Improved spindle detection through intuitive pre-processing of electroencephalogram

Abdul Jaleel, Beena Ahmed, Reza Tafreshi, Diane B. Boivin, Leopold Streletz, Naim Haddad

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Background: Numerous signal processing techniques have been proposed for automated spindle detection on EEG recordings with varying degrees of success. While the latest techniques usually introduce computational complexity and/or vagueness, the conventional techniques attempted in literature have led to poor results. This study presents a spindle detection approach which relies on intuitive pre-processing of the EEG prior to spindle detection, thus resulting in higher accuracy even with standard techniques. New method: The pre-processing techniques proposed include applying the derivative operator on the EEG, suppressing the background activity using Empirical Mode Decomposition and shortlisting candidate EEG segments based on eye-movements on the EOG. Results/comparison: Results show that standard signal processing tools such as wavelets and Fourier transforms perform much better when coupled with apt pre-processing techniques. The developed algorithm also relies on data-driven thresholds ensuring its adaptability to inter-subject and inter-scorer variability. When tested on sample EEG segments scored by multiple experts, the algorithm identified spindles with average sensitivities of 96.14 and 92.85% and specificities of 87.59 and 84.85% for Fourier transform and wavelets respectively. These results are found to be on par with results obtained by other recent studies in this area.

Original languageEnglish
Pages (from-to)1-12
Number of pages12
JournalJournal of Neuroscience Methods
Volume233
DOIs
Publication statusPublished - 15 Aug 2014

Fingerprint

Electroencephalography
Fourier Analysis
Electrooculography
Wavelet Analysis
Eye Movements

Keywords

  • Algorithms
  • EEG
  • EOG
  • Fourier transform
  • Spindle detection
  • Wavelets

ASJC Scopus subject areas

  • Neuroscience(all)

Cite this

Improved spindle detection through intuitive pre-processing of electroencephalogram. / Jaleel, Abdul; Ahmed, Beena; Tafreshi, Reza; Boivin, Diane B.; Streletz, Leopold; Haddad, Naim.

In: Journal of Neuroscience Methods, Vol. 233, 15.08.2014, p. 1-12.

Research output: Contribution to journalArticle

@article{670aedeacb23436f8c0dbc85f96820bc,
title = "Improved spindle detection through intuitive pre-processing of electroencephalogram",
abstract = "Background: Numerous signal processing techniques have been proposed for automated spindle detection on EEG recordings with varying degrees of success. While the latest techniques usually introduce computational complexity and/or vagueness, the conventional techniques attempted in literature have led to poor results. This study presents a spindle detection approach which relies on intuitive pre-processing of the EEG prior to spindle detection, thus resulting in higher accuracy even with standard techniques. New method: The pre-processing techniques proposed include applying the derivative operator on the EEG, suppressing the background activity using Empirical Mode Decomposition and shortlisting candidate EEG segments based on eye-movements on the EOG. Results/comparison: Results show that standard signal processing tools such as wavelets and Fourier transforms perform much better when coupled with apt pre-processing techniques. The developed algorithm also relies on data-driven thresholds ensuring its adaptability to inter-subject and inter-scorer variability. When tested on sample EEG segments scored by multiple experts, the algorithm identified spindles with average sensitivities of 96.14 and 92.85{\%} and specificities of 87.59 and 84.85{\%} for Fourier transform and wavelets respectively. These results are found to be on par with results obtained by other recent studies in this area.",
keywords = "Algorithms, EEG, EOG, Fourier transform, Spindle detection, Wavelets",
author = "Abdul Jaleel and Beena Ahmed and Reza Tafreshi and Boivin, {Diane B.} and Leopold Streletz and Naim Haddad",
year = "2014",
month = "8",
day = "15",
doi = "10.1016/j.jneumeth.2014.05.009",
language = "English",
volume = "233",
pages = "1--12",
journal = "Journal of Neuroscience Methods",
issn = "0165-0270",
publisher = "Elsevier",

}

TY - JOUR

T1 - Improved spindle detection through intuitive pre-processing of electroencephalogram

AU - Jaleel, Abdul

AU - Ahmed, Beena

AU - Tafreshi, Reza

AU - Boivin, Diane B.

AU - Streletz, Leopold

AU - Haddad, Naim

PY - 2014/8/15

Y1 - 2014/8/15

N2 - Background: Numerous signal processing techniques have been proposed for automated spindle detection on EEG recordings with varying degrees of success. While the latest techniques usually introduce computational complexity and/or vagueness, the conventional techniques attempted in literature have led to poor results. This study presents a spindle detection approach which relies on intuitive pre-processing of the EEG prior to spindle detection, thus resulting in higher accuracy even with standard techniques. New method: The pre-processing techniques proposed include applying the derivative operator on the EEG, suppressing the background activity using Empirical Mode Decomposition and shortlisting candidate EEG segments based on eye-movements on the EOG. Results/comparison: Results show that standard signal processing tools such as wavelets and Fourier transforms perform much better when coupled with apt pre-processing techniques. The developed algorithm also relies on data-driven thresholds ensuring its adaptability to inter-subject and inter-scorer variability. When tested on sample EEG segments scored by multiple experts, the algorithm identified spindles with average sensitivities of 96.14 and 92.85% and specificities of 87.59 and 84.85% for Fourier transform and wavelets respectively. These results are found to be on par with results obtained by other recent studies in this area.

AB - Background: Numerous signal processing techniques have been proposed for automated spindle detection on EEG recordings with varying degrees of success. While the latest techniques usually introduce computational complexity and/or vagueness, the conventional techniques attempted in literature have led to poor results. This study presents a spindle detection approach which relies on intuitive pre-processing of the EEG prior to spindle detection, thus resulting in higher accuracy even with standard techniques. New method: The pre-processing techniques proposed include applying the derivative operator on the EEG, suppressing the background activity using Empirical Mode Decomposition and shortlisting candidate EEG segments based on eye-movements on the EOG. Results/comparison: Results show that standard signal processing tools such as wavelets and Fourier transforms perform much better when coupled with apt pre-processing techniques. The developed algorithm also relies on data-driven thresholds ensuring its adaptability to inter-subject and inter-scorer variability. When tested on sample EEG segments scored by multiple experts, the algorithm identified spindles with average sensitivities of 96.14 and 92.85% and specificities of 87.59 and 84.85% for Fourier transform and wavelets respectively. These results are found to be on par with results obtained by other recent studies in this area.

KW - Algorithms

KW - EEG

KW - EOG

KW - Fourier transform

KW - Spindle detection

KW - Wavelets

UR - http://www.scopus.com/inward/record.url?scp=84902318306&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902318306&partnerID=8YFLogxK

U2 - 10.1016/j.jneumeth.2014.05.009

DO - 10.1016/j.jneumeth.2014.05.009

M3 - Article

C2 - 24887741

AN - SCOPUS:84902318306

VL - 233

SP - 1

EP - 12

JO - Journal of Neuroscience Methods

JF - Journal of Neuroscience Methods

SN - 0165-0270

ER -