaging
GIFT: Tools in functional neuroimaging
ICA:DTU toolbox: Tools in functional neuroimaging
ICALAB: Tools in functional neuroimaging
Infomax: Methods
Lyngby: Tools in functional neuroimaging
MELODIC: Tools in functional neuroimaging
min/max autocorrelation factorization: Methods
Molgedey-Schuster: Tools in functional neuroimaging
PICA: Methods

Finn Årup Nielsen 2010-04-23

Bibliography on Independent Component Analysis in Functional Neuroimaging

Abstract:

Bibliography on Independent Component Analysis
in Functional Neuroimaging