Skip to main content

Advertisement

SpringerLink
Log in

SADE3: an effective system for automated detection of epileptiform events in long-term EEG based on context information

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

Abstract

Interictal spike detection is a time-consuming, low-efficiency task, but is important to epilepsy diagnosis. Automated systems reported to date usually have their practical efficacy compromised by elevated rates of false-positive detections per minute, which are caused mainly by the influence of artifacts (such as noise activity and ocular movements) and by the adoption of single or simple approaches. This work describes the development of a hybrid system for automatic detection of spikes in long-term electroencephalogram (EEG), named System for Automatic Detection of Epileptiform Events in EEG (SADE3), which uses wavelet transform, neural networks and artificial intelligence procedures to recognize epileptic and to reject non-epileptic activity. The system’s pre-processing stage filters the EEG epochs with the Coiflet wavelet function, which showed the closest correlation to epileptogenic (EPG) activity, in opposition to some other wavelet functions that did not correlate with these events. In contrast to current attempts using continuous wavelet transform, we chose to work with fast wavelet transform to reduce processing time and data volume. Detail components at appropriate decomposition levels were used to accentuate spikes, sharp waves, high-frequency noise activity and ocular artifacts. These four detailed components were used to train four specialized neural networks, designed to detect and classify the EPG and non-EPG events. An expert module analyzes the networks’ outputs, together with multichannel and context information and concludes the detection. The system was evaluated with 126,000 EEG epochs, obtained from seven different patients during long-term monitoring, under diverse behavior and mental states. More than 6,721 spikes and sharp waves were previously identified by three experienced human electroencephalographers. In these tests, the SADE3 system simultaneously achieved 70.9% sensitivity, 99.9% specificity and a rate of 0.13 false-positives per minute, indicating its usefulness and low vulnerability to artifact influence. After tests, the SADE3 system showed itself to be able to process bipolar cortical EEG records, from long-term monitoring, up to 32 channels, without any data preparation or event positioning. At the same time, SADE3 revealed a high capacity to reject non-epileptic paroxysms, robustness in relation to a variety of spike morphologies, flexibility in adjustment of performance rates and the capacity to actually save time during EEG reading. Furthermore, it can be adapted to other applications for pattern recognition, with simple adjustments.

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

Access this article

Log in via an institution

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
Fig. 10

Similar content being viewed by others

Notes

  1. For biorthogonal wavelets, the first number indicates the decomposition filter order, while the last number (after the decimal point) indicates the reconstruction filter order.

References

  1. Argoud FIM (2001) Contribuição à Automatização da Detecção e Análise de Eventos Epileptiformes em Eletro encefalograma. Ph.D. thesis, Instituto de Engenharia Biomédica—IEB, Departamento de Engenharia Elétrica—EEL, Universidade Federal de Santa Catarina—UFSC, Brazil

  2. Argoud FIM, De Azevedo FM, Marino Neto J (2005) Sistema de detecção automática de paroxismos epileptogênicos em sinais de eletro encefalograma. Revista da SBA—Controle e Automação 4(15):467–475

    Google Scholar 

  3. Attelis CE, Isaacson SI, Sirne RO (1997) Detection of epileptic events in electroencephalograms using wavelet analysis. Ann Biomed Eng 25(1):286–293

    Article  Google Scholar 

  4. Bourges−Sévenier M (1994) Réalisation dúne bibliothéque C de fonctions ondelettes. Relatório técnico 1, Rennes Cedex, France: IRISA—Institut de Recherche en Informatique et Systémes Aléatoires, p. 108. http://www.wavelet.org/wavelet/digest—04/digest—04.01.html

  5. De Azevedo FM (1997) Uma proposta de modelos formais de neurônios e redes neurais artificiais. Anais do 3o. Congresso Brasileiro de Redes Neurais, Florianópolis, pp 503–514

  6. Duempelmann M, Elger CE (1999) Visual and automatic investigation of epileptiform spikes in intracranial EEG recordings. Epilepsia 40(3):275–285

    Article  Google Scholar 

  7. Feucht M, Hoffmann K, Steinberger K, Witte H, Benninger F, Arnold M, Doering A (1997) Simultaneous spike detection and topographic classification in pediatric surface EEGs. NeuroReport 8:2193–2197

    Article  Google Scholar 

  8. Gabor AJ, Seyal M (1992) Automated interracial EEG spike detection using artificial networks. Electroencephalogr Clin Neurophysiol 83(1):271–280

    Google Scholar 

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

    Article  Google Scholar 

  10. Gotman J, Wang LY (1991) State-dependent spike detection: concepts and preliminary results. Electroencephalogr Clin Neurophysiol 79:11–19

    Article  Google Scholar 

  11. Hoffmann K, et al (1996) Analysis and classification of interictal spikes discharges in benign partial epilepsy of childhood on the basis of the Hilbert transform. Neurosci Lett 211(1):195–198

    Article  Google Scholar 

  12. Kalayci T, Özdamar O (1995) Wavelet preprocessing for automated neural network detection of EEG spikes. In: IEEE Engineering in Medicine and Biology Magazine. Proceedings, March 1995, pp 160–166

    Article  Google Scholar 

  13. Khan YU, Gotman J (2003) Wavelet based automatic seizure detection in intracerebral electroencephalogram. Clin Neurophysiol 114:898–908

    Article  Google Scholar 

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

    Google Scholar 

  15. Liu HS, Zhang T, Yang FS (2002) A multistage, multimethod approach for automatic detection and classification of epileptiform EEG. IEEE Trans Biomed Eng 49(12):1557–1566

    Article  Google Scholar 

  16. Mallat S (1999) A wavelet tour of signal processing, 2nd edn. Academic/Elsevier, San Diego, 637 pp

  17. Morales-Chacon L, Zaldivar M (1999) The use of zygomatic electrodes in the assessment of epileptic patients—presentation of methodology for recording and assessing a digital EEG. Rev Neurol 28(3):224–227

    Google Scholar 

  18. Pradhan N, Sadasivan PK, Arunodaya GR (1996) Detection of seizure activity in EEG by an artificial neural network: a preliminary study. Comput Biomed Res 29(4):303–313

    Article  Google Scholar 

  19. Pereira MCV (2003) Tratamento de Sinais Bioelétricos para Processamento por Redes Neurais Artificiais. Ph.D. thesis, Instituto de Engenharia Biomédica—IEB, Departamento de Engenharia Elétrica—EEL, Universidade Federal de Santa Catarina—UFSC, Brazil

  20. Schiff SJ, Aldoubri A, Unser M, Satao S (1994) Fast wavelet transformation of EEG. Electroencephalogr Clin Neurophysiol 91:442–455

    Article  Google Scholar 

  21. Sheng Y (1996) Wavelet transform. In: The transforms and applications handbook, 1st edn. CRC and IEEE, Boca Raton, pp 747–827

  22. Stelle AL, Comley RA (1989) Portable analyzer for real-time detection of the epileptic pre-cursor. RBE 6(2):101–107

    Google Scholar 

  23. Stelle AL, Comley RA (1990) The application of the Wigner distribution to the analysis of EEG signals. RBE 7(1):670–676

    Google Scholar 

  24. Sweldens W (1996) The lifting scheme: a custom−design construction of biorthogonal wavelets. Appl Comput Harmon Anal 3(2):186–200

    Article  MATH  MathSciNet  Google Scholar 

  25. Sweldens W, Schröder P (1997) Building your own wavelets at home—introductory material. Wavelet Dig. http://www.wavelet.org/wavelet/digest—04/digest—04.01.html

  26. Thakor NV, Sherman D (1995) Wavelet (time−scale) analysis in biomedical signal processing. In: The biomedical engineering handbook, 1st edn. CRC and IEEE, Boca Raton, pp 887–906

  27. Unser M, Aldoubri A (1996) A review of wavelets in biomedical applications. Proc IEEE 84:626–638

    Article  Google Scholar 

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

    Article  Google Scholar 

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

    Article  Google Scholar 

  30. Wilson SB, Turner CA, Emerson RG, Scheuer ML (1999) Spike detection. Clin Neurophysiol 110:404–411

    Article  Google Scholar 

Download references

Acknowledgments

To CAPES, for supporting continuity of this project, through its PRODOC program. To the Montreal Neurological Institute and Prof. Dr Jean Gotman, for the assistance given to this work.

Author information

Authors and Affiliations

  1. Biomedical Engineering Institute (IEB), Federal University of Santa Catarina (UFSC), Florianópolis, Brazil

    Fernanda I. M. Argoud, Fernando M. De Azevedo, José Marino Neto & Eugênio Grillo

Authors
  1. Fernanda I. M. Argoud
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fernando M. De Azevedo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. José Marino Neto
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Eugênio Grillo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fernanda I. M. Argoud.

Appendix

Appendix

Definitions used in the assessment of system performance:

True positive:

number of events marked as positive by both the EEGer and the system;

False positive:

number of events marked as positive by the system only;

True negative:

number of events that were neither marked by the specialist, nor the system;

False negative:

number of positive events, which were not marked by the system;

True indeterminate:

number of events marked as undetermined by the specialist and by the system;

False indeterminate:

number of positive or negative events marked as undetermined by the system;

FPM rate:

distribution of false-positive detections over time in minutes:

$$ {\text{FPM}} = \frac{{{\text{FP}}}} {{\Delta t}} $$
Sensitivity:

the system’s capacity to recognize positive events, given by:

$$ {\text{Sensitivity}} = \frac{{{\text{TP}}}} {{{\text{TP}} + {\text{FN}}}} \times 100\% $$
Specificity:

the system’s capacity to recognize negative activity, given by:

$$ {\text{Specificity}} = \frac{{{\text{TN}}}} {{{\text{TN}} + {\text{FP}}}} \times 100\% $$
PPV:

percentage of successful judgments by the system in positive detections:

$$ {\text{PPV}} = \frac{{{\text{TP}}}} {{{\text{TP}} + {\text{FP}}}} \times 100\% $$
PNV:

percentage of successful judgments by the system in negative detections:

$$ {\text{PNV}} = \frac{{{\text{TN}}}} {{{\text{TN}} + {\text{FN}}}} \times 100\% $$

Rights and permissions

Reprints and permissions

About this article

Cite this article

Argoud, F.I.M., De Azevedo, F.M., Neto, J.M. et al. SADE3: an effective system for automated detection of epileptiform events in long-term EEG based on context information. Med Bio Eng Comput 44, 459–470 (2006). https://doi.org/10.1007/s11517-006-0056-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-006-0056-y

Keywords

Search

Navigation