Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Nov;12(11):e2763.
doi: 10.1002/brb3.2763. Epub 2022 Oct 5.

A medium-weight deep convolutional neural network-based approach for onset epileptic seizures classification in EEG signals

Nazanin Nemati  1 , Saeed Meshgini  1
Affiliations

A medium-weight deep convolutional neural network-based approach for onset epileptic seizures classification in EEG signals

Nazanin Nemati et al. Brain Behav. 2022 Nov.

Abstract

Introduction: Epileptic condition can be detected in EEG data seconds before it occurs, according to evidence. To overcome the related long-term mortality and morbidity from epileptic seizures, it is critical to make an initial diagnosis, uncover underlying causes, and avoid applicable risk factors. Progress in diagnosing onset epileptic seizures can ensure that seizures and destroyed damages are detectable at the time of manifestation. Previous seizure detection models had problems with the presence of multiple features, the lack of an appropriate signal descriptor, and the time-consuming analysis, all of which led to uncertainty and different interpretations. Deep learning has recently made tremendous progress in categorizing and detecting epilepsy.

Method: This work proposes an effective classification strategy in response to these issues. The discrete wavelet transform (DWT) is used to breakdown the EEG signal, and a deep convolutional neural network (DCNN) is used to diagnose epileptic seizures in the first phase. Using a medium-weight DCNN (mw-DCNN) architecture, we use a preprocess phase to improve the decision-maker method. The proposed approach was tested on the CHEG-MIT Scalp EEG database's collected EEG signals.

Result: The results of the studies reveal that the mw-DCNN algorithm produces proper classification results under various conditions. To solve the uncertainty challenge, K-fold cross-validation was used to assess the algorithm's repeatability at the test level, and the accuracies were evaluated in the range of 99%-100%.

Conclusion: The suggested structure can assist medical specialistsin analyzing epileptic seizures' EEG signals more precisely.

Keywords: EEG; convolutional neural network; discrete wavelet decomposition; early seizure detection; medium-weight structure.

PubMed Disclaimer

Conflict of interest statement

We have declared that we do not have any conflicts of interest.

Figures

FIGURE 1
FIGURE 1
We have used discrete wavelet decomposition (DWT) method to decompose EEG signals into multiple subbands. The down arrow is downsampling by 2
FIGURE 2
FIGURE 2
The schematic of introduced approach for identifying the onset epileptic seizures
FIGURE 3
FIGURE 3
Utilization of h[n] and g[n] filters to decompose EEG signals (x[n]) into subbands
FIGURE 4
FIGURE 4
Proposed medium‐weight structure of the deep convolutional network
FIGURE 5
FIGURE 5
This figure depicts correlation maps of decomposed EEG signal for a patient
FIGURE 6
FIGURE 6
The ROC curve of two test EEG signals
FIGURE 7
FIGURE 7
The ROC curve of two unseen EEG signals
FIGURE 8
FIGURE 8
Similar methods were compared to the recommended strategy in order to determine the onset of an epileptic episode
FIGURE 9
FIGURE 9
This figure shows the comparison of the accuracy of the classification with three classes. Experiment 1 has been performed without decomposition of input signals. Experiment 2 has been carried out with decomposition by DWT on input signals, and also, the network has a large number of layers. Finally, Experiment 3 has been conducted with decomposition by DWT on input signals, and also, the network structure has a low number of layers
FIGURE 10
FIGURE 10
mw‐DCNN convergence in reducing the error in training data—random data 1 after 31 iterations and reaching the minimum value of zero in the classifier cost function
FIGURE 11
FIGURE 11
mw‐DCNN convergence in reducing the error in training data—random data 2 after 14 iterations and reaching the minimum value of zero in the classifier cost function
FIGURE 12
FIGURE 12
mw‐DCNN convergence in reducing the error in training data—random data 3 after 8 iterations and reaching the minimum value of zero in the classifier cost function
See this image and copyright information in PMC

References

    1. Capovilla, G. , Kaufman, K. R. , Perucca, E. , Moshé, S. L. , & Arida, R. M. (2016). Epilepsy, seizures, physical exercise, and sports: A report from the ILAE Task Force on Sports and Epilepsy. Epilepsia, 57(1), 6–12. - PubMed
    1. de Lange, I. M. , Helbig, K. L. , Weckhuysen, S. , Møller, R. S. , Velinov, M. , Dolzhanskaya, N. , Marsh, E. , Helbig, I. , Devinsky, O. , Tang, S. , & Mefford, H. C. (2016). De novo mutations of KIAA2022 in females cause intellectual disability and intractable epilepsy. Journal of medical genetics, 53(12), 850–858. - PMC - PubMed
    1. Hill, T. , Coupland, C. , Morriss, R. , Arthur, A. , Moore, M. , & Hippisley‐Cox, J. (2015). Antidepressant use and risk of epilepsy and seizures in people aged 20 to 64 years: Cohort study using a primary care database. Bmc Psychiatry [Electronic Resource], 15(1), 3–15. - PMC - PubMed
    1. Yu, N. , Lin, X. J. , Zhang, S. G. , & Di, Q. (2019). Analysis of the reasons and costs of hospitalization for epilepsy patients in East China. Seizure: The Journal of the British Epilepsy Association, 1(72), 5–40. - PubMed
    1. Li, M. C. , & Cook, M. J. (2018). Deep brain stimulation for drug‐resistant epilepsy. Epilepsia, 59(2), 273–290. - PubMed