• Je něco špatně v tomto záznamu ?

Intracerebral EEG Artifact Identification Using Convolutional Neural Networks

P. Nejedly, J. Cimbalnik, P. Klimes, F. Plesinger, J. Halamek, V. Kremen, I. Viscor, BH. Brinkmann, M. Pail, M. Brazdil, G. Worrell, P. Jurak,

. 2019 ; 17 (2) : 225-234. [pub] -

Jazyk angličtina Země Spojené státy americké

Typ dokumentu časopisecké články, Research Support, N.I.H., Extramural, práce podpořená grantem

Perzistentní odkaz   https://www.medvik.cz/link/bmc19035073

Grantová podpora
16-33798A AZV CR - International
LO1212 MEYS CR - International
LQ1605 MEYS CR - International
UH2-NS095495 NIH HHS - United States
R01-NS063039 NIH HHS - United States
P103/11/0933), Grantová Agentura České Republiky - International
CZ.1.05/ 1.1.00/02.0123 European Regional Development Fund - International
NV16-33798A MZ0 CEP - Centrální evidence projektů

Digitální knihovna NLK
Plný text - Článek

E-zdroje Online Plný text

NLK ProQuest Central od 2003-03-01 do Před 1 rokem
Health & Medicine (ProQuest) od 2003-03-01 do Před 1 rokem
Psychology Database (ProQuest) od 2003-03-01 do Před 1 rokem

Odkazy

PubMed 30105544
DOI 10.1007/s12021-018-9397-6
Knihovny.cz E-zdroje

Manual and semi-automatic identification of artifacts and unwanted physiological signals in large intracerebral electroencephalographic (iEEG) recordings is time consuming and inaccurate. To date, unsupervised methods to accurately detect iEEG artifacts are not available. This study introduces a novel machine-learning approach for detection of artifacts in iEEG signals in clinically controlled conditions using convolutional neural networks (CNN) and benchmarks the method's performance against expert annotations. The method was trained and tested on data obtained from St Anne's University Hospital (Brno, Czech Republic) and validated on data from Mayo Clinic (Rochester, Minnesota, U.S.A). We show that the proposed technique can be used as a generalized model for iEEG artifact detection. Moreover, a transfer learning process might be used for retraining of the generalized version to form a data-specific model. The generalized model can be efficiently retrained for use with different EEG acquisition systems and noise environments. The generalized and specialized model F1 scores on the testing dataset were 0.81 and 0.96, respectively. The CNN model provides faster, more objective, and more reproducible iEEG artifact detection compared to manual approaches.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc19035073
003      
CZ-PrNML
005      
20210924104538.0
007      
ta
008      
191007s2019 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1007/s12021-018-9397-6 $2 doi
035    __
$a (PubMed)30105544
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Nejedly, Petr $u International Clinical Research Center, St. Anne's University Hospital, Brno, Czech Republic. nejedly@isibrno.cz. The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic. nejedly@isibrno.cz. Department of Neurology, Mayo Clinic, Mayo Systems Electrophysiology Laboratory, Rochester, MN, USA. nejedly@isibrno.cz.
245    10
$a Intracerebral EEG Artifact Identification Using Convolutional Neural Networks / $c P. Nejedly, J. Cimbalnik, P. Klimes, F. Plesinger, J. Halamek, V. Kremen, I. Viscor, BH. Brinkmann, M. Pail, M. Brazdil, G. Worrell, P. Jurak,
520    9_
$a Manual and semi-automatic identification of artifacts and unwanted physiological signals in large intracerebral electroencephalographic (iEEG) recordings is time consuming and inaccurate. To date, unsupervised methods to accurately detect iEEG artifacts are not available. This study introduces a novel machine-learning approach for detection of artifacts in iEEG signals in clinically controlled conditions using convolutional neural networks (CNN) and benchmarks the method's performance against expert annotations. The method was trained and tested on data obtained from St Anne's University Hospital (Brno, Czech Republic) and validated on data from Mayo Clinic (Rochester, Minnesota, U.S.A). We show that the proposed technique can be used as a generalized model for iEEG artifact detection. Moreover, a transfer learning process might be used for retraining of the generalized version to form a data-specific model. The generalized model can be efficiently retrained for use with different EEG acquisition systems and noise environments. The generalized and specialized model F1 scores on the testing dataset were 0.81 and 0.96, respectively. The CNN model provides faster, more objective, and more reproducible iEEG artifact detection compared to manual approaches.
650    12
$a artefakty $7 D016477
650    _2
$a mozek $x fyziologie $7 D001921
650    _2
$a elektroencefalografie $x metody $7 D004569
650    _2
$a lidé $7 D006801
650    12
$a strojové učení $7 D000069550
650    12
$a neuronové sítě (počítačové) $7 D016571
650    _2
$a retrospektivní studie $7 D012189
655    _2
$a časopisecké články $7 D016428
655    _2
$a Research Support, N.I.H., Extramural $7 D052061
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Cimbalnik, Jan $u International Clinical Research Center, St. Anne's University Hospital, Brno, Czech Republic.
700    1_
$a Klimes, Petr $u International Clinical Research Center, St. Anne's University Hospital, Brno, Czech Republic. The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic.
700    1_
$a Plesinger, Filip $u The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic.
700    1_
$a Halamek, Josef $u The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic.
700    1_
$a Kremen, Vaclav $u Department of Neurology, Mayo Clinic, Mayo Systems Electrophysiology Laboratory, Rochester, MN, USA. Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, MN, USA.
700    1_
$a Viscor, Ivo $u The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic.
700    1_
$a Brinkmann, Benjamin H $u Department of Neurology, Mayo Clinic, Mayo Systems Electrophysiology Laboratory, Rochester, MN, USA. Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, MN, USA.
700    1_
$a Pail, Martin $u Brno Epilepsy Center, Department of Neurology, St. Anne's University Hospital and Medical Faculty of Masaryk University, Brno, Czech Republic. $7 xx0264305
700    1_
$a Brazdil, Milan $u Brno Epilepsy Center, Department of Neurology, St. Anne's University Hospital and Medical Faculty of Masaryk University, Brno, Czech Republic. CEITEC - Central European Institute of Technology, Masaryk University, Brno, Czech Republic.
700    1_
$a Worrell, Gregory $u Department of Neurology, Mayo Clinic, Mayo Systems Electrophysiology Laboratory, Rochester, MN, USA. Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, MN, USA.
700    1_
$a Jurak, Pavel $u The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic.
773    0_
$w MED00200656 $t Neuroinformatics $x 1559-0089 $g Roč. 17, č. 2 (2019), s. 225-234
856    41
$u https://pubmed.ncbi.nlm.nih.gov/30105544 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y a $z 0
990    __
$a 20191007 $b ABA008
991    __
$a 20210924104537 $b ABA008
999    __
$a ok $b bmc $g 1451733 $s 1073623
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2019 $b 17 $c 2 $d 225-234 $e - $i 1559-0089 $m Neuroinformatics $n Neuroinformatics $x MED00200656
GRA    __
$a 16-33798A $p AZV CR $2 International
GRA    __
$a LO1212 $p MEYS CR $2 International
GRA    __
$a LQ1605 $p MEYS CR $2 International
GRA    __
$a UH2-NS095495 $p NIH HHS $2 United States
GRA    __
$a R01-NS063039 $p NIH HHS $2 United States
GRA    __
$a P103/11/0933), $p Grantová Agentura České Republiky $2 International
GRA    __
$a CZ.1.05/ 1.1.00/02.0123 $p European Regional Development Fund $2 International
GRA    __
$a NV16-33798A $p MZ0
LZP    __
$a Pubmed-20191007

Najít záznam

Citační ukazatele

Možnosti archivace