Advertisement

EEG Signal Processing: Applying Deep Learning Methods to Identify and Classify Epilepsy Episodes

  • George SuciuEmail author
  • Maria-Cristina Dițu
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 283)

Abstract

Epilepsy is a chronic disease characterized by a deviation from the normal electrical activity of the brain leading to seizures caused by nerve impulses discharge. It is currently considered the fourth global neurological problem, being overcome only by diseases such as strokes. Moreover, according to the World Health Organization, nearly 50 million people suffer from epilepsy, with approximately 2.4 million patients annually diagnosed. It is worth mentioning that the elderly and children are the most exposed categories, but if the situation is considered, one of 26 people is likely to develop this condition at a point in life.

Through three gates, the network can also be used for larger data sequences. Moreover, given that the EEG signals are significantly more dynamic and not linear, an LSTM-based approach has, by definition, an advantage given by the ability to isolate different characteristics of brain activity. In the United States, for example, this condition can be found at 48 people out of 100,000.

Keywords

Epilepsy EEG Strokes 

Notes

Acknowledgement

This paper has been supported in part by UEFISCDI Romania through projects ESTABLISH, PAPUD and WINS@HI, and funded in part by European Union’s Horizon 2020 research and innovation program under grant agreement No. 777996 (SealedGRID project) and No. 787002 (SAFECARE project).

References

  1. 1.
    Li, S., Zhou, W., Yuan, Q., Liu, Y.: Seizure prediction using spike rate of intracranial EEG. IEEE Trans. Neural Syst. Rehabil. Eng. 21, 880–886 (2013).  https://doi.org/10.1109/tnsre.2013.2282153CrossRefGoogle Scholar
  2. 2.
    Malmivuo, J., Plonsey, R.: Bioelectromagnetism. ElectroencephalographyGoogle Scholar
  3. 3.
    Swami, P., Gandhi, T.K., Panigrahi, B.K., et al.: A novel robust diagnostic model to detect seizures in electroencephalography. Expert Syst. Appl. 56, 116–130 (2016).  https://doi.org/10.1016/j.eswa.2016.02.040CrossRefGoogle Scholar
  4. 4.
    Rasekhi, J., Mollaei, M.R.K., Bandarabadi, M., et al.: Preprocessing effects of 22 linear univariate features on the performance of seizure prediction methods. J. Neurosci. Methods 217, 9–16 (2013).  https://doi.org/10.1016/j.jneumeth.2013.03.019CrossRefGoogle Scholar
  5. 5.
    Park, Y., Luo, L., Parhi, K.K., Netoff, T.: Seizure prediction with spectral power of EEG using cost-sensitive support vector machines. Epilepsia 52, 1761–1770 (2011).  https://doi.org/10.1111/j.1528-1167.2011.03138.xCrossRefGoogle Scholar
  6. 6.
    Zhang, Z., Parhi, K.K.: Low-complexity seizure prediction from iEEG/sEEG using spectral power and ratios of spectral power. IEEE Trans. Biomed. Circ. Syst. 10, 693–706 (2016).  https://doi.org/10.1109/tbcas.2015.2477264CrossRefGoogle Scholar
  7. 7.
    Tsiouris, Κ.Μ., Pezoulas, V.C., Zervakis, M., et al.: A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals. Comput. Biol. Med. 99, 24–37 (2018).  https://doi.org/10.1016/j.compbiomed.2018.05.019CrossRefGoogle Scholar
  8. 8.
    Li, S., Zhou, W., Yuan, Q., Liu, Y.: Seizure prediction using spike rate of intracranial EEG. IEEE Trans. Neural Syst. Rehabil. Eng. 21, 880–886 (2013).  https://doi.org/10.1109/tnsre.2013.2282153CrossRefGoogle Scholar
  9. 9.
    Swami, P., Gandhi, T.K., Panigrahi, B.K., et al.: A novel robust diagnostic model to detect seizures in electroencephalography. Expert Syst. Appl. 56, 116–130 (2016).  https://doi.org/10.1016/j.eswa.2016.02.040CrossRefGoogle Scholar
  10. 10.
    Gonzalez, J., Yu, W.: Non-linear system modeling using LSTM neural networks. IFAC-PapersOnLine. 51, 485–489 (2018)CrossRefGoogle Scholar
  11. 11.
    Suciu, G., et al.: Big data, internet of things and cloud convergence–an architecture for secure e-health applications. J. Med. Syst. 39(11), 141 (2015)CrossRefGoogle Scholar
  12. 12.
    Ullah, I., Hussain, M., Qazi, E.-U.-H., Aboalsamh, H.: An automated system for epilepsy detection using EEG brain signals based on deep learning approach. Expert Syst. Appl. 107, 61–71 (2018).  https://doi.org/10.1016/j.eswa.2018.04.021CrossRefGoogle Scholar
  13. 13.
    CHB-MIT Scalp EEG Database. https://www.physionet.org/pn6/chbmit/. Accessed 15 Jan 2019

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2019

Authors and Affiliations

  1. 1.Beia Consult InternationalBucharestRomania
  2. 2.Faculty of Electronics, Telecommunications and Information TechnologyPolitehnica University of BucharestBucharestRomania

Personalised recommendations