Skip to main content

Advertisement

Log in

A novel method for automated classification of epileptiform activity in the human electroencephalogram-based on independent component analysis

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Diagnosis of several neurological disorders is based on the detection of typical pathological patterns in the electroencephalogram (EEG). This is a time-consuming task requiring significant training and experience. Automatic detection of these EEG patterns would greatly assist in quantitative analysis and interpretation. We present a method, which allows automatic detection of epileptiform events and discrimination of them from eye blinks, and is based on features derived using a novel application of independent component analysis. The algorithm was trained and cross validated using seven EEGs with epileptiform activity. For epileptiform events with compensation for eyeblinks, the sensitivity was 65 ± 22% at a specificity of 86 ± 7% (mean ± SD). With feature extraction by PCA or classification of raw data, specificity reduced to 76 and 74%, respectively, for the same sensitivity. On exactly the same data, the commercially available software Reveal had a maximum sensitivity of 30% and concurrent specificity of 77%. Our algorithm performed well at detecting epileptiform events in this preliminary test and offers a flexible tool that is intended to be generalized to the simultaneous classification of many waveforms in the EEG.

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

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Acir N, Guzelis C (2004) Automatic spike detection in EEG by two-stage procedure based on support vector machine. Comput Biol Med 34:561–575

    Article  Google Scholar 

  2. Barbati G, Porcaro C, Zappasodi F, Rossini PM, Tecchio F (2004) Optimization of an independent component analysis approach for artefact identification and removal in magnetoencephalographic signals. Clin Neurophysiol 115:1220–1232

    Article  Google Scholar 

  3. Bell A, Sejnowski T (1995) An information-maximization approach to blind separaton and blind deconvolution. Neural Comput 7:1129–1159

    Article  Google Scholar 

  4. Bell AJ, Sejnowski TJ (1996) Learning the higher-order structure of a natural sound. Netw Comput Neural Syst 7:261–266

    Article  MATH  Google Scholar 

  5. Binnie CD, Holder DS (1999) Electroencephalography. In: Vinken PJ, Bruyn GW (eds) Handbook of clinical neurology. Amsterdam

  6. Calhoun VD, Adali T, Pearlson GD, Pekar JJ (2001) Spatial and temporal independent component analysis of functional MRI containing a pair of task-related waveforms. Hum Brain Map 13:43–53

    Article  Google Scholar 

  7. De Lucia M, Fritschy J, Dayan P, Holder DS (2006) The classification of spikes in EEG recordings using features derived from ICA. In: IET 3rd international conference MEDSIP 2006. Advances in Medical, Signal and Information Processing, issue 520, p. 39

  8. Diambra L, Malta P (1999) Nonlinear models for detecting epileptic spikes. Phys Rev E 59(1):929–937

    Article  Google Scholar 

  9. Dumermuth G (1977) Fundamentals of spectral analysis in electroencephalography. In: A.Rèmond (ed), EEG informatics. A didactic review of methods and applications of EEG data processing. Elsevier, Amsterdam, pp 83–105

  10. Faure C (1985) Attributed strings for recognition of epileptic transients in EEG. Int J Biomed Comput 16:217–229

    Article  Google Scholar 

  11. Franaszczuk PJ, Bergey GK (1999) An autoregressive method for the measurement of synchronization of interictal and ictal EEG signals. Biol Cybern 81:3–9

    Article  MATH  Google Scholar 

  12. Fritschy J, Horesh L, Holder DS, Bayford RH (2005) Using the GRID to improve the computation speed of electrical impedance tomography (EIT) reconstruction algorithms. Physiol Meas 26(2):209–215

    Article  Google Scholar 

  13. Fritschy J, Horesh L, Holder DS, Bayford RH (2005) Applications of GRID in clinical neurophysiology and electrical impedance tomography of brain function. Stud Health Technol Inform 112:138–145

    Google Scholar 

  14. Goelz H, Jones RD, Bones PJ (2000) Wavelet analysis of transient biomedical signals and its application to detection of epileptiform activity in the EEG. Clin Electroencephalogr 31:181–191

    Google Scholar 

  15. Gotman J, Gloor P (1976) Automatic recognition and quantification of interictal epileptic activity in the human scalp EEG. Electroenceph clin Neurophysiol 41:513–529

    Article  Google Scholar 

  16. Gotman J, Ives JR, Gloor P (1979) Automatic recognition of interictal epileptic activity in prolonged EEG recordings. Electroenceph clin Neurophysiol 46:510–520

    Article  Google Scholar 

  17. Hastie T, Tibshirani R, Friedman J (2001) The elements of Statistical Learning: Data Mining, Inference and Prediction. Springer Series in Statistics

  18. Hughes JR (1994) EEG in clinical practice, 2nd edn. Butterworth-Heinemann, Newton, MAJR. Hughes EEG in Clinical Practice

  19. Hyvarinen A (1999) Survey on independent component analysis. Neural Comput Surv 2:94–128

    Google Scholar 

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

    Article  Google Scholar 

  21. Hyvarinen A, Oja E (1997) A fast fixed-point algorithm for independent component analysis. Neural Comput 9(7):1483–1492

    Article  Google Scholar 

  22. Hyvarinen A, Oja E (2000) Independent component analysis: algorithms and applications. Neural Netw 13:411–430

    Article  Google Scholar 

  23. Jasper H (1958) The ten–twenty electrode system of the international federation. Electroencephalogr Clin Neurophysiol 10:371–375

    Google Scholar 

  24. Jung T, Makeig S, Mckeown MJ, Bell AJ, Lee T, Sejnowski TJ (2001) Imaging brain dynamics using independent component analysis. Proc IEEE 89(7):1107–1122

    Article  Google Scholar 

  25. Kalayci T, Ozdamar O (1995) Wavelet preprocessing for automated neural network detection of EEG spikes. IEEE Eng Med Biol Mag 14(2):160–166

    Article  Google Scholar 

  26. Kobayashi K, Akiyama T, Nakahori T (2002a) Systematic source estimation of spikes by a combination of independent component analysis and RAP-MUSIC. I: principles and simulation study. Clin Neurophysiol 113:713–724

    Article  Google Scholar 

  27. Kobayashi K, Akiyama T, Nakahori T (2002b) Systematic source estimation of spikes by a combination of independent component analysis and RAP-MUSIC. II: preliminary clinical application. Clin Neurophysiol 113:725–734

    Article  Google Scholar 

  28. Kobayashi K, James C, Nakahori T, Akiyama T, Gotman J (1999) Isolation of epileptiform discharges from unaveraged EEG by independent component analysis. Clin Neurophysiol 110(10):1755–1763

    Google Scholar 

  29. Latka M, Was Z, Kozik A, West B (2003) Wavelet Analysis of epileptic spikes. Phys Rev E 67:052902

    Article  Google Scholar 

  30. McKeown MJ, Brown GG, Jung TP, Kindermann SS, Bell AJ, Sejnowski TJ (1998) Analysis of fMRI data by blind separation into independent spatial components. Hum Brain Mapp 6:160–188

    Article  Google Scholar 

  31. McKeown MJ, Jung TP, Makeig S, Brown G, Kindermann SS, Lee TW, Sejnowski TJ (1998) Spatially independent activity pattern in functional MRI data during the stroop color-naming task. Proc Natl Acad Sci USA 95:803–810

    Article  Google Scholar 

  32. Ossadtchi A, Baillet S, Moscher JC, Thyerlei D, Sutherling W, Leahy RM (2004) Automated interictal spike detection and source localization in magnetoencephalography using independent components analysis and spatio-temporal clustering. Clin Neurophysiol 115(3):508–522

    Article  Google Scholar 

  33. Ozdamar O, Kalayci T (1998) Detection of spikes with artificial neural networks using raw EEG. Comput Biomed Res 31:122–142

    Article  Google Scholar 

  34. Pham D-T, Garrat P, Jutten C (1992) Separation of a mixture of independent sources through a maximum likelihood approach. In: Proceedings of EUSIPCO, pp 771–774

  35. Ramabhadran B, Frost JD Jr, Glover JR, Ktonas PY (1999) An automated system for epileptogenic focus localization in the electroencephalogram. J Clin Neurophysiol 16:59–68

    Article  Google Scholar 

  36. Schlesinger MI, Hlavàc V (2002) Ten lectures on statistical and structural pattern recognition. Kluwer, Dordrecht

    MATH  Google Scholar 

  37. Shoker L, Sanei S, Wang W, Chambers JA (2005) Removal of eyey blinking artifact from the electro-encephalogram, incorporating a new constrained blind source separation algorithm. Med Biol Eng Comput 43:290–295

    Article  Google Scholar 

  38. Vigario RN (1997) Extraction of ocular artefacts from EEG using independent component analysis. Electroencephal Clin Neurophysiol 103:395–404

    Article  Google Scholar 

  39. Vigario R, Jousmaki V, Hamalainen M, Hari R, Oja E (1998) Independent component analysis for identification of artefacts in magnetoencephalographic recordings. Adv Neural Inf Process Syst 10:229–235

    Google Scholar 

  40. Webber WR, Litt B, Wilson K, Lesser RP (1994) Practical detection of epileptiform discharge (EDs) in the EEG using an artificial neural network: a comparison of raw and parameterized EEG data. Electroencephalogr Clin Neurophysiol 91(3):194–204

    Article  Google Scholar 

  41. Wilson SB, Emerson R (2002) Spike detection: a review and comparison of algorithms. Clin Neurophysiol 113:1873–1881

    Article  Google Scholar 

  42. Wilson SB, Scheuer ML, Emerson RG, Gabor AJ (2004) Seizure detection: evaluation of the Reveal algorithm. Clin Neurophysiol 115(10):2280–2291

    Google Scholar 

  43. Wilson SB, Turner CA, Emerson RG, Scheuer ML (1999) Spike detection II: automatic, perception-based detection and clustering. Clin Neurophysiol 110:404–411

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Marzia De Lucia.

Rights and permissions

Reprints and permissions

About this article

Cite this article

De Lucia, M., Fritschy, J., Dayan, P. et al. A novel method for automated classification of epileptiform activity in the human electroencephalogram-based on independent component analysis. Med Biol Eng Comput 46, 263–272 (2008). https://doi.org/10.1007/s11517-007-0289-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-007-0289-4

Keywords

Navigation