Enhanced automated sleep spindle detection algorithm based on synchrosqueezing

Muammar M. Kabir, Reza Tafreshi, Diane B. Boivin, Naim Haddad

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Detection of sleep spindles is of major importance in the field of sleep research. However, manual scoring of spindles on prolonged recordings is very laborious and time-consuming. In this paper, we introduce a new algorithm based on synchrosqueezing transform for detection of sleep spindles. Synchrosqueezing is a powerful time–frequency analysis tool that provides precise frequency representation of a multicomponent signal through mode decomposition. Subsequently, the proposed algorithm extracts and compares the basic features of a spindle-like activity with its surrounding, thus adapting to an expert’s visual criteria for spindle scoring. The performance of the algorithm was assessed against the spindle scoring of one expert on continuous electroencephalogram sleep recordings from two subjects. Through appropriate choice of synchrosqueezing parameters, our proposed algorithm obtained a maximum sensitivity of 96.5 % with 98.1 % specificity. Compared to previously published works, our algorithm has shown improved performance by enhancing the quality of sleep spindle detection.

Original languageEnglish
Article number6
Pages (from-to)635-644
Number of pages10
JournalMedical and Biological Engineering and Computing
Volume53
Issue number7
DOIs
Publication statusPublished - 22 Jul 2015

Fingerprint

Sleep research
Electroencephalography
Sleep
Decomposition

Keywords

  • Electroencephalogram
  • Sleep
  • Spindles
  • Synchrosqueezing

ASJC Scopus subject areas

  • Biomedical Engineering
  • Computer Science Applications

Cite this

Enhanced automated sleep spindle detection algorithm based on synchrosqueezing. / Kabir, Muammar M.; Tafreshi, Reza; Boivin, Diane B.; Haddad, Naim.

In: Medical and Biological Engineering and Computing, Vol. 53, No. 7, 6, 22.07.2015, p. 635-644.

Research output: Contribution to journalArticle

Kabir, Muammar M. ; Tafreshi, Reza ; Boivin, Diane B. ; Haddad, Naim. / Enhanced automated sleep spindle detection algorithm based on synchrosqueezing. In: Medical and Biological Engineering and Computing. 2015 ; Vol. 53, No. 7. pp. 635-644.
@article{790588eec88043c6b33cd593130391a8,
title = "Enhanced automated sleep spindle detection algorithm based on synchrosqueezing",
abstract = "Detection of sleep spindles is of major importance in the field of sleep research. However, manual scoring of spindles on prolonged recordings is very laborious and time-consuming. In this paper, we introduce a new algorithm based on synchrosqueezing transform for detection of sleep spindles. Synchrosqueezing is a powerful time–frequency analysis tool that provides precise frequency representation of a multicomponent signal through mode decomposition. Subsequently, the proposed algorithm extracts and compares the basic features of a spindle-like activity with its surrounding, thus adapting to an expert’s visual criteria for spindle scoring. The performance of the algorithm was assessed against the spindle scoring of one expert on continuous electroencephalogram sleep recordings from two subjects. Through appropriate choice of synchrosqueezing parameters, our proposed algorithm obtained a maximum sensitivity of 96.5 {\%} with 98.1 {\%} specificity. Compared to previously published works, our algorithm has shown improved performance by enhancing the quality of sleep spindle detection.",
keywords = "Electroencephalogram, Sleep, Spindles, Synchrosqueezing",
author = "Kabir, {Muammar M.} and Reza Tafreshi and Boivin, {Diane B.} and Naim Haddad",
year = "2015",
month = "7",
day = "22",
doi = "10.1007/s11517-015-1265-z",
language = "English",
volume = "53",
pages = "635--644",
journal = "Medical and Biological Engineering and Computing",
issn = "0140-0118",
publisher = "Springer Verlag",
number = "7",

}

TY - JOUR

T1 - Enhanced automated sleep spindle detection algorithm based on synchrosqueezing

AU - Kabir, Muammar M.

AU - Tafreshi, Reza

AU - Boivin, Diane B.

AU - Haddad, Naim

PY - 2015/7/22

Y1 - 2015/7/22

N2 - Detection of sleep spindles is of major importance in the field of sleep research. However, manual scoring of spindles on prolonged recordings is very laborious and time-consuming. In this paper, we introduce a new algorithm based on synchrosqueezing transform for detection of sleep spindles. Synchrosqueezing is a powerful time–frequency analysis tool that provides precise frequency representation of a multicomponent signal through mode decomposition. Subsequently, the proposed algorithm extracts and compares the basic features of a spindle-like activity with its surrounding, thus adapting to an expert’s visual criteria for spindle scoring. The performance of the algorithm was assessed against the spindle scoring of one expert on continuous electroencephalogram sleep recordings from two subjects. Through appropriate choice of synchrosqueezing parameters, our proposed algorithm obtained a maximum sensitivity of 96.5 % with 98.1 % specificity. Compared to previously published works, our algorithm has shown improved performance by enhancing the quality of sleep spindle detection.

AB - Detection of sleep spindles is of major importance in the field of sleep research. However, manual scoring of spindles on prolonged recordings is very laborious and time-consuming. In this paper, we introduce a new algorithm based on synchrosqueezing transform for detection of sleep spindles. Synchrosqueezing is a powerful time–frequency analysis tool that provides precise frequency representation of a multicomponent signal through mode decomposition. Subsequently, the proposed algorithm extracts and compares the basic features of a spindle-like activity with its surrounding, thus adapting to an expert’s visual criteria for spindle scoring. The performance of the algorithm was assessed against the spindle scoring of one expert on continuous electroencephalogram sleep recordings from two subjects. Through appropriate choice of synchrosqueezing parameters, our proposed algorithm obtained a maximum sensitivity of 96.5 % with 98.1 % specificity. Compared to previously published works, our algorithm has shown improved performance by enhancing the quality of sleep spindle detection.

KW - Electroencephalogram

KW - Sleep

KW - Spindles

KW - Synchrosqueezing

UR - http://www.scopus.com/inward/record.url?scp=84939972918&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939972918&partnerID=8YFLogxK

U2 - 10.1007/s11517-015-1265-z

DO - 10.1007/s11517-015-1265-z

M3 - Article

VL - 53

SP - 635

EP - 644

JO - Medical and Biological Engineering and Computing

JF - Medical and Biological Engineering and Computing

SN - 0140-0118

IS - 7

M1 - 6

ER -