Automatic detection of artifacts in EEG by combining deep learning and histogram contour processing

This paper introduces a simple approach combining deep learning and histogram contour processing for automatic detection of various types of artifact contaminating the raw electroencephalogram (EEG). The proposed method considers both spatial and temporal information of raw EEG, without additional need for reference signals like ECG or EOG. The proposed method was evaluated with data including 785 EEG sequences contaminated by artifacts and 785 artifact-free EEG sequences collected from 15 intensive care patients. The obtained results showed an overall accuracy of 0.98, representing high reliability of proposed technique in detecting different types of artifacts and being comparable or outperforming the approaches proposed earlier in the literature.

Authors:
Bahador Nooshin, Erikson Kristo, Laurila Jouko, Koskenkari Juha, Ala-Kokko Tero, Kortelainen Jukka

Publication type:
A4 Article in conference proceedings

Place of publication:
Bi42nd Annual International Conferences of the IEEE Engineering in Medicine and ology Society, EMBC 2020, 20-24 July 2020, Montreal, QC, Canada

Keywords:
Brain modeling, Electrodes, Electroencephalography, Histograms, Machine learning, Signal analysis, Training

Published:

Full citation:
N. Bahador, K. Erikson, J. Laurila, J. Koskenkari, T. Ala-Kokko and J. Kortelainen, “Automatic detection of artifacts in EEG by combining deep learning and histogram contour processing,” 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada, 2020, pp. 138-141, doi: 10.1109/EMBC44109.2020.9175711

DOI:
https://doi.org/10.1109/EMBC44109.2020.9175711

Read the publication here:
http://urn.fi/urn:nbn:fi-fe2020112092122