Skip to main content
SpringerLink
Log in

Deep Learning for Interictal Epileptiform Discharge Detection from Scalp EEG Recordings

  • Conference paper
  • First Online:
XV Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019 (MEDICON 2019)

Part of the book series: IFMBE Proceedings ((IFMBE,volume 76))

Abstract

Interictal Epileptiform Discharge (IED) detection in EEG signals is widely used in the diagnosis of epilepsy. Visual analysis of EEGs by experts remains the gold standard, outperforming current computer algorithms. Deep learning methods can be an automated way to perform this task. We trained a VGG network using 2-s EEG epochs from patients with focal and generalized epilepsy (39 and 40 patients, respectively, 1977 epochs total) and 53 normal controls (110770 epochs). Five-fold cross-validation was performed on the training set. Model performance was assessed on an independent set (734 IEDs from 20 patients with focal and generalized epilepsy and 23040 normal epochs from 14 controls). Network visualization techniques (filter visualization and occlusion) were applied. The VGG yielded an Area Under the ROC Curve (AUC) of 0.96 (95% Confidence Interval (CI) = 0.95 − 0.97). At 99% specificity, the sensitivity was 79% and only one sample was misclassified per two minutes of analyzed EEG. Filter visualization showed that filters from higher level layers display patches of activity indicative of IED detection. Occlusion showed that the model correctly identified IED shapes. We show that deep neural networks can reliably identify IEDs, which may lead to a fundamental shift in clinical EEG analysis.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Da Silva, F.L., Blanes, W., Kalitzin, S.N., Parra, J., Suffczynski, P., Velis, D.N.: Epilepsies as dynamical diseases of brain systems: basic models of the transition between normal and epileptic activity. Epilepsia 44, 72–83 (2003)

    Article  Google Scholar 

  2. Fisher, R.S.: ILAE official report: a practical clinical definition of epilepsy. Epilepsia 55(4), 475–482 (2014)

    Article  MathSciNet  Google Scholar 

  3. Tatum, W.: Clinical utility of EEG in diagnosing and monitoring epilepsy in adults. Clin. Neurophysiol. 129(5), 1056–1082 (2018)

    Article  Google Scholar 

  4. Beach, R., Reading, R.: The importance of acknowledging clinical uncertainty in the diagnosis of epilepsy and non-epileptic events. Arch. Dis. Child. 90(12), 1219–1222 (2005)

    Article  Google Scholar 

  5. Zaidi, A., Clough, P., Cooper, P., Scheepers, B., Fitzpatrick, A.P.: Misdiagnosis of epilepsy: many seizure-like attacks have a cardiovascular cause. J. Am. Coll. Cardiol. 36(1), 181–184 (2000)

    Article  Google Scholar 

  6. Nowack, W.J.: Epilepsy: a costly misdiagnosis. Clin. Electroencephalogr. 28(4), 225–228 (1997)

    Article  Google Scholar 

  7. Torres, F.: Atlas and classification of electroencephalography. Pediatr. Neurol. 22(4), 332 (2000)

    Article  Google Scholar 

  8. Pillai, J., Sperling, M.R.: Interictal EEG and the diagnosis of epilepsy. Epilepsia 47, 14–22 (2006)

    Article  Google Scholar 

  9. Smith, S.: EEG in the diagnosis, classification, and management of patients with epilepsy. J. Neurol. Neurosurg. Psychiatry 76(Suppl. 2), ii2–ii7 (2005)

    Google Scholar 

  10. Lodder, S.S., Askamp, J., van Putten, M.J.: Computer-assisted interpretation of the EEG background pattern: a clinical evaluation. PLoS ONE 9(1), e85966 (2014)

    Article  Google Scholar 

  11. Lodder, S.S., van Putten, M.J.: Automated EEG analysis: characterizing the posterior dominant rhythm. J. Neurosci. Methods 200(1), 86–93 (2011)

    Article  Google Scholar 

  12. Lodder, S.S., van Putten, M.J.: Quantification of the adult EEG background pattern. Clin. Neurophysiol. 124(2), 228–237 (2013)

    Article  Google Scholar 

  13. Artameeyanant, P., Chiracharit, W., Chamnongthai, K.: Spike and epileptic seizure detection using wavelet packet transform based on approximate entropy and energy with artificial neural network. In: The 5th 2012 Biomedical Engineering International Conference, pp. 1–5. IEEE (2012)

    Google Scholar 

  14. Liu, Y.-C., Lin, C.-C., Tsai, J.-J., Sun, Y.-N.: Model-based spike detection of epileptic EEG data. Sensors 13(9), 12536–12547 (2013)

    Article  Google Scholar 

  15. Lodder, S.S., Askamp, J., van Putten, M.J.: Inter-ictal spike detection using a database of smart templates. Clin. Neurophysiol. 124(12), 2328–2335 (2013)

    Article  Google Scholar 

  16. Nonclercq, A., et al.: Cluster-based spike detection algorithm adapts to interpatient and intrapatient variation in spike morphology. J. Neurosci. Methods 210(2), 259–265 (2012)

    Article  Google Scholar 

  17. Webber, W., Litt, B., Wilson, K., Lesser, R.P.: 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(3), 194–204 (1994)

    Article  Google Scholar 

  18. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)

    Article  Google Scholar 

  19. Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)

    Article  Google Scholar 

  20. Qin, Z., Yu, F., Liu, C., Chen, X.: How convolutional neural network see the world-A survey of convolutional neural network visualization methods. arXiv preprint arXiv:1804.11191 (2018)

  21. Nguyen, A., Yosinski, J., Clune, J.: Multifaceted feature visualization: Uncovering the different types of features learned by each neuron in deep neural networks. arXiv preprint arXiv:1602.03616 (2016)

  22. Yosinski, J., Clune, J., Nguyen, A., Fuchs, T., Lipson, H.: Understanding neural networks through deep visualization. arXiv preprint arXiv:1506.06579 (2015)

  23. Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision, pp. 818–833. Springer (2014)

    Google Scholar 

  24. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)

  25. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  26. Scheuer, M.L., Bagic, A., Wilson, S.B.: Spike detection: inter-reader agreement and a statistical turing test on a large data set. Clin. Neurophysiol. 128(1), 243–250 (2017)

    Article  Google Scholar 

  27. Pang, C.C., Upton, A.R., Shine, G., Kamath, M.V.: A comparison of algorithms for detection of spikes in the electroencephalogram. IEEE Trans. Biomed. Eng. 50(4), 521–526 (2003)

    Article  Google Scholar 

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

    Article  Google Scholar 

  29. Özdamar, Ö., Kalayci, T.: Detection of spikes with artificial neural networks using raw EEG. Comput. Biomed. Res. 31(2), 122–142 (1998)

    Article  Google Scholar 

  30. Thomas, J., Comoretto, L., Jin, J., Dauwels, J., Cash, S.S., Westover, M.B.: EEG CLassification via convolutional neural network-based interictal epileptiform event detection. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3148–3151. IEEE (2018)

    Google Scholar 

  31. Johansen, A.R., Jin, J., Maszczyk, T., Dauwels, J., Cash, S.S., Westover, M.B.: Epileptiform spike detection via convolutional neural networks. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 754–758. IEEE (2016)

    Google Scholar 

  32. Tjepkema-Cloostermans, M.C., de Carvalho, R.C., van Putten, M.J.: Deep learning for detection of focal epileptiform discharges from scalp EEG recordings. Clin. Neurophysiol. 129(10), 2191–2196 (2018)

    Article  Google Scholar 

  33. Lodder, S.S., van Putten, M.J.: A self-adapting system for the automated detection of inter-ictal epileptiform discharges. PLoS ONE 9(1), e85180 (2014)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Engineering of the University of Porto, Porto, Portugal

    Catarina Lourenço & Luís F. Teixeira

  2. University of Twente, Enschede, The Netherlands

    Catarina Lourenço, Marleen C. Tjepkema-Cloostermans & Michel J. A. M. van Putten

  3. Medisch Spectrum Twente, University of Twente, Enschede, The Netherlands

    Marleen C. Tjepkema-Cloostermans

Authors
  1. Catarina Lourenço
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Marleen C. Tjepkema-Cloostermans
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Luís F. Teixeira
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Michel J. A. M. van Putten
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Catarina Lourenço .

Editor information

Editors and Affiliations

  1. University of Coimbra, Coimbra, Portugal

    Jorge Henriques

  2. Universidade do Minho, Braga, Portugal

    Nuno Neves

  3. University of Coimbra, Coimbra, Portugal

    Paulo de Carvalho

Appendix

Appendix

Table 2. Description of the training and test sets of each dataset, including its duration, the number of epochs and the number of epochs in the positive class (i.e. IEDs).
Full size table
Fig. 4.
figure 4

ROC curves for the VGG model trained with Set A (first row) and Set C (second row). The first column shows the results on the training set and the second column shows the results on the test set. The 95% Confidence Interval (CI) of the ROC curve is shown as a shaded area. The AUC value and the corresponding CI are also presented (right).

Full size image
Fig. 5.
figure 5

Examples of the application of occlusion to the VGG model trained with set A (aiming to distinguish IEDs from Normal EEG epochs and normal epochs in epileptic EEGs). First row: true positive (left) and true negative (right). Second row: false positive (left) and false negative (right).

Full size image
Fig. 6.
figure 6

Examples of the application of occlusion to the VGG model trained with set C (aiming to distinguish IEDs from Normal EEG epochs and epochs from EEGs containing non-epileptiform abnormalities). First row: true positive (left) and true negative (right). Second row: false positive (left) and false negative (right).

Full size image
Table 3. Number of epochs (Epochs), number of IEDs (IEDs), Sensitivity (Sens) and Specificity (Spec) in each recording on the test set of set B, classified by the VGG with weights 100:1, at a threshold of 0.5.
Full size table
Table 4. Number of epochs (Epochs), number of IEDs (IEDs), Sensitivity (Sens) and Specificity (Spec), in each recording on the test set of set C, classified by the VGG with weights 100:1, at a threshold of 0.5.
Full size table

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Lourenço, C., Tjepkema-Cloostermans, M.C., Teixeira, L.F., van Putten, M.J.A.M. (2020). Deep Learning for Interictal Epileptiform Discharge Detection from Scalp EEG Recordings. In: Henriques, J., Neves, N., de Carvalho, P. (eds) XV Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019. MEDICON 2019. IFMBE Proceedings, vol 76. Springer, Cham. https://doi.org/10.1007/978-3-030-31635-8_237

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-31635-8_237

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-31634-1

  • Online ISBN: 978-3-030-31635-8

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation