Multichannel-based newborn eeg seizure detection using time-frequency matched filter

M. S. Khlif, M. Mesbah, B. Boashash, P. Colditz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

Abstract

In recent years, much effort has been made toward developing computerized methods to detect seizures. In adults, the clinical signs of seizures are well defined and easily recognizable. But in newborns, these signs are either subtle or completely absent. For this reason, the electroencephalogram (EEG) has been the most dependable tool used for detecting seizures in newborns. Considering the non-stationary and multicomponent nature of the EEG signals, timefrequency (TF) based methods were found to be very suitable for the analysis of such signals. Using TF representation of EEG signals allows extracting TF signatures that are characteristic of EEG seizures. In this paper we present a TF method for newborn EEG seizure detection using a TF matched filter. The threshold used to distinguish between seizure and nonseizure is data-dependent and is set using the EEG background. Multichannel geometrical correlation, based on a concept of incidence matrix, was utilized to further enhance the performance of the detector.

Original languageEnglish
Title of host publication29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07
Pages1265-1268
Number of pages4
DOIs
Publication statusPublished - 2007
Event29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07 - Lyon, France
Duration: Aug 23 2007Aug 26 2007

Other

Other29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07
CountryFrance
CityLyon
Period8/23/078/26/07

Fingerprint

Matched filters
Electroencephalography
Seizures
Detectors
Incidence

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Khlif, M. S., Mesbah, M., Boashash, B., & Colditz, P. (2007). Multichannel-based newborn eeg seizure detection using time-frequency matched filter. In 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07 (pp. 1265-1268). [4352527] https://doi.org/10.1109/IEMBS.2007.4352527

Multichannel-based newborn eeg seizure detection using time-frequency matched filter. / Khlif, M. S.; Mesbah, M.; Boashash, B.; Colditz, P.

29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. 2007. p. 1265-1268 4352527.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Khlif, MS, Mesbah, M, Boashash, B & Colditz, P 2007, Multichannel-based newborn eeg seizure detection using time-frequency matched filter. in 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07., 4352527, pp. 1265-1268, 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07, Lyon, France, 8/23/07. https://doi.org/10.1109/IEMBS.2007.4352527
Khlif MS, Mesbah M, Boashash B, Colditz P. Multichannel-based newborn eeg seizure detection using time-frequency matched filter. In 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. 2007. p. 1265-1268. 4352527 https://doi.org/10.1109/IEMBS.2007.4352527
Khlif, M. S. ; Mesbah, M. ; Boashash, B. ; Colditz, P. / Multichannel-based newborn eeg seizure detection using time-frequency matched filter. 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. 2007. pp. 1265-1268
@inproceedings{c0c2093d51d5479e8e0a5aab55859f12,
title = "Multichannel-based newborn eeg seizure detection using time-frequency matched filter",
abstract = "In recent years, much effort has been made toward developing computerized methods to detect seizures. In adults, the clinical signs of seizures are well defined and easily recognizable. But in newborns, these signs are either subtle or completely absent. For this reason, the electroencephalogram (EEG) has been the most dependable tool used for detecting seizures in newborns. Considering the non-stationary and multicomponent nature of the EEG signals, timefrequency (TF) based methods were found to be very suitable for the analysis of such signals. Using TF representation of EEG signals allows extracting TF signatures that are characteristic of EEG seizures. In this paper we present a TF method for newborn EEG seizure detection using a TF matched filter. The threshold used to distinguish between seizure and nonseizure is data-dependent and is set using the EEG background. Multichannel geometrical correlation, based on a concept of incidence matrix, was utilized to further enhance the performance of the detector.",
author = "Khlif, {M. S.} and M. Mesbah and B. Boashash and P. Colditz",
year = "2007",
doi = "10.1109/IEMBS.2007.4352527",
language = "English",
isbn = "1424407885",
pages = "1265--1268",
booktitle = "29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07",

}

TY - GEN

T1 - Multichannel-based newborn eeg seizure detection using time-frequency matched filter

AU - Khlif, M. S.

AU - Mesbah, M.

AU - Boashash, B.

AU - Colditz, P.

PY - 2007

Y1 - 2007

N2 - In recent years, much effort has been made toward developing computerized methods to detect seizures. In adults, the clinical signs of seizures are well defined and easily recognizable. But in newborns, these signs are either subtle or completely absent. For this reason, the electroencephalogram (EEG) has been the most dependable tool used for detecting seizures in newborns. Considering the non-stationary and multicomponent nature of the EEG signals, timefrequency (TF) based methods were found to be very suitable for the analysis of such signals. Using TF representation of EEG signals allows extracting TF signatures that are characteristic of EEG seizures. In this paper we present a TF method for newborn EEG seizure detection using a TF matched filter. The threshold used to distinguish between seizure and nonseizure is data-dependent and is set using the EEG background. Multichannel geometrical correlation, based on a concept of incidence matrix, was utilized to further enhance the performance of the detector.

AB - In recent years, much effort has been made toward developing computerized methods to detect seizures. In adults, the clinical signs of seizures are well defined and easily recognizable. But in newborns, these signs are either subtle or completely absent. For this reason, the electroencephalogram (EEG) has been the most dependable tool used for detecting seizures in newborns. Considering the non-stationary and multicomponent nature of the EEG signals, timefrequency (TF) based methods were found to be very suitable for the analysis of such signals. Using TF representation of EEG signals allows extracting TF signatures that are characteristic of EEG seizures. In this paper we present a TF method for newborn EEG seizure detection using a TF matched filter. The threshold used to distinguish between seizure and nonseizure is data-dependent and is set using the EEG background. Multichannel geometrical correlation, based on a concept of incidence matrix, was utilized to further enhance the performance of the detector.

UR - http://www.scopus.com/inward/record.url?scp=57649158808&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57649158808&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2007.4352527

DO - 10.1109/IEMBS.2007.4352527

M3 - Conference contribution

C2 - 18002193

AN - SCOPUS:57649158808

SN - 1424407885

SN - 9781424407880

SP - 1265

EP - 1268

BT - 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07

ER -