Advertisement

Improving the Quality of EEG Data in Patients with Alzheimer’s Disease Using ICA

  • François-Benoit Vialatte
  • Jordi Solé-Casals
  • Monique Maurice
  • Charles Latchoumane
  • Nigel Hudson
  • Sunil Wimalaratna
  • Jaeseung Jeong
  • Andrzej Cichocki
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5507)

Abstract

Does Independent Component Analysis (ICA) denature EEG signals? We applied ICA to two groups of subjects (mild Alzheimer patients and control subjects). The aim of this study was to examine whether or not the ICA method can reduce both group differences and within-subject variability. We found that ICA diminished Leave-One-Out root mean square error (RMSE) of validation (from 0.32 to 0.28), indicative of the reduction of group difference. More interestingly, ICA reduced the inter-subject variability within each group (σ= 2.54 in the δ range before ICA, σ= 1.56 after, Bartlett p = 0.046 after Bonferroni correction). Additionally, we present a method to limit the impact of human error (≃ 13.8%, with 75.6% inter-cleaner agreement) during ICA cleaning, and reduce human bias. These findings suggests the novel usefulness of ICA in clinical EEG in Alzheimer’s disease for reduction of subject variability.

Keywords

Root Mean Square Error Independent Component Analysis Independent Component Analysis Blind Source Separation Independent Component Analysis Method 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ille, N., Berg, P., Scherg, M.: Artifact correction of the ongoing eeg using spatial filters based on artifact and brain signal topographies. Journal of clinical neurophysiology 19(2), 113–124 (2002)CrossRefGoogle Scholar
  2. 2.
    Jung, T.P., Makeig, S., Humphries, C., Lee, T.-W., McKeown, M.J., Iragui, V., Sejnowski, T.J.: Removing electroencephalographic artifacts by blind source separation. Psychophysiology 37, 163–178 (2000)CrossRefGoogle Scholar
  3. 3.
    Cichocki, A.: Blind Signal Processing Methods for Analyzing Multichannel Brain Signals. International Journal of Bioelectromagnetism 6(1) (2004)Google Scholar
  4. 4.
    Cichocki, A., Shishkin, S.L., Musha, T., Leonowicz, Z., Asada, T., Kurachi, T.: EEG filtering based on blind source separation (BSS) for early detection of Alzheimer”s disease. Clinical Neurophysiology 116(3), 729–737 (2006)CrossRefGoogle Scholar
  5. 5.
    Anderer, P., Roberts, S., Schlogl, A., Gruber, G., Klosch, G., Herrmann, W., Rappelsberger, P., Filz, O., Barbanoj, M.J., Dorffner, G., Saletu, B.: Artifact processing in computerized analysis of sleep eeg - a review. Neuropsychobiology 40(3), 150–157 (1999)CrossRefGoogle Scholar
  6. 6.
    Van de Velde, M.: Signal Validation in Electroencephalography Research. PhD thesis, Technische Universiteit Eindhoven, Netherlands (January 2000)Google Scholar
  7. 7.
    Woon, W.L., Cichocki, A., Vialatte, F., Musha, T.: Techniques for early detection of Alzheimer’s disease using spontaneous EEG recordings. Physiological Measurement 28(4), 335–347 (2007)CrossRefGoogle Scholar
  8. 8.
    Melissant, C., Ypma, A., Frietman, E.E., Stam, C.J.: A method for detection of Alzheimer’s disease using ICA-enhanced EEG measurements. Artif. Intell. 33(3), 209–222 (2005)CrossRefGoogle Scholar
  9. 9.
    Escudero, J., Hornero, R., Poza, J., Abásolo, D., Fernández, A.: Assessment of classification improvement in patients with Alzheimer’s disease based on magnetoencephalogram blind source separation. Artif. Intell. Med. 43, 75–85 (2008)CrossRefGoogle Scholar
  10. 10.
    Cichocki, A., Amari, S., Siwek, K., Tanaka, T., Phan, A.-H.: ICALAB version 3 toolbox, http://www.bsp.brain.riken.jp/ICALAB/
  11. 11.
    Henderson, G., Ifeachor, E., Hudson, N., Goh, C., Outram, N., Wimalaratna, S., Del Percio, C., Vecchio, F.: Development and assessment of methods for detecting dementia using the human electroencephalogram. IEEE Trans. Biom. Eng. 53, 1557–1568 (2006)CrossRefGoogle Scholar
  12. 12.
    Barlow, J.S.: The Electroencephalogram: Its Patterns and Origins. MIT Press, Cambridge (1993)Google Scholar
  13. 13.
    Tichavský, P., Yeredor, A., Nielsen, J.: A Fast Approximate Joint Diagonalization Algorithm Using a Criterion with a Block Diagonal Weight Matrix. In: Proc. ICASSP 2008, Las Vegas, USA (2008)Google Scholar
  14. 14.
    Yeredor, A.: Blind separation of Gaussian sources via second-order statistics with asymptotically optimal weighting. IEEE Signal Processing Letters 7, 197–200 (2000)CrossRefGoogle Scholar
  15. 15.
    Tichavský, P., Doron, E., Yeredor, A., Nielsen, J.: A Computationally Affordable Implementation an Asymptotically Optimal BSS algorithm for AR Sources. In: EUSIPCO 2006, Florence, Italy (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • François-Benoit Vialatte
    • 1
  • Jordi Solé-Casals
    • 2
  • Monique Maurice
    • 1
  • Charles Latchoumane
    • 3
  • Nigel Hudson
    • 4
  • Sunil Wimalaratna
    • 5
  • Jaeseung Jeong
    • 3
  • Andrzej Cichocki
    • 1
  1. 1.Riken BSI, Lab. ABSP, Wako-ShiJapan
  2. 2.Signal Processing Group, VicUniversity of VicSpain
  3. 3.Dept of Bio and Brain EngineeringKAISTDaejeonSouth Korea
  4. 4.Dept of NeurophysiologyDerriford HospitalPlymouthUK
  5. 5.Dept of NeurologyRadcliffe InfirmaryOxfordUK

Personalised recommendations