Deep Learning for Interictal Epileptiform Discharge Detection from Scalp EEG Recordings

Catarina Lourenço*, Marleen C. Tjepkema-Cloostermans, Luís F. Teixeira, Michel J.A.M. van Putten

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

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.

Original languageEnglish
Title of host publication15th Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019 - Proceedings of MEDICON 2019
EditorsJorge Henriques, Paulo de Carvalho, Nuno Neves
PublisherSpringer US
Pages1984-1997
Number of pages14
ISBN (Electronic)978-3-030-31635-8
ISBN (Print)978-3-030-31634-1
DOIs
Publication statusPublished - 1 Jan 2020
Event15th Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2019 - Coimbra, Portugal
Duration: 26 Sep 201928 Sep 2019
Conference number: 15

Publication series

NameIFMBE Proceedings
Volume76
ISSN (Print)1680-0737
ISSN (Electronic)1433-9277

Conference

Conference15th Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2019
Abbreviated titleMEDICON 2019
CountryPortugal
CityCoimbra
Period26/09/1928/09/19

Fingerprint Dive into the research topics of 'Deep Learning for Interictal Epileptiform Discharge Detection from Scalp EEG Recordings'. Together they form a unique fingerprint.

  • Cite this

    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 J. Henriques, P. de Carvalho, & N. Neves (Eds.), 15th Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019 - Proceedings of MEDICON 2019 (pp. 1984-1997). (IFMBE Proceedings; Vol. 76). Springer US. https://doi.org/10.1007/978-3-030-31635-8_237