Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

EpilepsyGAN : Synthetic Epileptic Brain Activities with Privacy Preservation

Pascual, Damian ; Amirshahi, Alireza ; Aminifar, Amir LU orcid ; Atienza, David ; Ryvlin, Philippe and Wattenhofer, Roger (2021) In IEEE Transactions on Biomedical Engineering 68(8). p.2435-2446
Abstract

Epilepsy is a chronic neurological disorder affecting more than 65 million people worldwide and manifested by recurrent unprovoked seizures. The unpredictability of seizures not only degrades the quality of life of the patients, but it can also be life-threatening. Modern systems monitoring elec-troencephalography (EEG) signals are being currently developed with the view to detect epileptic seizures in order to alert caregivers and reduce the impact of seizures on patients quality of life. Such seizure detection systems employ state-of-the-art machine learning algorithms that require a large amount of labeled personal data for training. However, acquiring EEG signals during epileptic seizures is a costly and time-consuming process for... (More)

Epilepsy is a chronic neurological disorder affecting more than 65 million people worldwide and manifested by recurrent unprovoked seizures. The unpredictability of seizures not only degrades the quality of life of the patients, but it can also be life-threatening. Modern systems monitoring elec-troencephalography (EEG) signals are being currently developed with the view to detect epileptic seizures in order to alert caregivers and reduce the impact of seizures on patients quality of life. Such seizure detection systems employ state-of-the-art machine learning algorithms that require a large amount of labeled personal data for training. However, acquiring EEG signals during epileptic seizures is a costly and time-consuming process for medical experts and patients. Furthermore, this data often contains sensitive personal information, presenting privacy concerns. In this work, we generate synthetic seizure-like brain electrical activities, i.e., EEG signals, that can be used to train seizure detection algorithms, alleviating the need for sensitive recorded data. Our experiments show that the synthetic seizure data generated with our GAN model succeeds at preserving the privacy of the patients without producing any degradation in performance during seizure monitoring.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Epilepsy Monitoring, Generative Adversarial Networks (GANs), Privacy, Seizure Detection, Synthetic Brain Activities
in
IEEE Transactions on Biomedical Engineering
volume
68
issue
8
pages
12 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • scopus:85097935440
  • pmid:33275573
ISSN
0018-9294
DOI
10.1109/TBME.2020.3042574
language
English
LU publication?
yes
id
36c0698a-a674-4dd7-8d61-40566f371ca0
date added to LUP
2021-01-12 07:47:27
date last changed
2024-06-13 04:18:46
@article{36c0698a-a674-4dd7-8d61-40566f371ca0,
  abstract     = {{<p>Epilepsy is a chronic neurological disorder affecting more than 65 million people worldwide and manifested by recurrent unprovoked seizures. The unpredictability of seizures not only degrades the quality of life of the patients, but it can also be life-threatening. Modern systems monitoring elec-troencephalography (EEG) signals are being currently developed with the view to detect epileptic seizures in order to alert caregivers and reduce the impact of seizures on patients quality of life. Such seizure detection systems employ state-of-the-art machine learning algorithms that require a large amount of labeled personal data for training. However, acquiring EEG signals during epileptic seizures is a costly and time-consuming process for medical experts and patients. Furthermore, this data often contains sensitive personal information, presenting privacy concerns. In this work, we generate synthetic seizure-like brain electrical activities, i.e., EEG signals, that can be used to train seizure detection algorithms, alleviating the need for sensitive recorded data. Our experiments show that the synthetic seizure data generated with our GAN model succeeds at preserving the privacy of the patients without producing any degradation in performance during seizure monitoring.</p>}},
  author       = {{Pascual, Damian and Amirshahi, Alireza and Aminifar, Amir and Atienza, David and Ryvlin, Philippe and Wattenhofer, Roger}},
  issn         = {{0018-9294}},
  keywords     = {{Epilepsy Monitoring; Generative Adversarial Networks (GANs); Privacy; Seizure Detection; Synthetic Brain Activities}},
  language     = {{eng}},
  number       = {{8}},
  pages        = {{2435--2446}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{IEEE Transactions on Biomedical Engineering}},
  title        = {{EpilepsyGAN : Synthetic Epileptic Brain Activities with Privacy Preservation}},
  url          = {{http://dx.doi.org/10.1109/TBME.2020.3042574}},
  doi          = {{10.1109/TBME.2020.3042574}},
  volume       = {{68}},
  year         = {{2021}},
}