Automatic Seizure Detection and Prediction Based on Brain Connectivity Features and a CNNsMeet Transformers Classifier | |
Tian, Ziwei1,2,3; Hu, Bingliang3; Si, Yang4,5; Wang, Quan1,3 | |
作者部门 | 光谱成像技术研究室 |
2023-05-18 | |
发表期刊 | BRAIN SCIENCES |
ISSN | 2076-3425 |
卷号 | 13期号:5 |
产权排序 | 1 |
摘要 | (1) Background: Epilepsy is a neurological disorder that causes repeated seizures. Since electroencephalogram (EEG) patterns differ in different states (inter-ictal, pre-ictal, and ictal), a seizure can be detected and predicted by extracting various features. However, the brain connectivity network, a two-dimensional feature, is rarely studied. We aim to investigate its effectiveness for seizure detection and prediction. (2) Methods: Two time-window lengths, five frequency bands, and five connectivity measures were used to extract image-like features, which were fed into a support vector machine for the subject-specific model (SSM) and a convolutional neural networks meet transformers (CMT) classifier for the subject-independent model (SIM) and cross-subject model (CSM). Finally, feature selection and efficiency analyses were conducted. (3) Results: The classification results on the CHB-MIT dataset showed that a long window indicated better performance. The best detection accuracies of SSM, SIM, and CSM were 100.00, 99.98, and 99.27%, respectively. The highest prediction accuracies were 99.72, 99.38, and 86.17%, respectively. In addition, Pearson Correlation Coefficient and Phase Lock Value connectivity in the beta and gamma bands showed good performance and high efficiency. (4) Conclusions: The proposed brain connectivity features showed good reliability and practical value for automatic seizure detection and prediction, which expects to develop portable real-time monitoring equipment. |
关键词 | epileptic state classification EEG brain connectivity support vector machine CNNs meet transformers |
DOI | 10.3390/brainsci13050820 |
收录类别 | SCI |
语种 | 英语 |
WOS记录号 | WOS:000995596600001 |
出版者 | MDPI |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/96533 |
专题 | 光谱成像技术研究室 |
通讯作者 | Wang, Quan |
作者单位 | 1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Spectral Imaging Technol, Xian 710119, Peoples R China 2.Univ Chinese Acad Sci, Sch Optoelect, Beijing 101408, Peoples R China 3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Biomed Spect Xian, Xian 710119, Peoples R China 4.Sichuan Acad Med Sci & Sichuan Prov Peoples Hosp, Dept Neurol, Chengdu 610072, Peoples R China 5.Univ Elect Sci & Technol China, Sch Med, Chengdu 611731, Peoples R China |
推荐引用方式 GB/T 7714 | Tian, Ziwei,Hu, Bingliang,Si, Yang,et al. Automatic Seizure Detection and Prediction Based on Brain Connectivity Features and a CNNsMeet Transformers Classifier[J]. BRAIN SCIENCES,2023,13(5). |
APA | Tian, Ziwei,Hu, Bingliang,Si, Yang,&Wang, Quan.(2023).Automatic Seizure Detection and Prediction Based on Brain Connectivity Features and a CNNsMeet Transformers Classifier.BRAIN SCIENCES,13(5). |
MLA | Tian, Ziwei,et al."Automatic Seizure Detection and Prediction Based on Brain Connectivity Features and a CNNsMeet Transformers Classifier".BRAIN SCIENCES 13.5(2023). |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Automatic Seizure De(3837KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论