Intracerebral EEG Artifact Identification Using Convolutional Neural Networks

0507970 - ÚPT 2020 RIV US eng J - Článek v odborném periodiku
Nejedlý, Petr - Cimbálník, J. - Klimeš, Petr - Plešinger, Filip - Halámek, Josef - Křemen, V. - Viščor, Ivo - Brinkmann, B. - Pail, M. - Brázdil, M. - Worell, G. - Jurák, Pavel
Intracerebral EEG Artifact Identification Using Convolutional Neural Networks.
Neuroinformatics. Roč. 17, č. 2 (2019), s. 225-234. ISSN 1539-2791. E-ISSN 1559-0089
Grant CEP: GA MZd(CZ) NV16-33798A; GA MŠMT(CZ) LO1212; GA ČR GAP103/11/0933
Institucionální podpora: RVO:68081731
Klíčová slova: intracranial EEG (iEEG) * noise detection * convolutional neural networks (CNN) * artifact probability matrix (APM)
Obor OECD: Medical engineering
Impakt faktor: 3.300, rok: 2019
Způsob publikování: Omezený přístup
https://link.springer.com/article/10.1007%2Fs12021-018-9397-6

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.
Trvalý link: http://hdl.handle.net/11104/0298935