A critique of Tensor Probabilistic Independent Component Analysis: Implications and recommendations for multi-subject fMRI data analysis

Journal of Neuroscience Methods

Volumn 213, Issue 2, 2013, Pages 263-273

  Helwig, Nathaniel E ^a   Hong, Sungjin ^a  

^a UNIVERSITY OF ILLINOIS AT URBANA CHAMPAIGN   (United States)

Author keywords

Neuroimage data analysis; Parafac; Parallel Factor Analysis; PICA; Tensor PICA; Tensor Probabilistic Independent Component Analysis

Indexed keywords

ALGORITHM; ARTICLE; DATA ANALYSIS; FACTORIAL ANALYSIS; FUNCTIONAL MAGNETIC RESONANCE IMAGING; INDEPENDENT COMPONENT ANALYSIS; INTERMETHOD COMPARISON; NEUROIMAGING; PARALLEL FACTOR ANALYSIS; PRIORITY JOURNAL; SIMULATION; TENSOR PROBABILISTIC INDEPENDENT COMPONENT ANALYSIS;

HUMANS; IMAGE INTERPRETATION, COMPUTER-ASSISTED; MAGNETIC RESONANCE IMAGING;

EID: 84873159873     PISSN: 01650270     EISSN: 1872678X     Source Type: Journal    
DOI: 10.1016/j.jneumeth.2012.12.009     Document Type: Article

References (35)

1. Beckmann C.F., Smith S.M. Probabilistic independent component analysis for functional magnetic resonance imaging. IEEE Trans Med Imag 2004, 23(2):137-152.
2. Beckmann C.F., Smith S.M. Tensorial extensions of independent component analysis for multisubject fMRI analysis. Neuroimage 2005, 25(1):294-311.
3. Calhoun V.D., Eichele T., Adali T., Allen E.A. Decomposing the brain: components and modes, networks and nodes. Trends Cogn Sci 2012, 16(5):255-256.
4. Cardoso J.-F., Souloumiac A. Blind beamforming for non-Gaussian signals. IEEE Proc F 1993, 140(6):362-370.
5. Cardoso J.-F., Souloumiac A. Jacobi angles for simultaneous diagonalization. SIAM J Matrix Anal Appl 1996, 17(1):161-164.
6. Comon P. Independent component analysis, a new concept?. Signal Process 1994, 36(3):287-314.
7. De Lathauwer L., De Moor B., Vandewalle J. An introduction to independent component analysis. J Chemometr 2000, 14(3):123-149.
8. De Silva V., Lim L.-H. Tensor rank and the ill-posedness of the best low-rank approximation problem. SIAM J Matrix Anal. Appl. 2008, 30(3):1084-1127.
9. De Vos M., Nion D., Van Huffel S., De Lathauwer L. A combination of parallel factor and independent component analysis. Signal Process 2012, 92(12):2990-2999.
10. Friston K.J. Modes or models: a critique on independent component analysis for fMRI. Trends Cogn Sci 1998, 2(10):373-375.
11. Hermans E.J., van Marle H.J.F., Ossewaarde L., Henckens J.A.G., Qin S., van Kesteren M.T.R., et al. Stress-related noradrenergic activity prompts large-scale neural network reconfiguration. Science 2011, 334(6059):1151-1153.
12. Harshman R.A. Foundations of the PARAFAC procedure: models and conditions for an " explanatory" multimodal factor analysis. UCLA Work Papers Phon 1970, 16(1):1-84.
13. Harshman R.A. PARAFAC2: mathematical and technical notes. UCLA Work Papers Phon 1972, 22(1):30-44.
14. Harshman R.A., Lundy M.E. The PARAFAC model for three-way factor analysis and multidimensional scaling. Research methods for multimode data analysis 1984, 122-215. Praeger, New York. H.G. Law, C.W. Snyder, J. Hattie, R.P. McDonald (Eds.).
15. Harshman R.A., Lundy M.E. PARAFAC: parallel factor analysis. Comput Stat Data Anal 1994, 18(1):39-72.
16. Hotelling H. Analysis of a complex of statistical variables into principal components. J Educ Psychol 1933, 24(6):417-441. [24 (7): 498-520].
17. Hyvärinen A. Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans Neural Netw 1999, 10(3):626-634.
18. Ibarretxe-Bilbao N., Zarei M., Junque C., Marti M.J., Segura B., Vendrell P., et al. Dysfunctions of cerebral networks precede recognition memory deficits in early Parkinson's disease. Neuroimage 2011, 57(2):589-597.
19. Jeong B., Kubicki M. Reduced task-related suppression during semantic repetition priming in schizophrenia. Psychiat Res-Neuroim 2010, 181(2):114-120.
20. Krijnen W.P., Dijkstra T.K., Stegeman A. On the non-existence of optimal solutions and the occurrence of " degeneracy" in the Candecomp/Parafac model. Psychometrika 2008, 73(3):431-439.
21. Kruskal J.B. Three-way arrays: rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statistics. Linear Algebra Appl 1977, 18(2):95-138.
22. Leech R., Kamourieh S., Beckmann C.F., Sharp D.J. Fractionating the default mode network: distinct contributions of the ventral and dorsal posterior cingulate cortex to cognitive control. J Neurosci 2011, 31(9):3217-3224.
23. Lesage E., Apps M.A.J., Hayter A.L., Beckmann C.F., Barnes D., Langdon D.W., et al. Cerebellar information processing in relapsing-remitting multiple sclerosis (RRMS). Behav Neurol 2010, 23(1-2):39-49.
24. McKeown M.J., Makeig S., Brown G.G., Jung T.-P., Kindermann S.S., Bell A.J., et al. Analysis of fMRI data by blind separation into independent spatial components. Hum Brain Mapp 1998, 6(3):160-188.
25. McKeown M.J., Makeig S., Brown G.G., Jung T.-P., Kindermann S.S., Bell A.J., et al. Response to Modes or models: a critique on independent component analysis for fMRI. Trends Cogn Sci 1998, 2(10):375.
26. O'Muircheartaigh J., Vollmar C., Traynor C., Barker G.J., Kumari V., Symms M.R., et al. Clustering probabilistic tractograms using independent component analysis applied to the thalamus. Neuroimage 2011, 54(3):2020-2032.
27. Pearson K. On lines and planes of closest fit to systems of points in space. Philos Mag 1901, 2(11):559-572.
28. Poudel G.R., Jones R.D., Innes C.R.H., Watts R., Davidson P.R., Bones P.J. Measurement of BOLD changes due to cued eye-closure and stopping during a continuous visuomotor task via model-based and model-free approaches. IEEE Trans Neur Syst Rehab 2010, 18(5):479-488.
29. Sala-Llonch R., Bosch B., Arenaza-Urquijo E.M., Rami L., Bargalló N., Junqué C., et al. Greater default-mode network abnormalities compared to high order visual processing systems in amnestic mild cognitive impairment: an integrated multi-modal MRI study. J Alzheimers Dis 2010, 22(2):523-539.
30. Sauvage C., Poirriez S., Manto M., Jissendi P., Habas C. Reevaluating brain networks activated during mental imagery of finger movements using probabilistic Tensorial Independent Component Analysis (TICA). Brain Imag Behav 2011, 5(2):137-148.
31. Stegeman A. Comparing independent component analysis and the Parafac model for artificial multi-subject fMRI data. Unpublished manuscript, University of Groningen: Groningen, 2007. Available at www.gmw.rug.nl/∼stegeman.
32. Stegeman A. CANDECOMP/PARAFAC: from diverging components to a decomposition in block terms. SIAM J Matrix Anal Appl 2012, 33(2):291-316.
33. Stegeman A., Sidiropoulos N.D. On Kruskal's uniqueness condition for the Candecomp/Parafac decomposition. Linear Algebra Appl 2007, 420(2-3):540-552.
34. Timmerman M.E., Kiers H.A.L. Four simultaneous component models for the analysis of multivariate time series from more than one subject to model intraindividual and interindividual differences. Psychometrika 2003, 68(1):105-121.
35. Wolf I., Dziobek I., Heekeren H.R. Neural correlates of social cognition in naturalistic settings: a model-free analysis approach. Neuroimage 2010, 49(1):894-904.