Evaluation of potential auras in generalized epilepsy from EEG signals using deep convolutional neural networks and time-frequency representation
| Autor: | Mehmet Ufuk Aluçlu, Mehmet Sirac Ozerdem, Hasan Polat |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
Biomedical Engineering Context (language use) 02 engineering and technology Electroencephalography Convolutional neural network 03 medical and health sciences Epilepsy 0302 clinical medicine Seizures 0202 electrical engineering electronic engineering information engineering medicine Humans Generalized epilepsy deep learning EEG epilepsy epileptic aura time-frequency representation medicine.diagnostic_test business.industry Deep learning Short-time Fourier transform Pattern recognition medicine.disease Quality of Life Spectrogram 020201 artificial intelligence & image processing Epilepsy Generalized Artificial intelligence Neural Networks Computer business 030217 neurology & neurosurgery |
| Zdroj: | Biomedizinische Technik. Biomedical engineeringReferences. 65(4) |
| ISSN: | 1862-278X |
| Popis: | PubMed: 31825886 2-s2.0-85089618356 The general uncertainty of epilepsy and its unpredictable seizures often affect badly the quality of life of people exposed to this disease. There are patients who can be considered fortunate in terms of prediction of any seizures. These are patients with epileptic auras. In this study, it was aimed to evaluate pre-seizure warning symptoms of the electroencephalography (EEG) signals by a convolutional neural network (CNN) inspired by the epileptic auras defined in the medical field. In this context, one-dimensional EEG signals were transformed into a spectrogram display form in the frequency-time domain by applying a short-time Fourier transform (STFT). Systemic changes in pre-epileptic seizure have been described by applying the CNN approach to the EEG signals represented in the image form, and the subjective EEG-Aura process has been tried to be determined for each patient. Considering all patients included in the evaluation, it was determined that the 1-min interval covering the time from the second minute to the third minute before the seizure had the highest mean and the lowest variance to determine the systematic changes before the seizure. Thus, the highest performing process is described as EEG-Aura. The average success for the EEG-Aura process was 90.38 ± 6.28%, 89.78 ± 8.34% and 90.47 ± 5.95% for accuracy, specificity and sensitivity, respectively. Through the proposed model, epilepsy patients who do not respond to medical treatment methods are expected to maintain their lives in a more comfortable and integrated way. © 2019 Walter de Gruyter GmbH, Berlin/Boston 2019. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|