TY - JOUR
T1 - Multicenter intracranial EEG dataset for classification of graphoelements and artifactual signals
AU - Nejedly, Petr
AU - Kremen, Vaclav
AU - Sladky, Vladimir
AU - Cimbalnik, Jan
AU - Klimes, Petr
AU - Plesinger, Filip
AU - Mivalt, Filip
AU - Travnicek, Vojtech
AU - Viscor, Ivo
AU - Pail, Martin
AU - Halamek, Josef
AU - Brinkmann, Benjamin H.
AU - Brazdil, Milan
AU - Jurak, Pavel
AU - Worrell, Gregory
N1 - Publisher Copyright:
© 2020, The Author(s).
PY - 2020/12/1
Y1 - 2020/12/1
N2 - EEG signal processing is a fundamental method for neurophysiology research and clinical neurology practice. Historically the classification of EEG into physiological, pathological, or artifacts has been performed by expert visual review of the recordings. However, the size of EEG data recordings is rapidly increasing with a trend for higher channel counts, greater sampling frequency, and longer recording duration and complete reliance on visual data review is not sustainable. In this study, we publicly share annotated intracranial EEG data clips from two institutions: Mayo Clinic, MN, USA and St. Anne’s University Hospital Brno, Czech Republic. The dataset contains intracranial EEG that are labeled into three groups: physiological activity, pathological/epileptic activity, and artifactual signals. The dataset published here should support and facilitate training of generalized machine learning and digital signal processing methods for intracranial EEG and promote research reproducibility. Along with the data, we also propose a statistical method that is recommended for comparison of candidate classifier performance utilizing out-of-institution/out-of-patient testing.
AB - EEG signal processing is a fundamental method for neurophysiology research and clinical neurology practice. Historically the classification of EEG into physiological, pathological, or artifacts has been performed by expert visual review of the recordings. However, the size of EEG data recordings is rapidly increasing with a trend for higher channel counts, greater sampling frequency, and longer recording duration and complete reliance on visual data review is not sustainable. In this study, we publicly share annotated intracranial EEG data clips from two institutions: Mayo Clinic, MN, USA and St. Anne’s University Hospital Brno, Czech Republic. The dataset contains intracranial EEG that are labeled into three groups: physiological activity, pathological/epileptic activity, and artifactual signals. The dataset published here should support and facilitate training of generalized machine learning and digital signal processing methods for intracranial EEG and promote research reproducibility. Along with the data, we also propose a statistical method that is recommended for comparison of candidate classifier performance utilizing out-of-institution/out-of-patient testing.
UR - http://www.scopus.com/inward/record.url?scp=85086581620&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85086581620&partnerID=8YFLogxK
U2 - 10.1038/s41597-020-0532-5
DO - 10.1038/s41597-020-0532-5
M3 - Article
C2 - 32546753
AN - SCOPUS:85086581620
SN - 2052-4463
VL - 7
JO - Scientific Data
JF - Scientific Data
IS - 1
M1 - 179
ER -