Meet Spinky: An Open-Source Spindle and K-Complex Detection Toolbox Validated on the Open-Access Montreal Archive of Sleep Studies (MASS)

被引:18
作者
Lajnef, Tarek [1 ,2 ]
O'Reilly, Christian [3 ]
Combrisson, Etienne [1 ,4 ,5 ]
Chaibi, Sahbi [6 ]
Eichenlaub, Jean-Baptiste [7 ]
Ruby, Perrine M. [5 ]
Aguera, Pierre-Emmanuel [5 ]
Samet, Mounir [6 ]
Kachouri, Abdennaceur [6 ]
Frenette, Sonia [2 ]
Carrier, Julie [1 ,2 ]
Jerbi, Karim [1 ,8 ,9 ,10 ]
机构
[1] Univ Montreal, Dept Psychol, Montreal, PQ, Canada
[2] Hop Sacre Coeur, Ctr Adv Res Sleep Med, Montreal, PQ, Canada
[3] Ecole Polytech Fed Lausanne, Blue Brain Project, Geneva, Switzerland
[4] Univ Claude Bernard Lyon 1, Interuniv Lab Human Movement Biol, Villeurbanne, France
[5] Univ Lyon 1, Lyon Neurosci Res Ctr, DYCOG Lab, INSERM U1028,UMR 5292, Lyon, France
[6] Univ Sfax, LETI Lab Sfax, Natl Engn Sch ENIS, Sfax, Tunisia
[7] Harvard Med Sch, Dept Neurol, Massachusetts Gen Hosp, Boston, MA USA
[8] CRIUGM, Montreal, PQ, Canada
[9] Univ Montreal, Dept Psychol, Ctr Rech Neuropsychol & Cognit CERNEC, Montreal, PQ, Canada
[10] Int Lab Res Brain Mus & Sound, BRAMS, Montreal, PQ, Canada
来源
FRONTIERS IN NEUROINFORMATICS | 2017年 / 11卷
基金
加拿大自然科学与工程研究理事会;
关键词
spindles; K-complex; automatic detection; sleep-EEG; spinky; open-source; toolbox; TQWT; SUPPORT VECTOR MACHINES; EYE-MOVEMENT SLEEP; AUTOMATIC DETECTION; PARKINSONS-DISEASE; WAVELET TRANSFORM; MOTOR SEQUENCE; DECISION-TREE; EEG; SLOW; BENCHMARKING;
D O I
10.3389/fninf.2017.00015
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Sleep spindles and K-complexes are among the most prominent micro-events observed in electroencephalographic (EEG) recordings during sleep. These EEG microstructures are thought to be hallmarks of sleep-related cognitive processes. Although tedious and time-consuming, their identification and quantification is important for sleep studies in both healthy subjects and patients with sleep disorders. Therefore, procedures for automatic detection of spindles and K-complexes could provide valuable assistance to researchers and clinicians in the field. Recently, we proposed a framework for joint spindle and K-complex detection (Lajnef et al., 2015a) based on a Tunable Q-factor Wavelet Transform (TQWT; Selesnick, 2011a) and morphological component analysis (MCA). Using a wide range of performance metrics, the present article provides critical validation and benchmarking of the proposed approach by applying it to open-access EEG data from the Montreal Archive of Sleep Studies (MASS; O'Reilly et al., 2014). Importantly, the obtained scores were compared to alternative methods that were previously tested on the same database. With respect to spindle detection, our method achieved higher performance than most of the alternative methods. This was corroborated with statistic tests that took into account both sensitivity and precision (i. e., Matthew's coefficient of correlation (MCC), F1, Cohen k). Our proposed method has been made available to the community via an open-source tool named Spinky (for spindle and K-complex detection). Thanks to a GUI implementation and access to Matlab and Python resources, Spinky is expected to contribute to an open-science approach that will enhance replicability and reliable comparisons of classifier performances for the detection of sleep EEG microstructure in both healthy and patient populations.
引用
收藏
页数:13
相关论文
共 59 条
[41]   Automatic sleep spindle detection: benchmarking with fine temporal resolution using open science tools [J].
O'Reilly, Christian ;
Nielsen, Tore .
FRONTIERS IN HUMAN NEUROSCIENCE, 2015, 9
[42]   Montreal Archive of Sleep Studies: an open-access resource for instrument benchmarking and exploratory research [J].
O'Reilly, Christian ;
Gosselin, Nadia ;
Carrier, Julie ;
Nielsen, Tore .
JOURNAL OF SLEEP RESEARCH, 2014, 23 (06) :628-635
[43]   Detection of K-complexes and sleep spindles (DETOKS) using sparse optimization [J].
Parekh, Ankit ;
Selesnick, Ivan W. ;
Rapoport, David M. ;
Ayappa, Indu .
JOURNAL OF NEUROSCIENCE METHODS, 2015, 251 :37-46
[44]  
Patti C. R., 2015, IEEE BIOM CIRC SYST, P1
[45]   Expert and crowd-sourced validation of an individualized sleep spindle detection method employing complex demodulation and individualized normalization [J].
Ray, Laura B. ;
Sockeel, Stephane ;
Soon, Melissa ;
Bore, Arnaud ;
Myhr, Ayako ;
Stojanoski, Bobby ;
Cusack, Rhodri ;
Owen, Adrian M. ;
Doyon, Julien ;
Fogel, Stuart M. .
FRONTIERS IN HUMAN NEUROSCIENCE, 2015, 9
[46]   Validating an automated sleep spindle detection algorithm using an individualized approach [J].
Ray, Laura B. ;
Fogel, Stuart M. ;
Smith, Carlyle T. ;
Peters, Kevin R. .
JOURNAL OF SLEEP RESEARCH, 2010, 19 (02) :374-378
[47]  
Rechtschaffen A., 1968, MANUAL STANDARDIZED
[48]   Sleep and depression - results from psychobiological studies: an overview [J].
Riemann, D ;
Berger, M ;
Voderholzer, U .
BIOLOGICAL PSYCHOLOGY, 2001, 57 (1-3) :67-103
[49]   Sleep spindles and their significance for declarative memory consolidation [J].
Schabus, M ;
Gruber, G ;
Parapatics, S ;
Sauter, C ;
Klosch, G ;
Anderer, P ;
Klimesch, W ;
Saletu, B ;
Zeitlhofer, J .
SLEEP, 2004, 27 (08) :1479-1485
[50]   Benchmarking matching pursuit to find sleep spindles [J].
Schonwald, Suzana V. ;
de Santa-Helena, Emerson L. ;
Rossatto, Roberto ;
Chaves, Marcia L. F. ;
Gerhardt, Gunther J. L. .
JOURNAL OF NEUROSCIENCE METHODS, 2006, 156 (1-2) :314-321