Open AccessData-driven electrophysiological feature based on deep learning to detect epileptic seizures
Author(s) -
Shota Yamamoto,
Takufumi Yanagisawa,
Ryohei Fukuma,
Satoru Oshino,
Naoki Tani,
Hui Ming Khoo,
Kohtaroh Edakawa,
Maki Kobayashi,
Miyuu Tanaka,
Yuya Fujita,
Haruhiko Kishima
Publication year - 2021
Publication title -
journal of neural engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.594
H-Index - 111
eISSN - 1741-2560
pISSN - 1741-2552
DOI - 10.1088/1741-2552/ac23bf
Subject(s) - epilepsy , ictal , pattern recognition (psychology) , support vector machine , feature (linguistics) , epileptic seizure , artificial intelligence , electroencephalography , computer science , receiver operating characteristic , convolutional neural network , electrophysiology , phase lag , audiology , neuroscience , psychology , medicine , mathematics , machine learning , linguistics , philosophy
Objective . To identify a new electrophysiological feature characterising the epileptic seizures, which is commonly observed in different types of epilepsy. Methods . We recorded the intracranial electroencephalogram (iEEG) of 21 patients (12 women and 9 men) with multiple types of refractory epilepsy. The raw iEEG signals of the early phase of epileptic seizures and interictal states were classified by a convolutional neural network (Epi-Net). For comparison, the same signals were classified by a support vector machine (SVM) using the spectral power and phase-amplitude coupling. The features learned by Epi-Net were derived by a modified integrated gradients method. We considered the product of powers multiplied by the relative contribution of each frequency amplitude as a data-driven epileptogenicity index (d-EI). We compared the d-EI and other conventional features in terms of accuracy to detect the epileptic seizures. Finally, we compared the d-EI among the electrodes to evaluate its relationship with the resected area and the Engel classification. Results . Epi-Net successfully identified the epileptic seizures, with an area under the receiver operating characteristic curve of 0.944 ± 0.067, which was significantly larger than that of the SVM (0.808 ± 0.253, n = 21; p = 0.025). The learned iEEG signals were characterised by increased powers of 17-92 Hz and >180 Hz in addition to decreased powers of other frequencies. The proposed d-EI detected them with better accuracy than the other iEEG features. Moreover, the surgical resection of areas with a larger increase in d-EI was observed for all nine patients with Engel class ⩽1, but not for the 4 of 12 patients with Engel class >1, demonstrating the significant association with seizure outcomes. Significance. We derived an iEEG feature from the trained Epi-Net, which identified the epileptic seizures with improved accuracy and might contribute to identification of the epileptogenic zone.