Multi-feature localization of epileptic foci from interictal, intracranial EEG

Jan Cimbalnik, Petr Klimes, Vladimir Sladky, Petr Nejedly, Pavel Jurak, Martin Pail, Robert Roman, Pavel Daniel, Hari Guragain, Benjamin Brinkmann, Milan Brazdil, Gregory Alan Worrell

Research output: Contribution to journalArticle

Abstract

Objective: When considering all patients with focal drug-resistant epilepsy, as high as 40–50% of patients suffer seizure recurrence after surgery. To achieve seizure freedom without side effects, accurate localization of the epileptogenic tissue is crucial before its resection. We investigate an automated, fast, objective mapping process that uses only interictal data. Methods: We propose a novel approach based on multiple iEEG features, which are used to train a support vector machine (SVM) model for classification of iEEG electrodes as normal or pathologic using 30 min of inter-ictal recording. Results: The tissue under the iEEG electrodes, classified as epileptogenic, was removed in 17/18 excellent outcome patients and was not entirely resected in 8/10 poor outcome patients. The overall best result was achieved in a subset of 9 excellent outcome patients with the area under the receiver operating curve = 0.95. Conclusion: SVM models combining multiple iEEG features show better performance than algorithms using a single iEEG marker. Multiple iEEG and connectivity features in presurgical evaluation could improve epileptogenic tissue localization, which may improve surgical outcome and minimize risk of side effects. Significance: In this study, promising results were achieved in localization of epileptogenic regions by SVM models that combine multiple features from 30 min of inter-ictal iEEG recordings.

Original languageEnglish (US)
Pages (from-to)1945-1953
Number of pages9
JournalClinical Neurophysiology
Volume130
Issue number10
DOIs
StatePublished - Oct 1 2019

Fingerprint

Electrodes
Seizures
Stroke
Partial Epilepsy
Electrocorticography
Recurrence
Support Vector Machine
Drug Resistant Epilepsy

Keywords

  • Connectivity
  • Drug resistant epilepsy
  • Epileptogenic zone localization
  • High frequency oscillations
  • Machine learning
  • Multi-feature approach

ASJC Scopus subject areas

  • Sensory Systems
  • Neurology
  • Clinical Neurology
  • Physiology (medical)

Cite this

Multi-feature localization of epileptic foci from interictal, intracranial EEG. / Cimbalnik, Jan; Klimes, Petr; Sladky, Vladimir; Nejedly, Petr; Jurak, Pavel; Pail, Martin; Roman, Robert; Daniel, Pavel; Guragain, Hari; Brinkmann, Benjamin; Brazdil, Milan; Worrell, Gregory Alan.

In: Clinical Neurophysiology, Vol. 130, No. 10, 01.10.2019, p. 1945-1953.

Research output: Contribution to journalArticle

Cimbalnik, J, Klimes, P, Sladky, V, Nejedly, P, Jurak, P, Pail, M, Roman, R, Daniel, P, Guragain, H, Brinkmann, B, Brazdil, M & Worrell, GA 2019, 'Multi-feature localization of epileptic foci from interictal, intracranial EEG', Clinical Neurophysiology, vol. 130, no. 10, pp. 1945-1953. https://doi.org/10.1016/j.clinph.2019.07.024
Cimbalnik J, Klimes P, Sladky V, Nejedly P, Jurak P, Pail M et al. Multi-feature localization of epileptic foci from interictal, intracranial EEG. Clinical Neurophysiology. 2019 Oct 1;130(10):1945-1953. https://doi.org/10.1016/j.clinph.2019.07.024
Cimbalnik, Jan ; Klimes, Petr ; Sladky, Vladimir ; Nejedly, Petr ; Jurak, Pavel ; Pail, Martin ; Roman, Robert ; Daniel, Pavel ; Guragain, Hari ; Brinkmann, Benjamin ; Brazdil, Milan ; Worrell, Gregory Alan. / Multi-feature localization of epileptic foci from interictal, intracranial EEG. In: Clinical Neurophysiology. 2019 ; Vol. 130, No. 10. pp. 1945-1953.
@article{02627f5b54194c23848c96eada72e1ef,
title = "Multi-feature localization of epileptic foci from interictal, intracranial EEG",
abstract = "Objective: When considering all patients with focal drug-resistant epilepsy, as high as 40–50{\%} of patients suffer seizure recurrence after surgery. To achieve seizure freedom without side effects, accurate localization of the epileptogenic tissue is crucial before its resection. We investigate an automated, fast, objective mapping process that uses only interictal data. Methods: We propose a novel approach based on multiple iEEG features, which are used to train a support vector machine (SVM) model for classification of iEEG electrodes as normal or pathologic using 30 min of inter-ictal recording. Results: The tissue under the iEEG electrodes, classified as epileptogenic, was removed in 17/18 excellent outcome patients and was not entirely resected in 8/10 poor outcome patients. The overall best result was achieved in a subset of 9 excellent outcome patients with the area under the receiver operating curve = 0.95. Conclusion: SVM models combining multiple iEEG features show better performance than algorithms using a single iEEG marker. Multiple iEEG and connectivity features in presurgical evaluation could improve epileptogenic tissue localization, which may improve surgical outcome and minimize risk of side effects. Significance: In this study, promising results were achieved in localization of epileptogenic regions by SVM models that combine multiple features from 30 min of inter-ictal iEEG recordings.",
keywords = "Connectivity, Drug resistant epilepsy, Epileptogenic zone localization, High frequency oscillations, Machine learning, Multi-feature approach",
author = "Jan Cimbalnik and Petr Klimes and Vladimir Sladky and Petr Nejedly and Pavel Jurak and Martin Pail and Robert Roman and Pavel Daniel and Hari Guragain and Benjamin Brinkmann and Milan Brazdil and Worrell, {Gregory Alan}",
year = "2019",
month = "10",
day = "1",
doi = "10.1016/j.clinph.2019.07.024",
language = "English (US)",
volume = "130",
pages = "1945--1953",
journal = "Clinical Neurophysiology",
issn = "1388-2457",
publisher = "Elsevier Ireland Ltd",
number = "10",

}

TY - JOUR

T1 - Multi-feature localization of epileptic foci from interictal, intracranial EEG

AU - Cimbalnik, Jan

AU - Klimes, Petr

AU - Sladky, Vladimir

AU - Nejedly, Petr

AU - Jurak, Pavel

AU - Pail, Martin

AU - Roman, Robert

AU - Daniel, Pavel

AU - Guragain, Hari

AU - Brinkmann, Benjamin

AU - Brazdil, Milan

AU - Worrell, Gregory Alan

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Objective: When considering all patients with focal drug-resistant epilepsy, as high as 40–50% of patients suffer seizure recurrence after surgery. To achieve seizure freedom without side effects, accurate localization of the epileptogenic tissue is crucial before its resection. We investigate an automated, fast, objective mapping process that uses only interictal data. Methods: We propose a novel approach based on multiple iEEG features, which are used to train a support vector machine (SVM) model for classification of iEEG electrodes as normal or pathologic using 30 min of inter-ictal recording. Results: The tissue under the iEEG electrodes, classified as epileptogenic, was removed in 17/18 excellent outcome patients and was not entirely resected in 8/10 poor outcome patients. The overall best result was achieved in a subset of 9 excellent outcome patients with the area under the receiver operating curve = 0.95. Conclusion: SVM models combining multiple iEEG features show better performance than algorithms using a single iEEG marker. Multiple iEEG and connectivity features in presurgical evaluation could improve epileptogenic tissue localization, which may improve surgical outcome and minimize risk of side effects. Significance: In this study, promising results were achieved in localization of epileptogenic regions by SVM models that combine multiple features from 30 min of inter-ictal iEEG recordings.

AB - Objective: When considering all patients with focal drug-resistant epilepsy, as high as 40–50% of patients suffer seizure recurrence after surgery. To achieve seizure freedom without side effects, accurate localization of the epileptogenic tissue is crucial before its resection. We investigate an automated, fast, objective mapping process that uses only interictal data. Methods: We propose a novel approach based on multiple iEEG features, which are used to train a support vector machine (SVM) model for classification of iEEG electrodes as normal or pathologic using 30 min of inter-ictal recording. Results: The tissue under the iEEG electrodes, classified as epileptogenic, was removed in 17/18 excellent outcome patients and was not entirely resected in 8/10 poor outcome patients. The overall best result was achieved in a subset of 9 excellent outcome patients with the area under the receiver operating curve = 0.95. Conclusion: SVM models combining multiple iEEG features show better performance than algorithms using a single iEEG marker. Multiple iEEG and connectivity features in presurgical evaluation could improve epileptogenic tissue localization, which may improve surgical outcome and minimize risk of side effects. Significance: In this study, promising results were achieved in localization of epileptogenic regions by SVM models that combine multiple features from 30 min of inter-ictal iEEG recordings.

KW - Connectivity

KW - Drug resistant epilepsy

KW - Epileptogenic zone localization

KW - High frequency oscillations

KW - Machine learning

KW - Multi-feature approach

UR - http://www.scopus.com/inward/record.url?scp=85071109284&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071109284&partnerID=8YFLogxK

U2 - 10.1016/j.clinph.2019.07.024

DO - 10.1016/j.clinph.2019.07.024

M3 - Article

VL - 130

SP - 1945

EP - 1953

JO - Clinical Neurophysiology

JF - Clinical Neurophysiology

SN - 1388-2457

IS - 10

ER -