ICA CLEANING PROCEDURE FOR EEG SIGNALS ANALYSIS - Application to Alzheimer's Disease Detection

J. Solé-Casals, F. Vialatte, J. Pantel, D. Prvulovic, C. Haenschel, A. Cichocki

2010

Abstract

To develop systems in order to detect Alzheimer’s disease we want to use EEG signals. Available database is raw, so the first step must be to clean signals properly. We propose a new way of ICA cleaning on a database recorded from patients with Alzheimer's disease (mildAD, early stage). Two researchers visually inspected all the signals (EEG channels), and each recording's least corrupted (artefact-clean) continuous 20 sec interval were chosen for the analysis. Each trial was then decomposed using ICA. Sources were ordered using a kurtosis measure, and the researchers cleared up to seven sources per trial corresponding to artefacts (eye movements, EMG corruption, EKG, etc), using three criteria: (i) Isolated source on the scalp (only a few electrodes contribute to the source), (ii) Abnormal wave shape (drifts, eye blinks, sharp waves, etc.), (iii) Source of abnormally high amplitude (≥100 μV). We then evaluated the outcome of this cleaning by means of the classification of patients using multilayer perceptron neural networks. Results are very satisfactory and performance is increased from 50.9% to 73.1% correctly classified data using ICA cleaning procedure.

References

  1. Ferri, C. P., Prince, M., Brayne, C., and et al., H. B. (2006). Global prevalence of dementia: a delphi consensus study. In The Lancet, vol. 366, pp. 2112- 2117.
  2. Alexander, G. E. (2002). Longitudinal pet evaluation of cerebral metabolic decline in dementia: A potential outcome measure in alzheimer's disease treatment studies. In American Journal of Psychiatry, vol. 159, pp. 738-745.
  3. Deweer, B., Lehericy, S., Pillon, B., Baulac, M., and et al. (1995). Memory disorders in probable alzheimer's disease: the role of hippocampal atrophy as shown with mri. In British Medical Journal, vol. 58, p. 590.
  4. Tanzi, R. E. and Bertram, L. (2001). New frontiers in alzheimer's disease genetics. In Neuron, vol. 32, pp. 181-184.
  5. Andreasen, N., Minthon, L., Davidsson, P., Vanmechelen, E., and et al. (2001). Evaluation of csf-tau and csf-a?2 as diagnostic markers for alzheimer disease in clinical practice. In Am Med Assoc, vol. 58, pp. 373-379.
  6. Solé-Casals, J., Vialatte, F., and Cichocki, Z. C. A. (2008).
  7. Investigation of ICA algorithms for feature extraction of EEG signals in discrimination of Alzheimer disease. In Proc. International Conference on Bio-Inspired Systems and Signal Processing, Biosignals, pp. 232- 235.
  8. Cichocki, A. and Amari, S. (2002). Adaptive Blind Signal and Image Processing. Wiley, New York.
  9. Cichocki, A., Amari, S. et al. (WWW). Icalab toolboxes. http://www.bsp.brain.riken.jp/ICALAB.Duda, R.O., Hart, P.E. and Stork, D., 2000 Pattern Classification. Wiley.
  10. Fukunaga, K., 1990 Introduction to Statistical Pattern Classification. Academic Press, San Diego, California, USA.
  11. Lippmann, D.E. (1987). “An Introduction to Computing with Neural Networks”. IEEE ASSP Magazine, 3(4), pp. 4-22
  12. Freeman, J.A. and Skapura, D.M., 1991 Neural Networks: Algorithms, Applications and Programming Techniques. Addison-Wesley Publishing Company, Inc. Reading, MA.
  13. Bishop, C.M., 1995. Neural Networks for Pattern Recognition, Oxford University Press.
  14. Hush, D.R., Horne, B.G., 1993. Progress in supervised neural networks”, IEEE Signal Processing Magazine, 10 (1), pp. 8-39.
  15. Moller, M.F. (1993). A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning. Neural Networks, Vol. 6, pp.523-533
Download


Paper Citation


in Harvard Style

Solé-Casals J., Vialatte F., Pantel J., Prvulovic D., Haenschel C. and Cichocki A. (2010). ICA CLEANING PROCEDURE FOR EEG SIGNALS ANALYSIS - Application to Alzheimer's Disease Detection . In Proceedings of the Third International Conference on Bio-inspired Systems and Signal Processing - Volume 1: Special Session on Neural Signals of Brain Disorde, (BIOSTEC 2010) ISBN 978-989-674-018-4, pages 485-490. DOI: 10.5220/0002755904850490


in Bibtex Style

@conference{special session on neural signals of brain disorde10,
author={J. Solé-Casals and F. Vialatte and J. Pantel and D. Prvulovic and C. Haenschel and A. Cichocki},
title={ICA CLEANING PROCEDURE FOR EEG SIGNALS ANALYSIS - Application to Alzheimer's Disease Detection},
booktitle={Proceedings of the Third International Conference on Bio-inspired Systems and Signal Processing - Volume 1: Special Session on Neural Signals of Brain Disorde, (BIOSTEC 2010)},
year={2010},
pages={485-490},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002755904850490},
isbn={978-989-674-018-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Bio-inspired Systems and Signal Processing - Volume 1: Special Session on Neural Signals of Brain Disorde, (BIOSTEC 2010)
TI - ICA CLEANING PROCEDURE FOR EEG SIGNALS ANALYSIS - Application to Alzheimer's Disease Detection
SN - 978-989-674-018-4
AU - Solé-Casals J.
AU - Vialatte F.
AU - Pantel J.
AU - Prvulovic D.
AU - Haenschel C.
AU - Cichocki A.
PY - 2010
SP - 485
EP - 490
DO - 10.5220/0002755904850490