Skip to main content
SpringerLink
Log in

Exploratory Analysis of Brain with ICA

  • Chapter
  • First Online:
Blind Source Separation

Part of the book series: Signals and Communication Technology ((SCT))

  • 2840 Accesses

Abstract

This chapter introduces the use of independent component analysis (ICA) in the study of electroencephalographic (EEG) data. Though the main application of ICA is in the context of denoising, we prefer to focus our attention to the independent components of artifacts-free EEG data. The interpretation of these independent components is still controversial, and we outline the more accepted alternatives. An introduction to the results obtained when applying ICA to evoked potentials (EPs) and event-related potentials (ERPs) is presented, as well as an explanation of the ICA of natural images and its relationship with models of visual cortex is also presented. This chapter is written as a general introduction to the subject for those who want to get started in the main topics.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    The hippocampus plays an important role in the formation of new memories, and in spatial orientation. It also seems to be related to behavioral inhibition.

  2. 2.

    The hypothalamus is involved in emotion and endocrine function control, hunger, and sleep–wake cycle regulation, among other tasks. It also controls the pituitary gland.

  3. 3.

    The amygdala is involved in memory, emotion, and fear.

  4. 4.

    The thalamus regulates auditory, somatosensory, and visual sensory information. All sensory stimuli, with the exception of smell, is received in the cortex after passing through the thalamus.

  5. 5.

    See Sect. 16.2.3.

  6. 6.

    P300 (also called P3 or late positive component or LPC) is a reliable positive ERP that peaks at approximately 300 ms after the presentation of relevant or infrequent stimuli. It has two subcomponents, P3a and P3b, which respectively originate from frontal and parietal lobes. P3a is associated with the response to a change in the environment, while the amplitude of P3b is inversely proportional to the probability of the stimulus. P300 also seems to be correlated with decision-making processes.

  7. 7.

    The term “grand average” means that the author averaged together epochs from many subjects.

  8. 8.

    N1 is a large EP that appears in visual discrimination tasks.

  9. 9.

    HOS = Higher Order Statistics. SOS = Second-Order Statistics.

  10. 10.

    The number of epochs ranged from 300 to 700.

  11. 11.

    Given the ICA model \(\mathbf{x} = \mathbf{A}\,\mathbf{s}\), where \(\mathbf{x}\) stands for the observations and \(\mathbf{s}\) represents the independent components, we project back to the scalp these independent components simply by setting the other independent components to zero. In other words, the observations are reconstructed considering only the contribution of the independent components time-locked to the visual stimuli.

  12. 12.

    P1 (or P100) is an EP sensitive to visual discrimination tasks that peaks at 100–130 ms after stimulus presentation and is modulated by attention.

  13. 13.

    Each cell in the visual cortex responds only to the presence of light in a well-defined part of the retina, called the receptive field of the cell. The part of the visual scene projected on that area of the retina is also called “receptive field”. Roughly speaking, we may think that the job of the cell is to report to the rest of the brain what is happening in that little area.

  14. 14.

    The pixels of each pack are stacked one under the other to form the associated \(\textit{MN} \times 1\) observation vector.

  15. 15.

    Actually, this statement has to be taken with care: all basis functions (more or less) equally contribute to many image patches.

  16. 16.

    Interestingly, in the original formulation of the algorithm [58], \(g(\mathbf{w})\) is defined as \(g(\mathbf{w}) = E[r(t)\,y(t)] - \epsilon \).

References

  1. Adankon, M., Chihab, N., Dansereau, J., Labelle, H., Cheriet, F.: Scoliosis follow-up using non-invasive trunk surface acquisition. IEEE Trans. Biomed. Eng. 60(8), 2262–2270 (2013)

    Google Scholar 

  2. Anemüller, J., Sejnowski, T., Makeig, S.: Complex independent component analysis of frequency-domain electroencephalographic data. Neural Netw. 16(9), 1311–1323 (2003)

    Article  Google Scholar 

  3. Barlow, H.B.: Possible principles underlying the transformation of sensory messages. In: Rosenblith, W.A. (ed.) Sensory Communication, pp. 217–234. MIT Press, Cambridge (1961)

    Google Scholar 

  4. Barlow, H.B.: Unsupervised learning. Neural Comput. 1, 295–311 (1989)

    Article  Google Scholar 

  5. Barlow, H.B.: Redundancy reduction revisited. Netw. Comput. Neural Syst. 12, 241–253 (2001)

    Google Scholar 

  6. Barros, A., Vigario, R., Jousmaki, V., Ohnishi, N.: Extraction of event-related signals from multichannel bioelectrical measurements. IEEE Trans. Biomed. Eng. 47(5), 583–588 (2000)

    Article  Google Scholar 

  7. Bell, A.J., Sejnowski, T.J.: An information maximisation approach to blind separation and blind deconvolution. Neural Comput. 7, 1129–1159 (1995)

    Article  Google Scholar 

  8. Bell, A.J., Sejnowski, T.J.: Edges are the ‘independent components’ of natural scenes. Adv. Neural Inf. Process. Syst. 9, 831–837 (1997)

    Google Scholar 

  9. Bishop, D., Anderson, M., Reid, C., Fox, A.: Auditory development between 7 and 11 years: an event-related potential study. PLoS ONE 6, e18, 993 (2011)

    Google Scholar 

  10. Can, Y., Kumar, B., Coimbra, M.: Heartbeat classification using morphological and dynamic features of ECG signals. IEEE Trans. Biomed. Eng. 59(10), 2930–2941 (2012)

    Article  Google Scholar 

  11. Cao, J., Zhao, L., Cichocki, A.: Visualization of dynamic brain activities based on single-trial MEG and EEG data analysis. In: Lecture Notes in Computer Science, vol. 3973, pp. 531–540. Springer, Berlin (2006)

    Google Scholar 

  12. Castells, F., Rieta, J., Millet, J., Zarzoso, V.: Spatiotemporal blind source separation approach to atrial activity estimation in atrial tachyarrhythmias. IEEE Trans. Biomed. Eng. 52(2), 258–267 (2005)

    Article  Google Scholar 

  13. Caywood, M., Willmore, B., Tolhurst, D.: Independent components of color natural scenes resemble v1 neurons in their spatial and color tuning. J. Neurophysiol. 91, 2854–2873 (2004)

    Article  Google Scholar 

  14. Chen, X., He, C., Wang, Z., McKeown, M.: An IC-PLS framework for group corticomuscular coupling analysis. IEEE Trans. Biomed. Eng. 60(7), 2022–2033 (2013)

    Article  Google Scholar 

  15. Chen, Y., Akutagawa, M., Katayama, M., Zhang, Q., Kinouchi, Y.: Ica based multiple brain sources localization. In: 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), pp. 1879–1882 (2008)

    Google Scholar 

  16. Chen, Z., Ohara, S., Cao, J., Vialatte, F., Lenz, F., Cichocki, A.: Statistical modeling and analysis of laser-evoked potentials of electrocorticogram recordings from awake humans. Comput. Intell. Neurosci. 2007, 1–24 (2007)

    Article  Google Scholar 

  17. Chin-Teng, L., I-Fang, C., Li-Wei, K., Yu-Chieh, C., Sheng-Fu, L., Jeng-Ren, D.: EEG-based assessment of driver cognitive responses in a dynamic virtual-reality driving environment. IEEE Trans. Biomed. Eng. 54(7), 1349–1352 (2007)

    Article  Google Scholar 

  18. Dammers, J., Schiek, M., Boers, F., Silex, C., Zvyagintsev, M., Pietrzyk, U., Mathiak, K.: Integration of amplitude and phase statistics for complete artifact removal in independent components of neuromagnetic recordings. IEEE Trans. Biomed. Eng. 55(10), 2353–2362 (2008)

    Article  Google Scholar 

  19. De Clercq, W., Vergult, A., Vanrumste, B., Van Paesschen, W., Van Huffel, S.: Canonical correlation analysis applied to remove muscle artifacts from the electroencephalogram. IEEE Trans. Biomed. Eng. 53(12), 2583–2587 (2006)

    Article  Google Scholar 

  20. De Lathauwer, L., De Moor, B., Vandewalle, J.: Fetal electrocardiogram extraction by blind source subspace separation. IEEE Trans. Biomed. Eng. 47(5), 567–572 (2000)

    Article  Google Scholar 

  21. Delorme, A., Palmer, J., Onton, J., Oostenveld, R., Makeig, S.: Independent EEG sources are dipolar. PloS one 7(2), e30135 (2012)

    Google Scholar 

  22. Dyrholm, M., Goldman, R., Sajda, P., Brown, T.: Removal of BCG artifacts using a non-kirchhoffian overcomplete representation. IEEE Trans. Biomed. Eng. 56(2), 200–204 (2009)

    Article  Google Scholar 

  23. Escudero, J., Hornero, R., Abasolo, D., Fernández, A., Lopez-Coronado, M.: Artifact removal in magnetoencephalogram background activity with independent component analysis. IEEE Trans. Biomed. Eng. 54(11), 1965–1973 (2007)

    Article  Google Scholar 

  24. Field, D.J.: Relations between the statistics of natural images and the response properties of cortical cells. J. Opt. Soc. Am. A 4, 2379–2394 (1987)

    Article  Google Scholar 

  25. Field, D.J.: What is the goal of sensory coding? Neural Comput. 6, 559–601 (1994)

    Article  Google Scholar 

  26. Groppe, D., Makeig, S., Kutas, M.: Identifying reliable independent components via split-half comparisons. Neuroimage 45(4), 1199–2011 (2009)

    Article  Google Scholar 

  27. Grosse-Wentrup, M., Buss, M.: Multiclass common spatial patterns and information theoretic feature extraction. IEEE Trans. Biomed. Eng. 55(8), 1991–2000 (2008)

    Article  Google Scholar 

  28. Guimaraes, M., Wong, D.K., Uy, E., Grosenick, L., Suppes, P.: Single-trial classification of MEG recordings. IEEE Trans. Biomed. Eng. 54(3), 436–443 (2007)

    Article  Google Scholar 

  29. Guyton, A.C., Hall, J.E.: Textbook of medical physiology. Saunders, Philadelphia (2000)

    Google Scholar 

  30. Hae-Jeong, P., Do-Un, J., Kwang-Suk, P.: Automated detection and elimination of periodic ECG artifacts in EEG using the energy interval histogram method. IEEE Trans. Biomed. Eng. 49(12), 1526–1533 (2002)

    Article  Google Scholar 

  31. Hancock, P.J., Baddeley, R., Smith, L.: The principle components of natural images. Neural Comput. 3, 61–72 (1992)

    Article  Google Scholar 

  32. Hesse, C., James, C.: The fastica algorithm with spatial constraints. IEEE Signal Process. Lett. 12(11), 792–795 (2005)

    Article  Google Scholar 

  33. Hesse, C., James, C.: On semi-blind source separation using spatial constraints with applications in EEG analysis. IEEE Trans. Biomed. Eng. 53(12), 2525–2534 (2006)

    Article  Google Scholar 

  34. Hild, K., Nagarajan, S.: Source localization of EEG/MEG data by correlating columns of ICA and lead field matrices. IEEE Trans. Biomed. Eng. 56(11), 2619–2626 (2009)

    Article  Google Scholar 

  35. Hu, S., Stead, M., Worrell, G.: Automatic identification and removal of scalp reference signal for intracranial EEGs based on independent component analysis. IEEE Trans. Biomed. Eng. 54(9), 1560–1572 (2007)

    Article  Google Scholar 

  36. Hualiang, L., Correa, N., Rodriguez, P., Calhoun, V., Adali, T.: Application of independent component analysis with adaptive density model to complex-valued fMRI data. IEEE Trans. Biomed. Eng. 58(10), 2794–2803 (2011)

    Article  Google Scholar 

  37. Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in cat’s visual cortex. J. Physiol. 160, 106–154 (1962)

    Google Scholar 

  38. Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture of the monkey striate cortex. J. Physiol. 195, 215–243 (1968)

    Google Scholar 

  39. Hyvärinen, A.: Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. Neural Netw. 10(3), 626–634 (1999)

    Article  Google Scholar 

  40. Hyvärinen, A., Gutmann, M., Hoyer, P.: Statistical model of natural stimuli predicts edge-like pooling of spatial frequency channels in v2. BMC Neurosci. (2005). doi:10.1186/1471-2202-6-12

  41. Hyvärinen, A., Hoyer, P., Hurri, J.: Extensions of ICA as models of natural images and visual processing. In: Proceedings of 4th International Symposium on Independent Component Analysis and Blind, Signal Separation (ICA2003) (2003)

    Google Scholar 

  42. Hyvärinen, A., Hoyer, P., Inki, M.: Topographic ICA as a model of v1 receptive fields. Neural Netw. 4, 83–88 (2000)

    Google Scholar 

  43. Iriarte, J., Urrestarazu, E., Valencia, M., Alegre, M., Malanda, A.: Independent component analysis as a tool to eliminate artifacts in EEG: a quantitative study. J. Clin. Neurophysiol. 20, 249–257 (2003)

    Article  Google Scholar 

  44. Irimia, A., Richards, W., Bradshaw, L.: Comparison of conventional filtering and independent component analysis for artifact reduction in simultaneous gastric EMG and magnetogastrography from porcines. IEEE Trans. Biomed. Eng. 56(11), 2611–2618 (2009)

    Article  Google Scholar 

  45. Jafari, M., Chambers, J.: Fetal electrocardiogram extraction by sequential source separation in the wavelet domain. IEEE Trans. Biomed. Eng. 52(3), 390–400 (2005). doi:10.1109/TBME.2004.842958

    Article  Google Scholar 

  46. James, C., Gibson, O.: Temporally constrained ICA: an application to artifact rejection in electromagnetic brain signal analysis. IEEE Trans. Biomed. Eng. 50(9), 1108–1116 (2003)

    Article  Google Scholar 

  47. Jentzsch, I.: Independent component analysis separates sequence-sensitive ERP components. Int. J. Bifurcat. Chaos 14(2), 667–678 (2004)

    Article  MATH  Google Scholar 

  48. Joyce, C., Gorodnitsky, I., Kutas, M.: Automatic removal of eye movement and blink artifacts from EEG data using blind component separation. Psychophysiology 41, 313–325 (2004)

    Article  Google Scholar 

  49. Jung T-P. adn Makeig, S., Westerfield, M., Townsend, J., Courchesne, E., Sejnowski, T.J.: Removal of eye activity artifacts from visual event-related potentials in normal and clinical subjects. Clin. Neurophysiol. 11, 1754–1758 (2000)

    Google Scholar 

  50. Jung, T.P., Makeig, S., McKeown, M., Bell, A.J., Lee, T.W., Sejnowski, T.: Imaging brain dynamics using independent component analysis. Proc. IEEE 89(7), 1107–1122 (2001)

    Article  Google Scholar 

  51. Jung, T.P., Makeig, S., Westerfield, M., Townsend, J., Courchesne, E., Sejnowski, T.J.: Analysis and visualization of sigle-trial event-related potentials. Hum. Brain Mapp. 14(3), 166–185 (2001)

    Article  Google Scholar 

  52. Kadah, Y.: Adaptive denoising of event-related functional magnetic resonance imaging data using spectral subtraction. IEEE Trans. Biomed. Eng. 51(11), 1944–1953 (2004)

    Article  Google Scholar 

  53. Kelly, J., Siewiorek, D., Smailagic, A., Collinger, J., Weber, D., Wang, W.: Fully automated reduction of ocular artifacts in high-dimensional neural data. IEEE Trans. Biomed. Eng. 58(3), 598–606 (2011)

    Article  Google Scholar 

  54. Kim, B., Yoo, S.: Motion artifact reduction in photoplethysmography using independent component analysis. IEEE Trans. Biomed. Eng. 53(3), 566–568 (2006)

    Article  Google Scholar 

  55. Koutras, A., Kostopoulos, G., Ioannides, A.: Exploring the variability of single trials in somatosensory evoked responses using constrained source extraction and RMT. IEEE Trans. Biomed. Eng. 55(3), 957–969 (2008)

    Article  Google Scholar 

  56. Krishnan, R., Natarajan, B., Warren, S.: Two-stage approach for detection and reduction of motion artifacts in photoplethysmographic data. IEEE Trans. Biomed. Eng. 57(8), 1867–1876 (2010)

    Article  Google Scholar 

  57. Langley, P., Rieta, J., Stridh, M., Millet, J., Sornmo, L., Murray, A.: Comparison of atrial signal extraction algorithms in 12-lead ECGs with atrial fibrillation. IEEE Trans. Biomed. Eng. 53(2), 343–346 (2006)

    Article  Google Scholar 

  58. Lu, W., Rajapakse, J.C.: ICA with reference. In: Proceedings of 3rd International Conference on Independent Component Analysis and Blind, Signal Separation, pp. 120–125 (2001)

    Google Scholar 

  59. Mabrouk, R., Dubeau, F., Bentabet, L.: Dynamic cardiac PET imaging: extraction of time-activity curves using ICA and a generalized gaussian distribution model. IEEE Trans. Biomed. Eng. 60(1), 63–71 (2013)

    Article  Google Scholar 

  60. Makeig, S., Bell, A.J., Jung, T.P., Sejnowski, T.: Independent component analysis of electroencephalographic data. In: D. Touretzky, M. Mozer (eds.) Advances in Neural Information Processing Systems, vol. 8, pp. 145–151. MIT Press, Cambridge (1996)

    Google Scholar 

  61. Makeig, S., Onton, J.: Oxford Handbook of Event-Related Potential Components, chap. ERP features and EEG dynamics: and ICA perspective, pp. 51–88. Oxford University Press, New York (2012)

    Google Scholar 

  62. Makeig, S., Westerfield, M., Jung, T.P., Covington, J., Townsend, J., Sejnowski, T.J., Courhesne, E.: Functionally independent components of the late positive event-related potential during visual spatial attention. J. Neurosci. 19(7), 2665–2680 (1999)

    Google Scholar 

  63. Makeig, S., Westerfield, M., Jung, T.P., Enghoff, S., Townsend, J., Courchesne, E., Sejnowski, T.: Dynamic brain sours of visual evoked responses. Science 295(5555), 690–694 (2002)

    Article  Google Scholar 

  64. Martín-Clemente, R., Camargo-Olivares, J.: Independent Component Analysis for Audio and Biosignal Applications, Chap. ICA-Based Fetal Monitoring, pp. 247–268. Intech, Vienna (2012)

    Google Scholar 

  65. Martín-Clemente, R., Camargo-Olivares, J., Hornillo-Mellado, S., Elena, M., Román, I.: Fast technique for noninvasive fetal ECG extraction. IEEE Trans. Biomed. Eng. 58(2), 227–230 (2011)

    Article  Google Scholar 

  66. McCubbin, J., Robinson, S., Cropp, R., Moiseev, A., Vrba, J., Murphy, P., Preissl, H., Eswaran, H.: Optimal reduction of MCG in fetal MEG recordings. IEEE Trans. Biomed. Eng. 53(8), 1720–1724 (2006)

    Article  Google Scholar 

  67. Müller, K.R., Vigário, R., Meinecke, F., Ziehe, A.: Blind source separation techniques for decomposing event-related brain signals. Int. J. Bifurcat. Chaos 14(2), 773–791 (2004)

    Article  MATH  Google Scholar 

  68. Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381, 607–609 (1996)

    Article  Google Scholar 

  69. Olshausen, B.A., Field, D.J.: Natural image statistics and efficient coding. Network 7, 333–339 (1996)

    Article  Google Scholar 

  70. Ossadtchi, A., Baillet, S., Mosher, J., Thyerleid, D., Sutherling, W., Leahy, R.: Automated interictal spike detection and source localization in magnetoencephalography using independent component analysis and spatio-temporal clustering. Clin. Neurophysiol. 115, 508–522 (2004)

    Google Scholar 

  71. Phlypo, R., Zarzoso, V., Lemahieu, I.: Atrial activity estimation from atrial fibrillation ECGs by blind source extraction based on a conditional maximum likelihood approach. Med. Biol. Eng. Comput. 48(5), 483–488 (2010)

    Article  Google Scholar 

  72. Sanei, S., Chambers, J.A.: EEG Signal Processing. Wiley, New York (2007)

    Google Scholar 

  73. Särelä, J., Vigário, R.: Overlearning in marginal distribution-based ICA: analysis and solutions. J. Mach. Learn. Res. 4, 1447–1469 (2003)

    Google Scholar 

  74. Shi-Yun, S., Kai-Quan, S., Chong-Jin, O., Wilder-Smith, E., Xiao-Ping, L.: Automatic EEG artifact removal: a weighted support vector machine approach with error correction. IEEE Trans. Biomed. Eng. 56(2), 336–344 (2009)

    Article  Google Scholar 

  75. Tang, A., Pearlmutter, B., Malaszenko, N., Phung, D.: Independent components of magnetoencephalography: localization. Neural Comput. 14, 1827–1858 (2002)

    Article  MATH  Google Scholar 

  76. Vigario, R.: Extraction of ocular artefacts from EEG using independent component analysis. Clin. Neurophysiol. 103, 395–404 (1997)

    Article  Google Scholar 

  77. Vigário, R., Oja, E.: BSS and ICA in neuroinformatics: from current practices to open challenges. IEEE Rev. Biomed. Eng. 1, 50–61 (2008). doi:10.1109/RBME.2008.2008244

    Article  Google Scholar 

  78. Vigário, R., Sarela, J., Jousmiki, V., Hainen, M., Oja, E.: Independent component approach to the analysis of eeg and meg recordings. IEEE Trans. Biomed. Eng. 47, 589–593 (2000)

    Google Scholar 

  79. Wang, W., Zhang, Z., Gao, X., Gao, S.: Lead selection for SSVEP-based brain computer interface. In: Proceedings of the 26th International Conference on Engineering in Medicine and Biology Society (EBS 04), pp. 4507–4510 (2004)

    Google Scholar 

  80. Xu, N., Xiaorong, G., Hong, B., Xiaobo, M., Shangkai, G., Fusheng, Y.: BCI competition 2003 data set IIB: Enhancing p 300 wave detection using ICA-based subspace projections for BCI applications. IEEE Trans. Biomed. Eng. 51(6), 1067–1072 (2004). doi:10.1109/TBME.2004.826699

Download references

Acknowledgments

This work was supported by the Andalusian Regional Government (under the program entitled Programa de Proyectos de Excelencia) under project P07-TIC-02865. We are also grateful to S. Makeig and A. Delorme for their permission to include graphs and figures generated with EEGLAB in the manuscript.

Author information

Authors and Affiliations

  1. Department of Signal Processing and Communications, University of Seville, Sevilla, Spain

    Rubén Martín-Clemente

Authors
  1. Rubén Martín-Clemente
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rubén Martín-Clemente .

Editor information

Editors and Affiliations

  1. University of Technology, Sydney, Sydney, Australia

    Ganesh R. Naik

  2. University of Surrey, Guildford, United Kingdom

    Wenwu Wang

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Martín-Clemente, R. (2014). Exploratory Analysis of Brain with ICA. In: Naik, G., Wang, W. (eds) Blind Source Separation. Signals and Communication Technology. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-55016-4_16

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-55016-4_16

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-55015-7

  • Online ISBN: 978-3-642-55016-4

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation