Display options
Cite
Soldati N, Calhoun VD, Bruzzone L, et al. ICA analysis of fMRI with real-time constraints: an evaluation of fast detection performance as function of algorithms, parameters and a priori conditions. Front Hum Neurosci. 2013;7:19doi: 10.3389/fnhum.2013.00019.
Soldati, N., Calhoun, V. D., Bruzzone, L., & Jovicich, J. (2013). ICA analysis of fMRI with real-time constraints: an evaluation of fast detection performance as function of algorithms, parameters and a priori conditions. Frontiers in human neuroscience, 719. https://doi.org/10.3389/fnhum.2013.00019
Soldati, Nicola, et al. "ICA analysis of fMRI with real-time constraints: an evaluation of fast detection performance as function of algorithms, parameters and a priori conditions." Frontiers in human neuroscience vol. 7 (2013): 19. doi: https://doi.org/10.3389/fnhum.2013.00019
Soldati N, Calhoun VD, Bruzzone L, Jovicich J. ICA analysis of fMRI with real-time constraints: an evaluation of fast detection performance as function of algorithms, parameters and a priori conditions. Front Hum Neurosci. 2013 Feb 01;7:19. doi: 10.3389/fnhum.2013.00019. eCollection 2013. PMID: 23378835; PMCID: PMC3561692.
Copy Download .nbib Format: NLM
Share it on

Front Hum Neurosci. 2013 Feb 01;7:19. doi: 10.3389/fnhum.2013.00019. eCollection 2013.

ICA analysis of fMRI with real-time constraints: an evaluation of fast detection performance as function of algorithms, parameters and a priori conditions.

Frontiers in human neuroscience

Nicola Soldati, Vince D Calhoun, Lorenzo Bruzzone, Jorge Jovicich

Affiliations

  1. CIMeC, Interdipartimental Center for Mind/Brain Sciences, University of Trento Trento, Italy.

PMID: 23378835 PMCID: PMC3561692 DOI: 10.3389/fnhum.2013.00019

Abstract

Independent component analysis (ICA) techniques offer a data-driven possibility to analyze brain functional MRI data in real-time. Typical ICA methods used in functional magnetic resonance imaging (fMRI), however, have been until now mostly developed and optimized for the off-line case in which all data is available. Real-time experiments are ill-posed for ICA in that several constraints are added: limited data, limited analysis time and dynamic changes in the data and computational speed. Previous studies have shown that particular choices of ICA parameters can be used to monitor real-time fMRI (rt-fMRI) brain activation, but it is unknown how other choices would perform. In this rt-fMRI simulation study we investigate and compare the performance of 14 different publicly available ICA algorithms systematically sampling different growing window lengths (WLs), model order (MO) as well as a priori conditions (none, spatial or temporal). Performance is evaluated by computing the spatial and temporal correlation to a target component as well as computation time. Four algorithms are identified as best performing (constrained ICA, fastICA, amuse, and evd), with their corresponding parameter choices. Both spatial and temporal priors are found to provide equal or improved performances in similarity to the target compared with their off-line counterpart, with greatly reduced computation costs. This study suggests parameter choices that can be further investigated in a sliding-window approach for a rt-fMRI experiment.

Keywords: ill-posed problems; independent component analysis; real-time; whole-brain fMRI

References

  1. Nat Rev Neurosci. 2008 Sep;9(9):720-9 - PubMed
  2. J Neurosci. 2011 Nov 9;31(45):16309-17 - PubMed
  3. Neural Netw. 2000 May-Jun;13(4-5):411-30 - PubMed
  4. Neuroimage. 2003 Dec;20(4):2209-24 - PubMed
  5. Neuroimage. 2012 Aug 15;62(2):748-56 - PubMed
  6. Neuroimage. 2003 Nov;20(3):1661-9 - PubMed
  7. Neural Comput. 1999 Feb 15;11(2):417-41 - PubMed
  8. IEEE Eng Med Biol Mag. 2006 Mar-Apr;25(2):79-90 - PubMed
  9. Magn Reson Imaging. 2007 Jun;25(5):684-94 - PubMed
  10. Science. 2011 Dec 9;334(6061):1413-5 - PubMed
  11. Hum Brain Mapp. 2001 May;13(1):43-53 - PubMed
  12. Neural Comput. 1999 Nov 15;11(8):1875-83 - PubMed
  13. Neural Comput. 1995 Nov;7(6):1129-59 - PubMed
  14. Hum Brain Mapp. 1998;6(3):160-88 - PubMed
  15. BMC Neurosci. 2009 Nov 23;10:137 - PubMed
  16. Neuroimage. 2007 Jan 1;34(1):177-94 - PubMed
  17. Hum Brain Mapp. 2010 Jul;31(7):1076-88 - PubMed
  18. Proc Natl Acad Sci U S A. 2006 Sep 12;103(37):13848-53 - PubMed
  19. Hum Brain Mapp. 2002 Jul;16(3):146-57 - PubMed
  20. Neuroscientist. 2012 Oct;18(5):487-501 - PubMed
  21. Neuroimage. 2012 Aug 15;62(2):682-92 - PubMed
  22. Neuroimage. 2011 May 15;56(2):440-54 - PubMed
  23. IEEE Trans Neural Netw. 2006 Sep;17(5):1265-77 - PubMed

Publication Types