Abstract
Electroencephalogram (EEG) is one of the widely used non-invasive brain signal acquisition techniques that measure voltage fluctuations caused by neuron activities in the brain. EEG is typically used to diagnose and monitor disorders such as epilepsy, sleep disorders, and brain death and to help the advancement of various fields of science such as cognitive science and psychology. Unfortunately, EEGs usually suffer from a variety of artifacts, such as eye movements, chewing, muscle movements, and electrode pops. These artifacts disrupt the diagnosis and hinder the precise representation of brain activities.
In this chapter, we will introduce and evaluate three deep learning methods and an ensemble method to detect the presence of artifacts and to classify the types of artifacts to help clinicians resolve problems regarding artifacts immediately during the signal collection process. Models were optimized to map the 1-second segments of raw EEG signals to detect four different kinds of artifacts. Among all the models, the best model is an ensemble model, which achieves five-class classification accuracy of 67.59% and a true positive rate of 80% with 25.82% false alarm for binary classification with time-lapse. The model is lightweight and can be easily deployed in portable machines.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
M. Aminoff, Principles of neural science. 4th edition. Muscle Nerve 24(6), 839–839 (2001)
W. Clercq, A. Vergult, B. Vanrumste, W. Paesschen, S. Huffel, Canonical correlation analysis applied to remove muscle artifacts from the electroencephalogram. IEEE Trans. Biomed. Eng. 53(12), 2583–2587 (2006)
J. DellaBadia, W. Bell, J. Keyes, V. Mathews, S. Glazier, Assessment and cost comparison of sleep-deprived EEG, MRI and PET in the prediction of surgical treatment for epilepsy. Seizure-Eur. J. Epilepsy 11(5), 303–309 (2002)
M. Golmohammadi, A. Torbati, S. Diego, I. Obeid, J. Picone, Automatic analysis of EEGs using big data and hybrid deep learning architectures. Front. Hum. Neurosci. 13 (2019)
I. Goodfellow, Y. Bengio, A. Courville, Deep Learning (MIT Press, 2016)
D. Hand, R. Till, A simple generalisation of the area under the ROC curve for multiple class classification problems. Mach. Learn. 45(2), 171–186 (2001) Retrieved from https://academic.microsoft.com/paper/1912982817
A. Hasasneh, N. Kampel, P. Sripad, N. Shah, J. Dammers, Deep learning approach for automatic classification of ocular and cardiac artifacts in MEG data. J. Eng. 2018, 1–10 (2018)
S. Hochreiter, J. Schmidhuber, Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
S. Ioffe, C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift. International conference on machine learning, 448–456 (2015)
D. Kingma, J. Ba, Adam: A Method for Stochastic Optimization (International conference on learning representations, 2015)
V. Krishnaveni, S. Jayaraman, A. Gunasekaran, K. Ramadoss, Automatic removal of ocular artifacts using JADE algorithm and neural network. International Journal of Computer and Information. Engineering 2(4), 1330–1341 (2007)
T.-W. Lee, M. Girolami, T. Sejnowski, Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources. Neural Comput. 11(2), 417–441 (1999)
S. Lopez, A. Gross, S. Yang, M. Golmohammadi, I. Obeid, J. Picone, An analysis of two common reference points for EEGS, in 2016 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), 2016, (2016), pp. 1–5. Retrieved from https://academic.microsoft.com/paper/2586273059
E. Louis, Frey, L., Britton, J., Hopp, J., Korb, P., Koubeissi, M., … Pestana-Knight, E. Electroencephalography (EEG): An Introductory Text and Atlas of Normal and Abnormal Findings in Adults, Children, and Infants (2016)
H. Nolan, R. Whelan, R. Reilly, FASTER: Fully automated statistical thresholding for EEG artifact rejection. J. Neurosci. Methods 192(1), 152–162 (2010)
I. Obeid, J. Picone, The Temple University Hospital EEG data corpus. Front. Neurosci. 10, 196 (2016). https://doi.org/10.3389/fnins.2016.00196
M. Richards. Fundamentals of Radar Signal Processing (2005)
Y. Roy, H. Banville, I. Albuquerque, A. Gramfort, T. Falk, J. Faubert, Deep learning-based electroencephalography analysis: a systematic review. arXiv preprint arXiv 1901.05498 (2019)
B. Singh, H. Wagatsuma, A removal of eye movement and blink artifacts from EEG data using morphological component analysis. Comput. Math. Methods Med. 2017, 1861645 (2017)
M. Zweig, G. Campbell, Receiver-operating characteristic (ROC) plots: A fundamental evaluation tool in clinical medicine. Clin. Chem. 39(4), 561–577 (1993)
Acknowledgments
We would like to thank the Department of Electrical Engineering at The Cooper Union and Temple University Hospital for supporting this research by providing us the necessary resources.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Kim, D.K., Keene, S. (2021). Fast Automatic Artifact Annotator for EEG Signals Using Deep Learning. In: Obeid, I., Selesnick, I., Picone, J. (eds) Biomedical Signal Processing. Springer, Cham. https://doi.org/10.1007/978-3-030-67494-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-67494-6_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-67493-9
Online ISBN: 978-3-030-67494-6
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)