Neonatal seizure detection and localization using time-frequency analysis of multichannel EEG

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

doi:10.1109/ICSPC.2007.4728632

Neonatal seizure detection and localization using time-frequency analysis of multichannel EEG

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

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

Contrarily to adults and older children, the clinical signs of seizure in newborns are either subtle or occult. For this reason, the electroencephalogram (EEG) has been the most dependable tool used for detecting seizures in newborns. Given nonstationary and multicomponent EEG signals, time-frequency (TF) based methods were found to be very suitable for the analysis of such signals. The TF domain techniques are utilized to extract TF signatures that are characteristic of EEG seizures. In this paper, multichannel EEG signals are processed using a TF matched filter to detect and to geometrically localize neonatal EEG seizures. 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 language	English
Title of host publication	ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications
Pages	1567-1570
Number of pages	4
DOIs	https://doi.org/10.1109/ICSPC.2007.4728632
Publication status	Published - 2007
Event	2007 IEEE International Conference on Signal Processing and Communications, ICSPC 2007 - Dubai, United Arab Emirates Duration: Nov 14 2007 → Nov 27 2007

Other

Other	2007 IEEE International Conference on Signal Processing and Communications, ICSPC 2007
Country	United Arab Emirates
City	Dubai
Period	11/14/07 → 11/27/07

Keywords

EEG
Matched filter
Multichannel
Seizure
Time frequency

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing
Communication

Access to Document

10.1109/ICSPC.2007.4728632

Fingerprint Dive into the research topics of 'Neonatal seizure detection and localization using time-frequency analysis of multichannel EEG'. Together they form a unique fingerprint.

Cite this

Khlif, MS, Mesbah, M, Boashash, B & Colditz, P 2007, Neonatal seizure detection and localization using time-frequency analysis of multichannel EEG. in ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications., 4728632, pp. 1567-1570, 2007 IEEE International Conference on Signal Processing and Communications, ICSPC 2007, Dubai, United Arab Emirates, 11/14/07. https://doi.org/10.1109/ICSPC.2007.4728632

@inproceedings{233e218b85f54dce8563f00718d11260,

title = "Neonatal seizure detection and localization using time-frequency analysis of multichannel EEG",

abstract = "Contrarily to adults and older children, the clinical signs of seizure in newborns are either subtle or occult. For this reason, the electroencephalogram (EEG) has been the most dependable tool used for detecting seizures in newborns. Given nonstationary and multicomponent EEG signals, time-frequency (TF) based methods were found to be very suitable for the analysis of such signals. The TF domain techniques are utilized to extract TF signatures that are characteristic of EEG seizures. In this paper, multichannel EEG signals are processed using a TF matched filter to detect and to geometrically localize neonatal EEG seizures. 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.",

keywords = "EEG, Matched filter, Multichannel, Seizure, Time frequency",

author = "Khlif, {M. S.} and M. Mesbah and B. Boashash and P. Colditz",

year = "2007",

doi = "10.1109/ICSPC.2007.4728632",

language = "English",

isbn = "9781424412365",

pages = "1567--1570",

booktitle = "ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications",

note = "2007 IEEE International Conference on Signal Processing and Communications, ICSPC 2007 ; Conference date: 14-11-2007 Through 27-11-2007",

}

TY - GEN

T1 - Neonatal seizure detection and localization using time-frequency analysis of multichannel EEG

AU - Khlif, M. S.

AU - Mesbah, M.

AU - Boashash, B.

AU - Colditz, P.

PY - 2007

Y1 - 2007

N2 - Contrarily to adults and older children, the clinical signs of seizure in newborns are either subtle or occult. For this reason, the electroencephalogram (EEG) has been the most dependable tool used for detecting seizures in newborns. Given nonstationary and multicomponent EEG signals, time-frequency (TF) based methods were found to be very suitable for the analysis of such signals. The TF domain techniques are utilized to extract TF signatures that are characteristic of EEG seizures. In this paper, multichannel EEG signals are processed using a TF matched filter to detect and to geometrically localize neonatal EEG seizures. 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 - Contrarily to adults and older children, the clinical signs of seizure in newborns are either subtle or occult. For this reason, the electroencephalogram (EEG) has been the most dependable tool used for detecting seizures in newborns. Given nonstationary and multicomponent EEG signals, time-frequency (TF) based methods were found to be very suitable for the analysis of such signals. The TF domain techniques are utilized to extract TF signatures that are characteristic of EEG seizures. In this paper, multichannel EEG signals are processed using a TF matched filter to detect and to geometrically localize neonatal EEG seizures. 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.

KW - EEG

KW - Matched filter

KW - Multichannel

KW - Seizure

KW - Time frequency

UR - http://www.scopus.com/inward/record.url?scp=60349100704&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60349100704&partnerID=8YFLogxK

U2 - 10.1109/ICSPC.2007.4728632

DO - 10.1109/ICSPC.2007.4728632

M3 - Conference contribution

AN - SCOPUS:60349100704

SN - 9781424412365

SP - 1567

EP - 1570

BT - ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications

T2 - 2007 IEEE International Conference on Signal Processing and Communications, ICSPC 2007

Y2 - 14 November 2007 through 27 November 2007

ER -