{"title":"Weighted directed graph-based automatic seizure detection with effective brain connectivity for EEG signals","authors":"Qi Sun, Yuanjian Liu, Shuangde Li","doi":"10.1007/s11760-023-02816-4","DOIUrl":null,"url":null,"abstract":"Abstract Epileptic seizure is one of the most common neurological disorders characterized by sudden abnormal discharge of neurons in the brain. Automated seizure detection using electroencephalograph (EEG) recordings would improve the quality of treatment and reduce medical overhead. The purpose of this paper is to design an automated seizure detection framework that can effectively identify seizure and non-seizure events by discovering connectivity between brain regions. In this work, a weighted directed graph-based method with effective brain connectivity (EBC) is proposed for seizure detection. The weighted directed graph is built by analyzing the correlation among the different regions of the brain. Then, graph theory-based measures are used to extract features for classification. Furthermore, we illustrate the ability of the proposed method to achieve seizure detection for the patient-specific model and the cross-patient model. The results show that the proposed method achieves accuracy values of 99.97% and 98.29% for the patient-specific model and the cross-patient model in the CHB-MIT dataset, respectively. These results demonstrate that the proposed method achieves an effective classification performance and can be used to provide assistance for automatic seizure detection and clinical diagnosis.","PeriodicalId":54393,"journal":{"name":"Signal Image and Video Processing","volume":"13 1","pages":"0"},"PeriodicalIF":2.0000,"publicationDate":"2023-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Signal Image and Video Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s11760-023-02816-4","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
Abstract Epileptic seizure is one of the most common neurological disorders characterized by sudden abnormal discharge of neurons in the brain. Automated seizure detection using electroencephalograph (EEG) recordings would improve the quality of treatment and reduce medical overhead. The purpose of this paper is to design an automated seizure detection framework that can effectively identify seizure and non-seizure events by discovering connectivity between brain regions. In this work, a weighted directed graph-based method with effective brain connectivity (EBC) is proposed for seizure detection. The weighted directed graph is built by analyzing the correlation among the different regions of the brain. Then, graph theory-based measures are used to extract features for classification. Furthermore, we illustrate the ability of the proposed method to achieve seizure detection for the patient-specific model and the cross-patient model. The results show that the proposed method achieves accuracy values of 99.97% and 98.29% for the patient-specific model and the cross-patient model in the CHB-MIT dataset, respectively. These results demonstrate that the proposed method achieves an effective classification performance and can be used to provide assistance for automatic seizure detection and clinical diagnosis.
期刊介绍:
The journal is an interdisciplinary journal presenting the theory and practice of signal, image and video processing. It aims at:
- Disseminating high level research results and engineering developments to all signal, image or video processing researchers and research groups.
- Presenting practical solutions for the current signal, image and video processing problems in Engineering and Science.
Subject areas covered by the journal include but are not limited to:
Adaptive processing – biomedical signal processing – multimedia signal processing – communication signal processing – non-linear signal processing – array processing – statistics and statistical signal processing – modeling – filtering – data science – graph signal processing – multi-resolution signal analysis and wavelets – segmentation – coding – restoration – enhancement – storage and retrieval – colour and multi-spectral processing – scanning – displaying – printing – interpolation – image processing - video processing-motion detection and estimation – stereoscopic processing – image and video coding.