Automated video detection of epileptic convulsion slowing as a precursor for post-ictal generalized EEG suppression

Stiliyan N. Kalitzin, Prisca R. Bauer, Robert J. Lamberts, Demetrios N. Velis, Roland D. Thijs, Fernando H. Lopes Da Silva

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

Abstract

Rationale. Automated monitoring and alerting for adverse events in patients with epilepsy can provide higher security and quality of life for those who suffer from this debilitating condition. Recently we explored the relation between clonic slowing at the end of a convulsive seizure and the occurrence and duration of a subsequent period of post-ictal generalized EEG suppression (PGES). We found that prolonged periods of PGES can be predicted by the amount of progressive increase of inter-clonic intervals (ICI) during the seizure. PGES was previously linked to SUDEP The purpose of the present study is to develop an automated, remote video sensing based algorithm for real-time detection of significant clonic slowing that can be used to alert for PGES and which may eventually help preventing sudden unexpected death in epilepsy (SUDEP). Methods. The technique is based on our earlier published optical flow video sequence processing paradigm that has been applied for automated detection of major motor seizures. Here we introduce an integral Radon-like transformation on the timefrequency wavelet spectrum in order to detect log-linear frequency changes during the seizure. We validate the automated detection and quantification of the ICI increase by comparison to the results from manually processed EEG traces as “gold standard”. We studied 48 cases of convulsive seizures for which synchronized EEG-video recording was available. Results. In most cases the spectral ridges obtained from Gabor-wavelet transformations of the optical flow group velocities were in close proximity to the ICI traces detected manually from EEG data during seizure (the gold standard). The quantification of the slowing-down effect measured by the dominant angle in the Radon transformed spectrum was significantly correlated with the exponential ICI increase factors obtained from manual detection.

Original languageEnglish
Title of host publicationXIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016
PublisherSpringer Verlag
Pages100-104
Number of pages5
Volume57
ISBN (Print)9783319327013
DOIs
Publication statusPublished - 2016
Event14th Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016 - Paphos, Cyprus
Duration: 31 Mar 20162 Apr 2016

Conference

Conference14th Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016
CountryCyprus
CityPaphos
Period31/03/201602/04/2016

Cite this

Kalitzin, S. N., Bauer, P. R., Lamberts, R. J., Velis, D. N., Thijs, R. D., & Lopes Da Silva, F. H. (2016). Automated video detection of epileptic convulsion slowing as a precursor for post-ictal generalized EEG suppression. In XIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016 (Vol. 57, pp. 100-104). Springer Verlag. https://doi.org/10.1007/978-3-319-32703-7_21
Kalitzin, Stiliyan N. ; Bauer, Prisca R. ; Lamberts, Robert J. ; Velis, Demetrios N. ; Thijs, Roland D. ; Lopes Da Silva, Fernando H. / Automated video detection of epileptic convulsion slowing as a precursor for post-ictal generalized EEG suppression. XIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016. Vol. 57 Springer Verlag, 2016. pp. 100-104
@inproceedings{dda28d37a88140f084e58adb0d70196c,
title = "Automated video detection of epileptic convulsion slowing as a precursor for post-ictal generalized EEG suppression",
abstract = "Rationale. Automated monitoring and alerting for adverse events in patients with epilepsy can provide higher security and quality of life for those who suffer from this debilitating condition. Recently we explored the relation between clonic slowing at the end of a convulsive seizure and the occurrence and duration of a subsequent period of post-ictal generalized EEG suppression (PGES). We found that prolonged periods of PGES can be predicted by the amount of progressive increase of inter-clonic intervals (ICI) during the seizure. PGES was previously linked to SUDEP The purpose of the present study is to develop an automated, remote video sensing based algorithm for real-time detection of significant clonic slowing that can be used to alert for PGES and which may eventually help preventing sudden unexpected death in epilepsy (SUDEP). Methods. The technique is based on our earlier published optical flow video sequence processing paradigm that has been applied for automated detection of major motor seizures. Here we introduce an integral Radon-like transformation on the timefrequency wavelet spectrum in order to detect log-linear frequency changes during the seizure. We validate the automated detection and quantification of the ICI increase by comparison to the results from manually processed EEG traces as “gold standard”. We studied 48 cases of convulsive seizures for which synchronized EEG-video recording was available. Results. In most cases the spectral ridges obtained from Gabor-wavelet transformations of the optical flow group velocities were in close proximity to the ICI traces detected manually from EEG data during seizure (the gold standard). The quantification of the slowing-down effect measured by the dominant angle in the Radon transformed spectrum was significantly correlated with the exponential ICI increase factors obtained from manual detection.",
keywords = "Clonic seizures, Epilepsy, SUDEP, Video processing",
author = "Kalitzin, {Stiliyan N.} and Bauer, {Prisca R.} and Lamberts, {Robert J.} and Velis, {Demetrios N.} and Thijs, {Roland D.} and {Lopes Da Silva}, {Fernando H.}",
year = "2016",
doi = "10.1007/978-3-319-32703-7_21",
language = "English",
isbn = "9783319327013",
volume = "57",
pages = "100--104",
booktitle = "XIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016",
publisher = "Springer Verlag",
address = "Germany",

}

Kalitzin, SN, Bauer, PR, Lamberts, RJ, Velis, DN, Thijs, RD & Lopes Da Silva, FH 2016, Automated video detection of epileptic convulsion slowing as a precursor for post-ictal generalized EEG suppression. in XIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016. vol. 57, Springer Verlag, pp. 100-104, 14th Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016, Paphos, Cyprus, 31/03/2016. https://doi.org/10.1007/978-3-319-32703-7_21

Automated video detection of epileptic convulsion slowing as a precursor for post-ictal generalized EEG suppression. / Kalitzin, Stiliyan N.; Bauer, Prisca R.; Lamberts, Robert J.; Velis, Demetrios N.; Thijs, Roland D.; Lopes Da Silva, Fernando H.

XIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016. Vol. 57 Springer Verlag, 2016. p. 100-104.

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

TY - GEN

T1 - Automated video detection of epileptic convulsion slowing as a precursor for post-ictal generalized EEG suppression

AU - Kalitzin, Stiliyan N.

AU - Bauer, Prisca R.

AU - Lamberts, Robert J.

AU - Velis, Demetrios N.

AU - Thijs, Roland D.

AU - Lopes Da Silva, Fernando H.

PY - 2016

Y1 - 2016

N2 - Rationale. Automated monitoring and alerting for adverse events in patients with epilepsy can provide higher security and quality of life for those who suffer from this debilitating condition. Recently we explored the relation between clonic slowing at the end of a convulsive seizure and the occurrence and duration of a subsequent period of post-ictal generalized EEG suppression (PGES). We found that prolonged periods of PGES can be predicted by the amount of progressive increase of inter-clonic intervals (ICI) during the seizure. PGES was previously linked to SUDEP The purpose of the present study is to develop an automated, remote video sensing based algorithm for real-time detection of significant clonic slowing that can be used to alert for PGES and which may eventually help preventing sudden unexpected death in epilepsy (SUDEP). Methods. The technique is based on our earlier published optical flow video sequence processing paradigm that has been applied for automated detection of major motor seizures. Here we introduce an integral Radon-like transformation on the timefrequency wavelet spectrum in order to detect log-linear frequency changes during the seizure. We validate the automated detection and quantification of the ICI increase by comparison to the results from manually processed EEG traces as “gold standard”. We studied 48 cases of convulsive seizures for which synchronized EEG-video recording was available. Results. In most cases the spectral ridges obtained from Gabor-wavelet transformations of the optical flow group velocities were in close proximity to the ICI traces detected manually from EEG data during seizure (the gold standard). The quantification of the slowing-down effect measured by the dominant angle in the Radon transformed spectrum was significantly correlated with the exponential ICI increase factors obtained from manual detection.

AB - Rationale. Automated monitoring and alerting for adverse events in patients with epilepsy can provide higher security and quality of life for those who suffer from this debilitating condition. Recently we explored the relation between clonic slowing at the end of a convulsive seizure and the occurrence and duration of a subsequent period of post-ictal generalized EEG suppression (PGES). We found that prolonged periods of PGES can be predicted by the amount of progressive increase of inter-clonic intervals (ICI) during the seizure. PGES was previously linked to SUDEP The purpose of the present study is to develop an automated, remote video sensing based algorithm for real-time detection of significant clonic slowing that can be used to alert for PGES and which may eventually help preventing sudden unexpected death in epilepsy (SUDEP). Methods. The technique is based on our earlier published optical flow video sequence processing paradigm that has been applied for automated detection of major motor seizures. Here we introduce an integral Radon-like transformation on the timefrequency wavelet spectrum in order to detect log-linear frequency changes during the seizure. We validate the automated detection and quantification of the ICI increase by comparison to the results from manually processed EEG traces as “gold standard”. We studied 48 cases of convulsive seizures for which synchronized EEG-video recording was available. Results. In most cases the spectral ridges obtained from Gabor-wavelet transformations of the optical flow group velocities were in close proximity to the ICI traces detected manually from EEG data during seizure (the gold standard). The quantification of the slowing-down effect measured by the dominant angle in the Radon transformed spectrum was significantly correlated with the exponential ICI increase factors obtained from manual detection.

KW - Clonic seizures

KW - Epilepsy

KW - SUDEP

KW - Video processing

UR - http://www.scopus.com/inward/record.url?scp=84968586454&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-32703-7_21

DO - 10.1007/978-3-319-32703-7_21

M3 - Conference contribution

SN - 9783319327013

VL - 57

SP - 100

EP - 104

BT - XIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016

PB - Springer Verlag

ER -

Kalitzin SN, Bauer PR, Lamberts RJ, Velis DN, Thijs RD, Lopes Da Silva FH. Automated video detection of epileptic convulsion slowing as a precursor for post-ictal generalized EEG suppression. In XIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016. Vol. 57. Springer Verlag. 2016. p. 100-104 https://doi.org/10.1007/978-3-319-32703-7_21