Paper published in a journal (Scientific congresses and symposiums)
Deep neural networks for automatic classification of anesthetic-induced unconsciousness
Patlatzoglou, K.; Chennu, S.; Boly, Mélanie et al.
2018In Lecture Notes in Computer Science, 11309 LNAI, p. 216-225
Peer reviewed


Full Text
Publisher postprint (639.42 kB)

All documents in ORBi are protected by a user license.

Send to


Keywords :
Anesthesia; Consciousness; Deep learning; EEG; Anesthetics; Brain; Convolution; Electroencephalography; Multilayer neural networks; Spectral density; Automatic classification; Automatic extraction; Convolutional networks; Convolutional neural network; Cross validation; Discrimination accuracy; Deep neural networks
Abstract :
[en] Despite the common use of anesthetics to modulate consciousness in the clinic, brain-based monitoring of consciousness is uncommon. We combined electroencephalographic measurement of brain activity with deep neural networks to automatically discriminate anesthetic states induced by propofol. Our results with leave-one-participant-out-cross-validation show that convolutional neural networks significantly outperform multilayer perceptrons in discrimination accuracy when working with raw time series. Perceptrons achieved comparable accuracy when provided with power spectral densities. These findings highlight the potential of deep convolutional networks for completely automatic extraction of useful spatio-temporo-spectral features from human EEG. © 2018, Springer Nature Switzerland AG.
Disciplines :
Neurosciences & behavior
Author, co-author :
Patlatzoglou, K.;  University of Kent Chatham Maritime, Kent, United Kingdom
Chennu, S.;  University of Kent Chatham Maritime, Kent, United Kingdom, University of Cambridge, Cambridge, United Kingdom
Boly, Mélanie;  Department of Neurology and Department of Psychiatry, University of Wisconsin, Madison, WI, United States
Noirhomme, Quentin ;  Université de Liège - ULiège > GIGA CRC In vivo Imaging
BONHOMME, Vincent  ;  Centre Hospitalier Universitaire de Liège - CHU > Département d'Anesthésie et réanimation > Service d'anesthésie - réanimation
Brichant, Jean-François ;  Université de Liège - ULiège > Département des sciences cliniques > Anesthésie et réanimation
Gosseries, Olivia  ;  Université de Liège - ULiège > Consciousness-Coma Science Group
Laureys, Steven  ;  Université de Liège - ULiège > Consciousness-Coma Science Group
Language :
Title :
Deep neural networks for automatic classification of anesthetic-induced unconsciousness
Publication date :
Event name :
International Conference on Brain Informatics, BI 2018
Event date :
7 December 2018 through 9 December 2018
Journal title :
Lecture Notes in Computer Science
Publisher :
Springer Verlag
Volume :
11309 LNAI
Pages :
Peer reviewed :
Peer reviewed
Available on ORBi :
since 23 September 2019


Number of views
77 (5 by ULiège)
Number of downloads
70 (1 by ULiège)

Scopus citations®
Scopus citations®
without self-citations


Similar publications

Contact ORBi