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

J 2019

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

CIMBÁLNÍK, Jan, Petr KLIMES, Vladimir SLADKY, Petr NEJEDLY, Pavel JURAK et. al.

Basic information

Original name

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

Authors

CIMBÁLNÍK, Jan (203 Czech Republic, guarantor), Petr KLIMES (203 Czech Republic), Vladimir SLADKY (203 Czech Republic), Petr NEJEDLY (203 Czech Republic), Pavel JURAK (203 Czech Republic), Martin PAIL (203 Czech Republic, belonging to the institution), Robert ROMAN (203 Czech Republic, belonging to the institution), Pavel DANIEL (203 Czech Republic, belonging to the institution), Hari GURAGAIN (840 United States of America), Benjamin BRINKMANN (840 United States of America), Milan BRÁZDIL (203 Czech Republic, belonging to the institution) and Greg WORRELL (840 United States of America)

Edition

Clinical Neurophysiology, Clare, Elsevier Ireland, 2019, 1388-2457

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

30103 Neurosciences

Country of publisher

Ireland

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 3.214

RIV identification code

RIV/00216224:14110/19:00110969

Organization unit

Faculty of Medicine

DOI

http://dx.doi.org/10.1016/j.clinph.2019.07.024

UT WoS

000485832400022

Keywords in English

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

Abstract

V originále

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. (C) 2019 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.

Links

LM2015062, research and development project

Name: Národní infrastruktura pro biologické a medicínské zobrazování

Investor: Ministry of Education, Youth and Sports of the CR

90062, large research infrastructures

Name: Czech-BioImaging

Citovat

CIMBÁLNÍK, Jan, Petr KLIMES, Vladimir SLADKY, Petr NEJEDLY, Pavel JURAK, Martin PAIL, Robert ROMAN, Pavel DANIEL, Hari GURAGAIN, Benjamin BRINKMANN, Milan BRÁZDIL and Greg WORRELL. Multi-feature localization of epileptic foci from interictal, intracranial EEG. Clinical Neurophysiology. Clare: Elsevier Ireland, 2019, vol. 130, No 10, p. 1945-1953. ISSN 1388-2457. Available from: https://dx.doi.org/10.1016/j.clinph.2019.07.024.

@article{1569797,
   author = {Cimbálník, Jan and Klimes, Petr and Sladky, Vladimir and Nejedly, Petr and Jurak, Pavel and Pail, Martin and Roman, Robert and Daniel, Pavel and Guragain, Hari and Brinkmann, Benjamin and Brázdil, Milan and Worrell, Greg},
   article_location = {Clare},
   article_number = {10},
   doi = {http://dx.doi.org/10.1016/j.clinph.2019.07.024},
   keywords = {Drug resistant epilepsy; Epileptogenic zone localization; Multi-feature approach; High frequency oscillations; Connectivity; Machine learning},
   language = {eng},
   issn = {1388-2457},
   journal = {Clinical Neurophysiology},
   title = {Multi-feature localization of epileptic foci from interictal, intracranial EEG},
   url = {http://dx.doi.org/10.1016/j.clinph.2019.07.024},
   volume = {130},
   year = {2019}
}

TY  - JOUR
ID  - 1569797
AU  - Cimbálník, Jan - Klimes, Petr - Sladky, Vladimir - Nejedly, Petr - Jurak, Pavel - Pail, Martin - Roman, Robert - Daniel, Pavel - Guragain, Hari - Brinkmann, Benjamin - Brázdil, Milan - Worrell, Greg
PY  - 2019
TI  - Multi-feature localization of epileptic foci from interictal, intracranial EEG
JF  - Clinical Neurophysiology
VL  - 130
IS  - 10
SP  - 1945-1953
EP  - 1945-1953
PB  - Elsevier Ireland
SN  - 13882457
KW  - Drug resistant epilepsy
KW  - Epileptogenic zone localization
KW  - Multi-feature approach
KW  - High frequency oscillations
KW  - Connectivity
KW  - Machine learning
UR  - http://dx.doi.org/10.1016/j.clinph.2019.07.024
L2  - http://dx.doi.org/10.1016/j.clinph.2019.07.024
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. (C) 2019 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.
ER  -

CIMBÁLNÍK, Jan, Petr KLIMES, Vladimir SLADKY, Petr NEJEDLY, Pavel JURAK, Martin PAIL, Robert ROMAN, Pavel DANIEL, Hari GURAGAIN, Benjamin BRINKMANN, Milan BRÁZDIL and Greg WORRELL. Multi-feature localization of epileptic foci from interictal, intracranial EEG. \textit{Clinical Neurophysiology}. Clare: Elsevier Ireland, 2019, vol.~130, No~10, p.~1945-1953. ISSN~1388-2457. Available from: https://dx.doi.org/10.1016/j.clinph.2019.07.024.

Detailed Information on Publication Record