Efficient EEG Feature Learning Model Combining Random Convolutional Kernel with Wavelet Scattering for Seizure Detection
International Journal of Neural Systems · 2024
DOI: 10.1142/s0129065724500606 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Neural Systems, 2024. Verfasst von Yasheng Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Shandong Province Key Laboratory of Medical Physics and Image Processing Technology, School of Physics and Electronics, Shandong Normal University, J…. Hauptthemen laut MEDLINE: Seizures, Electroencephalography, Wavelet Analysis, Deep Learning. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: Shandong Provincial Natural Science Foundation, The China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Automatic seizure detection has significant value in epilepsy diagnosis and treatment. Although a variety of deep learning models have been proposed to automatically learn electroencephalography (EEG) features for seizure detection, the generalization performance and computational burden of such deep models remain the bottleneck of practical application. In this study, a novel lightweight model based on random convolutional kernel transform (ROCKET) is developed for EEG feature learning for seizure detection. Specifically, random convolutional kernels are embedded into the structure of a wavelet scattering network instead of original wavelet transform convolutions. Then the significant EEG features are selected from the scattering coefficients and convolutional outputs by analysis of variance (ANOVA) and minimum redundancy-maximum relevance (MRMR) methods. This model not only preserves the merits of the fast-training process from ROCKET, but also provides insight into seizure detection by retaining only the helpful channels. The extreme gradient boosting (XGboost) classifier was combined with this EEG feature learning model to build a comprehensive seizure detection system that achieved promising epoch-based results, with over 90% of both sensitivity and specificity on the scalp and intracranial EEG databases. The experimental comparisons showed that the proposed method outperformed other state-of-the-art methods for cross-patient and patient-specific seizure detection.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Shandong Province Key Laboratory of Medical Physics and Image Processing Technology, School of Physics and Electronics, Shandong Normal University, Jinan 250358, P. R. China.
- Department of Pediatric Intensive Care Unit, Shandong Provincial Maternal and Child Health Care Hospital, Affiliated to Qingdao University, Jinan 250014, P. R. China.
- The First Affiliated Hospital of Shandong First Medical University, Shandong First Medical University, Jinan 250014, P. R. China.
ORCID-Profile: Qi Yuan
Förderung
- Shandong Provincial Natural Science Foundation
- The China Postdoctoral Science Foundation
Zitieren
APA
Liu, Y., Jiang, Y., Liu, J., Li, J., Liu, M., Nie, W., & Yuan, Q. (2024). Efficient EEG Feature Learning Model Combining Random Convolutional Kernel with Wavelet Scattering for Seizure Detection. International Journal of Neural Systems. https://doi.org/10.1142/s0129065724500606
Vancouver
Liu Y, Jiang Y, Liu J, Li J, Liu M, Nie W, et al. Efficient EEG Feature Learning Model Combining Random Convolutional Kernel with Wavelet Scattering for Seizure Detection. International Journal of Neural Systems. 2024. doi:10.1142/s0129065724500606
BibTeX
@article{Liu2024,
author = {Liu, Yasheng and Jiang, Yonghui and Liu, Jie and Li, Jie and Liu, Mingze and Nie, Weiwei and Yuan, Qi},
title = {Efficient EEG Feature Learning Model Combining Random Convolutional Kernel with Wavelet Scattering for Seizure Detection},
journal = {International Journal of Neural Systems},
year = {2024},
doi = {10.1142/s0129065724500606}
}
EUVIMED