Feature separation and adversarial training for the patient-independent detection of epileptic seizures

作者全名："Yang, Yong; Li, Feng; Qin, Xiaolin; Wen, Han; Lin, Xiaoguang; Huang, Dong"

作者地址："[Yang, Yong; Qin, Xiaolin; Wen, Han] Chinese Acad Sci, Chengdu Inst Comp Applicat, Chengdu, Sichuan, Peoples R China; [Yang, Yong; Lin, Xiaoguang; Huang, Dong] Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing, Peoples R China; [Yang, Yong; Lin, Xiaoguang] Univ Chinese Acad Sci, Chongqing Sch, Chongqing, Peoples R China; [Li, Feng] Chongqing Med Univ, Dept Neurol, Affiliated Hosp 1, Chongqing, Peoples R China"

通信作者："Yang, Y (通讯作者)，Chinese Acad Sci, Chengdu Inst Comp Applicat, Chengdu, Sichuan, Peoples R China.; Yang, Y (通讯作者)，Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing, Peoples R China.; Yang, Y (通讯作者)，Univ Chinese Acad Sci, Chongqing Sch, Chongqing, Peoples R China."

来源：FRONTIERS IN COMPUTATIONAL NEUROSCIENCE

ESI学科分类：NEUROSCIENCE & BEHAVIOR

WOS号：WOS:001039360200001

JCR分区：Q2

影响因子：2.1

年份：2023

卷号：17

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：epileptic seizure detection; EEG; feature separation; adversarial training; patient-independent

摘要："An epileptic seizure is the external manifestation of abnormal neuronal discharges, which seriously affecting physical health. The pathogenesis of epilepsy is complex, and the types of epileptic seizures are diverse, resulting in significant variation in epileptic seizure data between subjects. If we feed epilepsy data from multiple patients directly into the model for training, it will lead to underfitting of the model. To overcome this problem, we propose a robust epileptic seizure detection model that effectively learns from multiple patients while eliminating the negative impact of the data distribution shift between patients. The model adopts a multi-level temporal-spectral feature extraction network to achieve feature extraction, a feature separation network to separate features into category-related and patient-related components, and an invariant feature extraction network to extract essential feature information related to categories. The proposed model is evaluated on the TUH dataset using leave-one-out cross-validation and achieves an average accuracy of 85.7%. The experimental results show that the proposed model is superior to the related literature and provides a valuable reference for the clinical application of epilepsy detection."

基金机构："Sichuan Science and Technology Plan of China [2019ZDZX0005, 2019ZDZX0006, 2020YFQ0056]"

基金资助正文："Funding This research was supported by the Sichuan Science and Technology Plan of China Grants (2019ZDZX0005, 2019ZDZX0006, and 2020YFQ0056)."