Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

Exploiting Graphoelements and Convolutional Neural Networks with Long Short Term Memory for Classification of the Human Electroencephalogram

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

. 2019 ; 9 (1) : 11383. [pub] 20190806

Jazyk angličtina Země Velká Británie

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

Perzistentní odkaz   https://www.medvik.cz/link/bmc20028852

The electroencephalogram (EEG) is a cornerstone of neurophysiological research and clinical neurology. Historically, the classification of EEG as showing normal physiological or abnormal pathological activity has been performed by expert visual review. The potential value of unbiased, automated EEG classification has long been recognized, and in recent years the application of machine learning methods has received significant attention. A variety of solutions using convolutional neural networks (CNN) for EEG classification have emerged with impressive results. However, interpretation of CNN results and their connection with underlying basic electrophysiology has been unclear. This paper proposes a CNN architecture, which enables interpretation of intracranial EEG (iEEG) transients driving classification of brain activity as normal, pathological or artifactual. The goal is accomplished using CNN with long short-term memory (LSTM). We show that the method allows the visualization of iEEG graphoelements with the highest contribution to the final classification result using a classification heatmap and thus enables review of the raw iEEG data and interpret the decision of the model by electrophysiology means.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc20028852
003      
CZ-PrNML
005      
20210924103950.0
007      
ta
008      
210105s2019 xxk f 000 0|eng||
009      
AR
024    7_
$a 10.1038/s41598-019-47854-6 $2 doi
035    __
$a (PubMed)31388101
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxk
100    1_
$a Nejedly, P $u Mayo Systems Electrophysiology Laboratory, Department of Neurology, Mayo Clinic, Rochester, MN, 55905, USA. Nejedly.Petr@mayo.edu. The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic. Nejedly.Petr@mayo.edu. International Clinical Research Center, St. Anne's University Hospital Brno, Brno, Czech Republic. Nejedly.Petr@mayo.edu.
245    10
$a Exploiting Graphoelements and Convolutional Neural Networks with Long Short Term Memory for Classification of the Human Electroencephalogram / $c P. Nejedly, V. Kremen, V. Sladky, J. Cimbalnik, P. Klimes, F. Plesinger, I. Viscor, M. Pail, J. Halamek, BH. Brinkmann, M. Brazdil, P. Jurak, G. Worrell,
520    9_
$a The electroencephalogram (EEG) is a cornerstone of neurophysiological research and clinical neurology. Historically, the classification of EEG as showing normal physiological or abnormal pathological activity has been performed by expert visual review. The potential value of unbiased, automated EEG classification has long been recognized, and in recent years the application of machine learning methods has received significant attention. A variety of solutions using convolutional neural networks (CNN) for EEG classification have emerged with impressive results. However, interpretation of CNN results and their connection with underlying basic electrophysiology has been unclear. This paper proposes a CNN architecture, which enables interpretation of intracranial EEG (iEEG) transients driving classification of brain activity as normal, pathological or artifactual. The goal is accomplished using CNN with long short-term memory (LSTM). We show that the method allows the visualization of iEEG graphoelements with the highest contribution to the final classification result using a classification heatmap and thus enables review of the raw iEEG data and interpret the decision of the model by electrophysiology means.
650    _2
$a artefakty $7 D016477
650    _2
$a datové soubory jako téma $7 D066264
650    12
$a deep learning $7 D000077321
650    _2
$a elektroencefalografie $x klasifikace $x přístrojové vybavení $x metody $7 D004569
650    _2
$a lidé $7 D006801
650    _2
$a ROC křivka $7 D012372
655    _2
$a časopisecké články $7 D016428
655    _2
$a pozorovací studie $7 D064888
655    _2
$a Research Support, N.I.H., Extramural $7 D052061
655    _2
$a práce podpořená grantem $7 D013485
655    _2
$a validační studie $7 D023361
700    1_
$a Kremen, V $u Mayo Systems Electrophysiology Laboratory, Department of Neurology, Mayo Clinic, Rochester, MN, 55905, USA. Kremen.Vaclav@mayo.edu. Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, MN, 55905, USA. Kremen.Vaclav@mayo.edu. Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University in Prague, Prague, Czech Republic. Kremen.Vaclav@mayo.edu.
700    1_
$a Sladky, V $u Mayo Systems Electrophysiology Laboratory, Department of Neurology, Mayo Clinic, Rochester, MN, 55905, USA. International Clinical Research Center, St. Anne's University Hospital Brno, Brno, Czech Republic.
700    1_
$a Cimbalnik, J $u Mayo Systems Electrophysiology Laboratory, Department of Neurology, Mayo Clinic, Rochester, MN, 55905, USA. International Clinical Research Center, St. Anne's University Hospital Brno, Brno, Czech Republic.
700    1_
$a Klimes, P $u Mayo Systems Electrophysiology Laboratory, Department of Neurology, Mayo Clinic, Rochester, MN, 55905, USA. The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic. International Clinical Research Center, St. Anne's University Hospital Brno, Brno, Czech Republic.
700    1_
$a Plesinger, F $u The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic.
700    1_
$a Viscor, I $u The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic.
700    1_
$a Pail, Martin $u Department of Neurology, St. Anne's University Hospital, Brno, Czech Republic. $7 xx0264305
700    1_
$a Halamek, J $u The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic.
700    1_
$a Brinkmann, B H $u Mayo Systems Electrophysiology Laboratory, Department of Neurology, Mayo Clinic, Rochester, MN, 55905, USA. Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, MN, 55905, USA.
700    1_
$a Brazdil, M $u Department of Neurology, St. Anne's University Hospital, Brno, Czech Republic.
700    1_
$a Jurak, P $u The Czech Academy of Sciences, Institute of Scientific Instruments, Brno, Czech Republic.
700    1_
$a Worrell, G $u Mayo Systems Electrophysiology Laboratory, Department of Neurology, Mayo Clinic, Rochester, MN, 55905, USA. Worrell.Gregory@mayo.edu. Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, MN, 55905, USA. Worrell.Gregory@mayo.edu.
773    0_
$w MED00182195 $t Scientific reports $x 2045-2322 $g Roč. 9, č. 1 (2019), s. 11383
856    41
$u https://pubmed.ncbi.nlm.nih.gov/31388101 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y a $z 0
990    __
$a 20210105 $b ABA008
991    __
$a 20210924103948 $b ABA008
999    __
$a ok $b bmc $g 1609187 $s 1120032
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2019 $b 9 $c 1 $d 11383 $e 20190806 $i 2045-2322 $m Scientific reports $n Sci Rep $x MED00182195
LZP    __
$a Pubmed-20210105

Najít záznam

Citační ukazatele

Možnosti archivace