Automated real-time epileptic seizure detection in scalp EEG recordings using an algorithm based on wavelet packet transform

Ali Shahidi Zandi, Manouchehr Javidan, Guy A. Dumont, Reza Tafreshi

Research output: Contribution to journalArticle

119 Citations (Scopus)

Abstract

A novel wavelet-based algorithm for real-time detection of epileptic seizures using scalp EEG is proposed. In a movingwindow analysis, the EEG from each channel is decomposed by wavelet packet transform. Using wavelet coefficients from seizure and nonseizure references, a patient-specific measure is developed to quantify the separation between seizure and nonseizure states for the frequency range of 1-30 Hz. Utilizing this measure, a frequency band representing themaximum separation between the two states is determined and employed to develop a normalized index, called combined seizure index (CSI). CSI is derived for each epoch of every EEG channel based on both rhythmicity and relative energy of that epoch as well as consistency among different channels. Increasing significantly during ictal states, CSI is inspected using one-sided cumulative sum test to generate proper channel alarms. Analyzing alarms from all channels, a seizure alarm is finally generated. The algorithm was tested on scalp EEG recordings from 14 patients, totaling ∼75.8 h with 63 seizures. Results revealed a high sensitivity of 90.5%, a false detection rate of 0.51 h-1 and a median detection delay of 7 s. The algorithm could also lateralize the focus side for patients with temporal lobe epilepsy.

Original languageEnglish
Article number5484951
Pages (from-to)1639-1651
Number of pages13
JournalIEEE Transactions on Biomedical Engineering
Volume57
Issue number7
DOIs
Publication statusPublished - 2010

Fingerprint

Electroencephalography
Frequency bands

Keywords

  • EEG
  • epilepsy
  • seizure detection
  • seizure focus lateralization
  • wavelet packet (WP) transform

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Automated real-time epileptic seizure detection in scalp EEG recordings using an algorithm based on wavelet packet transform. / Zandi, Ali Shahidi; Javidan, Manouchehr; Dumont, Guy A.; Tafreshi, Reza.

In: IEEE Transactions on Biomedical Engineering, Vol. 57, No. 7, 5484951, 2010, p. 1639-1651.

Research output: Contribution to journalArticle

@article{5a87ce7817fc4be394346f91a0a1f14e,
title = "Automated real-time epileptic seizure detection in scalp EEG recordings using an algorithm based on wavelet packet transform",
abstract = "A novel wavelet-based algorithm for real-time detection of epileptic seizures using scalp EEG is proposed. In a movingwindow analysis, the EEG from each channel is decomposed by wavelet packet transform. Using wavelet coefficients from seizure and nonseizure references, a patient-specific measure is developed to quantify the separation between seizure and nonseizure states for the frequency range of 1-30 Hz. Utilizing this measure, a frequency band representing themaximum separation between the two states is determined and employed to develop a normalized index, called combined seizure index (CSI). CSI is derived for each epoch of every EEG channel based on both rhythmicity and relative energy of that epoch as well as consistency among different channels. Increasing significantly during ictal states, CSI is inspected using one-sided cumulative sum test to generate proper channel alarms. Analyzing alarms from all channels, a seizure alarm is finally generated. The algorithm was tested on scalp EEG recordings from 14 patients, totaling ∼75.8 h with 63 seizures. Results revealed a high sensitivity of 90.5{\%}, a false detection rate of 0.51 h-1 and a median detection delay of 7 s. The algorithm could also lateralize the focus side for patients with temporal lobe epilepsy.",
keywords = "EEG, epilepsy, seizure detection, seizure focus lateralization, wavelet packet (WP) transform",
author = "Zandi, {Ali Shahidi} and Manouchehr Javidan and Dumont, {Guy A.} and Reza Tafreshi",
year = "2010",
doi = "10.1109/TBME.2010.2046417",
language = "English",
volume = "57",
pages = "1639--1651",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "7",

}

TY - JOUR

T1 - Automated real-time epileptic seizure detection in scalp EEG recordings using an algorithm based on wavelet packet transform

AU - Zandi, Ali Shahidi

AU - Javidan, Manouchehr

AU - Dumont, Guy A.

AU - Tafreshi, Reza

PY - 2010

Y1 - 2010

N2 - A novel wavelet-based algorithm for real-time detection of epileptic seizures using scalp EEG is proposed. In a movingwindow analysis, the EEG from each channel is decomposed by wavelet packet transform. Using wavelet coefficients from seizure and nonseizure references, a patient-specific measure is developed to quantify the separation between seizure and nonseizure states for the frequency range of 1-30 Hz. Utilizing this measure, a frequency band representing themaximum separation between the two states is determined and employed to develop a normalized index, called combined seizure index (CSI). CSI is derived for each epoch of every EEG channel based on both rhythmicity and relative energy of that epoch as well as consistency among different channels. Increasing significantly during ictal states, CSI is inspected using one-sided cumulative sum test to generate proper channel alarms. Analyzing alarms from all channels, a seizure alarm is finally generated. The algorithm was tested on scalp EEG recordings from 14 patients, totaling ∼75.8 h with 63 seizures. Results revealed a high sensitivity of 90.5%, a false detection rate of 0.51 h-1 and a median detection delay of 7 s. The algorithm could also lateralize the focus side for patients with temporal lobe epilepsy.

AB - A novel wavelet-based algorithm for real-time detection of epileptic seizures using scalp EEG is proposed. In a movingwindow analysis, the EEG from each channel is decomposed by wavelet packet transform. Using wavelet coefficients from seizure and nonseizure references, a patient-specific measure is developed to quantify the separation between seizure and nonseizure states for the frequency range of 1-30 Hz. Utilizing this measure, a frequency band representing themaximum separation between the two states is determined and employed to develop a normalized index, called combined seizure index (CSI). CSI is derived for each epoch of every EEG channel based on both rhythmicity and relative energy of that epoch as well as consistency among different channels. Increasing significantly during ictal states, CSI is inspected using one-sided cumulative sum test to generate proper channel alarms. Analyzing alarms from all channels, a seizure alarm is finally generated. The algorithm was tested on scalp EEG recordings from 14 patients, totaling ∼75.8 h with 63 seizures. Results revealed a high sensitivity of 90.5%, a false detection rate of 0.51 h-1 and a median detection delay of 7 s. The algorithm could also lateralize the focus side for patients with temporal lobe epilepsy.

KW - EEG

KW - epilepsy

KW - seizure detection

KW - seizure focus lateralization

KW - wavelet packet (WP) transform

UR - http://www.scopus.com/inward/record.url?scp=77953788429&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953788429&partnerID=8YFLogxK

U2 - 10.1109/TBME.2010.2046417

DO - 10.1109/TBME.2010.2046417

M3 - Article

C2 - 20659825

AN - SCOPUS:77953788429

VL - 57

SP - 1639

EP - 1651

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 7

M1 - 5484951

ER -