Analysis of Multi-Channel Subdural EEG by Recurrent Neural Networks

  • Robyn R. Bates
  • Mingui Sun
  • Mark L. Scheuer
  • Robert J. Sclabassi
Chapter
Part of the International Series in Intelligent Technologies book series (ISIT, volume 20)

5. Conclusions

It was shown that recurrent neural networks with relatively simple architectures are capable of detecting seizure-like activity in multi-channel EEG records. Furthermore, the results obtained from the three different architectures studied were fairly consistent in locating the generators of seizure-like activity based on the patient’s subdural EEG montage. If these results are verified by other studies, then these neural networks may serve as effective functional engines in more sophisticated seizure detection utilities. Additional work to increase the detection ability of these networks needs to be undertaken, especially with regard to the separation of the EEG data recorded at each electrode. Also, a means by which a utility using these neural networks can be made more adaptive to a variety of seizures from a wide patient population needs to be examined.

Keywords

Seizure Activity Recurrent Neural Network Input Node Seizure Detection Epileptogenic Focus 
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.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Niedermeyer, Ernst, and Da Silva, Fernando, Electroencephalography: Basic Principles, Clinical Applications, and Related Fields. Baltimore: Williams & Wilkins, 1993, p. 8–9, 228–235.Google Scholar
  2. Ebersole, John, S., “Defining Epileptogenic Foci: Past, Present, and Future,” J. Clin. Neurophys., 14(6) (1997), pp. 470–483.CrossRefGoogle Scholar
  3. Gutnick, M. J., Connors, R. W., and Prince, D.A., “Mechanisms of Neocortical Epileptogenesis in Vitro,” J. Neurophys. 48:6 (December 1982), pp. 1321–1335.Google Scholar
  4. Nuñez, P.L., Neocortical Dynamics and Human EEG Rhythms, New York, Oxford University Press, (1994).Google Scholar
  5. Blum, D.E., “Computer-based Electroencephalography: Technical Basics, Basis for New Applications, and Potential Pitfalls,” Electroenceph. and Clin. Neurophys. 106 (1998), pp. 118–126.CrossRefGoogle Scholar
  6. Gotman, J. “Automatic Recognition of Epileptic Seizures in the EEG,” Electroenceph. and Clin. Neurophys. 54 (1982), pp. 530–540.CrossRefGoogle Scholar
  7. Gotman, J., “Automatic Seizure Detection: Improvements and Evaluation,” Electroenceph. and Clin. Neurophys. 76 (1990), pp. 317–324CrossRefGoogle Scholar
  8. Gotman, J., and Gloor, P., “Automatic Recognition and Quantification of Interictal Epileptic Activity in the Human Scalp EEG,” Electroenceph. and Clin. Neurophys., 41 (1976), pp. 513–529.CrossRefGoogle Scholar
  9. Haykin, S., Neural Networks, A Comprehensive Foundation, New York: Macmillan College Publishing Company Books (1994).Google Scholar
  10. Elman, J.L., “Finding Structure in Time,” Cognitive Science 14, (1990), pp. 179–211.CrossRefGoogle Scholar
  11. Casey, M., “How Discrete-Time Recurrent Neural Networks Work,” Department of Mathematics 0112, University of California at San Diego, La Jolla, CA., Technical Report INC-9503, (April 11, 1995), pp. 1–41.Google Scholar
  12. Petrosian, A., Prokhorov, D., Homan, R., Dashieff, and Wunsch, D., “Recurrent Neural Network Based Prediction of Epileptic Seizures in Intra-and Extracranial EEG,” Neurocomputing 30 (2000), pp. 201–218.CrossRefGoogle Scholar
  13. Palus M., “Nonlinearity in Normal Human EEG: Cycles, Temporal Asymmetry, Nonstationarity and Randomness, Not Chaos,” Biological Cybernetics. 75:5 (November 1996), pp. 389–396.CrossRefGoogle Scholar
  14. Cleermans, A., McClelland, J.L., and Servan-Schreiber, D., “Encoding Sequential Structure in Simple Recurrent Networks,” School of Computer Science, Carnegie-Mellon University, Pittsburgh, PA, CMU-CS-88-183. (November, 1988).Google Scholar
  15. Williams, R.J. and Zipser, D., “Experimental Analysis of the Real-time Recurrent Learning Algorithm”. Connection Science. 1989 1:1, pp. 87–111.CrossRefGoogle Scholar
  16. Haykin, ibid., pp. 21–22.Google Scholar
  17. Niedermeyer, Ernst, and Da Silva. ibid., pp. 108–111.Google Scholar
  18. Haykin, ibid., pp. 265–266.Google Scholar
  19. Niedermeyer, Ernst, and Da Silva, ibid., pp. 1066–1068.Google Scholar
  20. Zhukov, Leonid, Weinstein, David, and Johnson, Chris, “Independent Component Analysis for EEG Source Localization,” IEEE Eng. Med. Bio., 19:3, pp. 87–96.Google Scholar
  21. Baum, E.B., Haussler, D., “What size net gives valid generalization?” Neural Computation, vol. 1, no. 1, pp. 151–160, 1989.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, Inc. 2005

Authors and Affiliations

  • Robyn R. Bates
    • 1
  • Mingui Sun
    • 1
  • Mark L. Scheuer
    • 1
  • Robert J. Sclabassi
    • 1
  1. 1.University of PittsburghPittsburghUSA

Personalised recommendations