Combining time-frequency and spatial information for the detection of sleep spindles

O’Reilly, C., Godbout, J., Carrier, J. et Lina, Jean-Marc. 2015. « Combining time-frequency and spatial information for the detection of sleep spindles ». Frontiers in Human Neuroscience, vol. 9.
Compte des citations dans Scopus : 15.

Prévisualisation

PDF Lina J-M 2015 9394.pdf - Version publiée Licence d'utilisation : Creative Commons CC BY. Télécharger (8MB) | Prévisualisation

Résumé

EEG sleep spindles are short (0.5–2.0 s) bursts of activity in the 11–16 Hz band occurring during non-rapid eye movement (NREM) sleep. This sporadic activity is thought to play a role in memory consolidation, brain plasticity, and protection of sleep integrity. Many automatic detectors have been proposed to assist or replace experts for sleep spindle scoring. However, these algorithms usually detect too many events making it difficult to achieve a good tradeoff between sensitivity (Se) and false detection rate (FDr). In this work, we propose a semi-automatic detector comprising a sensitivity phase based on well-established criteria followed by a specificity phase using spatial and spectral criteria. In the sensitivity phase, selected events are those which amplitude in the 10–16 Hz band and spectral ratio characteristics both reject a null hypothesis (p < 0.1) stating that the considered event is not a spindle. This null hypothesis is constructed from events occurring during rapid eye movement (REM) sleep epochs. In the specificity phase, a hierarchical clustering of the selected candidates is done based on events’ frequency and spatial position along the anterior-posterior axis. Only events from the classes grouping most (at least 80%) spindles scored by an expert are kept. We obtain Se = 93.2% and FDr = 93.0% in the first phase and Se = 85.4% and FDr = 86.2% in the second phase. For these two phases, Matthew’s correlation coefficients are respectively 0.228 and 0.324. Results suggest that spindles are defined by specific spatio-spectral properties and that automatic detection methods can be improved by considering these features.

Type de document:	Article publié dans une revue, révisé par les pairs
Informations complémentaires:	Identifiant de l'article: 70
Professeur:	Professeur Lina, Jean-Marc
Affiliation:	Génie électrique
Date de dépôt:	17 mars 2015 16:06
Dernière modification:	19 oct. 2020 18:41
URI:	https://espace2.etsmtl.ca/id/eprint/9394

Actions (Authentification requise)

Dernière vérification avant le dépôt