Transfer Learning of EEG for Analysis of Interictal Epileptiform Discharges. / Cheong Took, Clive; Alty, Stephen; Martin-Lopez, David; Valentin, Antonio; Alarcon, Gonzalo; Sanei, Saeid.

International Conference on e-Health and Bioengineering. IEEE, 2021.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Published

Standard

Transfer Learning of EEG for Analysis of Interictal Epileptiform Discharges. / Cheong Took, Clive; Alty, Stephen; Martin-Lopez, David; Valentin, Antonio; Alarcon, Gonzalo; Sanei, Saeid.

International Conference on e-Health and Bioengineering. IEEE, 2021.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Harvard

Cheong Took, C, Alty, S, Martin-Lopez, D, Valentin, A, Alarcon, G & Sanei, S 2021, Transfer Learning of EEG for Analysis of Interictal Epileptiform Discharges. in International Conference on e-Health and Bioengineering. IEEE. https://doi.org/10.1109/EHB52898.2021.9657569

APA

Cheong Took, C., Alty, S., Martin-Lopez, D., Valentin, A., Alarcon, G., & Sanei, S. (2021). Transfer Learning of EEG for Analysis of Interictal Epileptiform Discharges. In International Conference on e-Health and Bioengineering IEEE. https://doi.org/10.1109/EHB52898.2021.9657569

Vancouver

Cheong Took C, Alty S, Martin-Lopez D, Valentin A, Alarcon G, Sanei S. Transfer Learning of EEG for Analysis of Interictal Epileptiform Discharges. In International Conference on e-Health and Bioengineering. IEEE. 2021 https://doi.org/10.1109/EHB52898.2021.9657569

Author

Cheong Took, Clive ; Alty, Stephen ; Martin-Lopez, David ; Valentin, Antonio ; Alarcon, Gonzalo ; Sanei, Saeid. / Transfer Learning of EEG for Analysis of Interictal Epileptiform Discharges. International Conference on e-Health and Bioengineering. IEEE, 2021.

BibTeX

@inproceedings{09980b98dbc74563a880fbbc251f0f16,
title = "Transfer Learning of EEG for Analysis of Interictal Epileptiform Discharges",
abstract = "Analysis of EEG requires years of clinical training and mentorship. To alleviate the human cost involved in EEG analysis, we propose a general LSTM-Autoencoder-CNN for EEG (GLACE) framework, which is adequately general to facilitate the use of transfer learning in smart healthcare. Traditionally in transfer learning, only the last few layers of the neural network are changed and adapted to the new task. Instead, we focus on the adaptation of the first layers to each new task. We exploit the inter-trial couplings in our proposed deep learning approach called GLACE. The efficacy of GLACE was assessed against a real-world clinical problem, i.e. the detection of interictal epileptiform discharges; GLACE circumvents the need for the neurophysiologist to spend hours on EEG analysis.Simulations show that the adaptation of the first layers of the trained model leads to an accuracy improvement of 12%.",
author = "{Cheong Took}, Clive and Stephen Alty and David Martin-Lopez and Antonio Valentin and Gonzalo Alarcon and Saeid Sanei",
year = "2021",
month = nov,
day = "19",
doi = "10.1109/EHB52898.2021.9657569",
language = "English",
isbn = "978-1-6654-4001-1",
booktitle = "International Conference on e-Health and Bioengineering",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Transfer Learning of EEG for Analysis of Interictal Epileptiform Discharges

AU - Cheong Took, Clive

AU - Alty, Stephen

AU - Martin-Lopez, David

AU - Valentin, Antonio

AU - Alarcon, Gonzalo

AU - Sanei, Saeid

PY - 2021/11/19

Y1 - 2021/11/19

N2 - Analysis of EEG requires years of clinical training and mentorship. To alleviate the human cost involved in EEG analysis, we propose a general LSTM-Autoencoder-CNN for EEG (GLACE) framework, which is adequately general to facilitate the use of transfer learning in smart healthcare. Traditionally in transfer learning, only the last few layers of the neural network are changed and adapted to the new task. Instead, we focus on the adaptation of the first layers to each new task. We exploit the inter-trial couplings in our proposed deep learning approach called GLACE. The efficacy of GLACE was assessed against a real-world clinical problem, i.e. the detection of interictal epileptiform discharges; GLACE circumvents the need for the neurophysiologist to spend hours on EEG analysis.Simulations show that the adaptation of the first layers of the trained model leads to an accuracy improvement of 12%.

AB - Analysis of EEG requires years of clinical training and mentorship. To alleviate the human cost involved in EEG analysis, we propose a general LSTM-Autoencoder-CNN for EEG (GLACE) framework, which is adequately general to facilitate the use of transfer learning in smart healthcare. Traditionally in transfer learning, only the last few layers of the neural network are changed and adapted to the new task. Instead, we focus on the adaptation of the first layers to each new task. We exploit the inter-trial couplings in our proposed deep learning approach called GLACE. The efficacy of GLACE was assessed against a real-world clinical problem, i.e. the detection of interictal epileptiform discharges; GLACE circumvents the need for the neurophysiologist to spend hours on EEG analysis.Simulations show that the adaptation of the first layers of the trained model leads to an accuracy improvement of 12%.

U2 - 10.1109/EHB52898.2021.9657569

DO - 10.1109/EHB52898.2021.9657569

M3 - Conference contribution

SN - 978-1-6654-4001-1

BT - International Conference on e-Health and Bioengineering

PB - IEEE

ER -