Independent component analysis, a data-driven analysis method, has found significant applications in task-based as well as resting state fMRI studies. There are numbers of independent component analysis algorithms available, but only a few of them have been used frequently so far for fMRI images. With a view that algorithms that are overlooked may outperform the most opted, a comparative study is taken up in this paper to analyze their abilities for the purpose of synthesis of fMRI images. In this paper, ten independent component algorithms: Fast ICA, INFOMAX, SIMBEC, JADE, ERICA, EVD, RADICAL, ICA-EBM, ERBM, and COMBI are compared. Their separation abilities are adjudged on both, synthetic and real fMRI images. Performance to decompose synthetic fMRI images is being monitored on the basis of spatial correlation coefficients, time elapsed to extract independent components and the visual appearance of independent components. Ranking of their performances on task-based real fMRI images are based on the closeness of time courses of identified independent components with model time course and the closeness of spatial maps of components with spatial templates while their competencies for resting state fMRI data are analyzed by examining how distinctly they decompose the data into the most consistent resting state networks. Sum of mutual information between all the permutations of decomposed components of resting state fMRI data are also calculated.
AllenE.A., ErhardtE.B., DamarajuE., GrunerW., SegallJ.M., SilvaR.F., HavlicekM., RachakondaS., FriesJ., KalyanamR. and MichaelA.M., A baseline for the multivariate comparison of resting-state networks, Frontiers in Systems Neuroscience5 (2011), 2.
2.
BellA.J. and SejnowskiT.J., An information-maximization approach to blind separation and blind deconvolution, Neural Computation7 (1995), 1129–1159. doi:10.1162/neco.1995.7.6.1129.
3.
BiswalB., Zerrin YetkinF., HaughtonV.M. and HydeJ.S., Functional connectivity in the motor cortex of resting human brain using echo-planar mri, Magnetic Resonance in Medicine34 (1995), 537–541. doi:10.1002/mrm.1910340409.
4.
BiswalB.B., Resting state fMRI: A personal history, Neuroimage62 (2012), 938–944. doi:10.1016/j.neuroimage.2012.01.090.
CalhounV.D., AdaliT., HansenL.K., LarsenJ. and PekarJ.J., ICA of Functional MRI Data: An Overview, 2003.
7.
CardosoJ.-F. and SouloumiacA., Blind beamforming for non-Gaussian signals, in: IEE Proceedings F (Radar and Signal Processing), 1993, pp. 362–370.
8.
CorreaN., AdalıT. and CalhounV.D., Performance of blind source separation algorithms for fMRI analysis using a group ICA method, Magnetic Resonance Imaging25 (2007), 684–694. doi:10.1016/j.mri.2006.10.017.
9.
CorreaN., AdaliT., LiY.-O. and CalhounV.D., Comparison of blind source separation algorithms for fMRI using a new Matlab toolbox: GIFT, in: Proceedings. (ICASSP’05). IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 5, 2005, pp. v/401–v/404.
10.
CrucesS., CastedoL. and CichockiA., Robust blind source separation algorithms using cumulants, Neurocomputing49 (2002), 87–118. doi:10.1016/S0925-2312(02)00525-8.
11.
CrucesS., CichockiA. and AmariS.-I., Criteria for the simultaneous blind extraction of arbitrary groups of sources, in: Proc. Int. Conf. on ICA and BSS, 2001, pp. 740–745.
12.
DamoiseauxJ., RomboutsS., BarkhofF., ScheltensP., StamC., SmithS.M. and BeckmannC.F., Consistent resting-state networks across healthy subjects, Proceedings of the National Academy of Sciences103 (2006), 13848–13853. doi:10.1073/pnas.0601417103.
13.
DaubechiesI., RoussosE., TakerkartS., BenharroshM., GoldenC., D'ardenneK.et al., Independent component analysis for brain fMRI does not select for independence, Proceedings of the National Academy of Sciences106 (2009), 10415–10422. doi:10.1073/pnas.0903525106.
14.
Di MartinoA., YanC.-G., LiQ., DenioE., CastellanosF.X., AlaertsK., AndersonJ.S., AssafM., BookheimerS.Y., DaprettoM. and DeenB., The autism brain imaging data exchange: Towards a large-scale evaluation of the intrinsic brain architecture in autism, Molecular Psychiatry19 (2014), 659–667. doi:10.1038/mp.2013.78.
15.
DuW., MaS., FuG.-S., CalhounV.D. and AdaliT., A novel approach for assessing reliability of ICA for fMRI analysis, in: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014, pp. 2084–2088. doi:10.1109/ICASSP.2014.6853966.
16.
ErhardtE.B., AllenE.A., WeiY., EicheleT. and CalhounV.D., SimTB, a simulation toolbox for fMRI data under a model of spatiotemporal separability, Neuroimage59 (2012), 4160–4167. doi:10.1016/j.neuroimage.2011.11.088.
17.
GeorgievP. and CichockiA., Blind source separation via symmetric eigenvalue decomposition, in: Sixth International Symposium on Signal Processing and Its Applications, 2001, pp. 17–20.
18.
GreiciusM.D., SupekarK., MenonV. and DoughertyR.F., Resting-state functional connectivity reflects structural connectivity in the default mode network, Cerebral Cortex19 (2009), 72–78. doi:10.1093/cercor/bhn059.
19.
GudbjartssonH. and PatzS., The Rician distribution of noisy MRI data, Magnetic Resonance in Medicine34 (1995), 910–914. doi:10.1002/mrm.1910340618.
20.
HoneyC., SpornsO., CammounL., GigandetX., ThiranJ.P., MeuliR. and HagmannP., Predicting human resting-state functional connectivity from structural connectivity, Proceedings of the National Academy of Sciences106 (2009), 2035–2040. doi:10.1073/pnas.0811168106.
21.
HyvärinenA. and OjaE., A fast fixed-point algorithm for independent component analysis, Neural Computation9 (1997), 1483–1492. doi:10.1162/neco.1997.9.7.1483.
22.
LiX.-L. and AdaliT., Independent component analysis by entropy bound minimization, IEEE Transactions on Signal Processing58 (2010), 5151–5164. doi:10.1109/TSP.2010.2055859.
23.
LiX.-L. and AdaliT., Blind spatiotemporal separation of second and/or higher-order correlated sources by entropy rate minimization, in: 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2010, pp. 1934–1937. doi:10.1109/ICASSP.2010.5495311.
24.
McKeownM.J., HansenL.K. and SejnowskiT.J., Independent component analysis of functional MRI: What is signal and what is noise?, Current Opinion in Neurobiology13 (2003), 620–629. doi:10.1016/j.conb.2003.09.012.
25.
MillerE.G. and FisherJ.W.III, Independent components analysis by direct entropy minimization, DTIC Document 2003.
26.
MoussaM.N., SteenM.R., LaurientiP.J. and HayasakaS., Consistency of network modules in resting-state fMRI connectome data, PloS One7 (2012), e44428.
27.
PernetC., AnderssonJ., PaulesuE. and DemonetJ.F., When all hypotheses are right: A multifocal account of dyslexia, Human Brain Mapping30 (2009), 2278–2292. doi:10.1002/hbm.20670.
28.
PierceK., Early functional brain development in autism and the promise of sleep fMRI, Brain Research1380 (2011), 162–174. doi:10.1016/j.brainres.2010.09.028.
29.
RachakondaS., EgolfE. and CalhounV., Group ICA of FMRI Toolbox (GIFT) Walk Through, 2011.
RaichleM.E. and SnyderA.Z., A default mode of brain function: A brief history of an evolving idea, Neuroimage37 (2007), 1083–1090. doi:10.1016/j.neuroimage.2007.02.041.
32.
RedcayE., KennedyD.P. and CourchesneE., FMRI during natural sleep as a method to study brain function during early childhood, Neuroimage38 (2007), 696–707. doi:10.1016/j.neuroimage.2007.08.005.
33.
RobinsonS., BassoG., SoldatiN., SailerU., JovicichJ., BruzzoneL., Kryspin-ExnerI., BauerH. and MoserE., A resting state network in the motor control circuit of the basal ganglia, BMC Neuroscience10 (2009), 137. doi:10.1186/1471-2202-10-137.
34.
RobinsonS.D. and SchopfV., ICA of fMRI Studies: New Approaches and Cutting Edge Applications, Front Hum Neurosci7 (2013), 724.
35.
SabriM., HumphriesC., VerberM., LiebenthalE., BinderJ.R., MangalathuJ. and DesaiA., Neural effects of cognitive control load on auditory selective attention, Neuropsychologia61 (2014), 269–279. doi:10.1016/j.neuropsychologia.2014.06.009.
36.
TichavskyP., KoldovskyZ., DoronE., YeredorA. and Gómez-HerreroG., Blind signal separation by combining two ICA algorithms: HOS-based EFICA and time structure-based WASOBI, in: 14th European Signal Processing Conference, 2006, pp. 1–5.
37.
Van Den HeuvelM.P. and PolH.E.H., Exploring the brain network: A review on resting-state fMRI functional connectivity, European Neuropsychopharmacology20 (2010), 519–534. doi:10.1016/j.euroneuro.2010.03.008.
