Weighted directed graph-based automatic seizure detection with effective brain connectivity for EEG signals
Open Access
- 19 October 2023
- journal article
- research article
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (1) , 899-909
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.Keywords
All Related Versions
Funding Information
- Postgraduate Research & Practice Innovation Program of Jiangsu Province in 2021 (KYCX21_0718)
- Natural Science Research Start-up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications (NY222059)
This publication has 40 references indexed in Scilit:
- EEG-based seizure detection in patients with intellectual disability: Which EEG and clinical factors are important?Biomedical Signal Processing and Control, 2018
- Epileptic Seizure Detection Based on Time-Frequency Images of EEG Signals Using Gaussian Mixture Model and Gray Level Co-Occurrence Matrix FeaturesInternational Journal of Neural Systems, 2018
- Automatic seizure detection using a highly adaptive directional time–frequency distributionMultidimensional Systems and Signal Processing, 2017
- A Multivariate Approach for Patient-Specific EEG Seizure Detection Using Empirical Wavelet TransformIEEE Transactions on Biomedical Engineering, 2017
- Nonlinear Dynamics and Chaos: With Applications to Physics, Biology, Chemistry, and EngineeringPhysics Today, 2015
- Review of the methods of determination of directed connectivity from multichannel dataMedical & Biological Engineering & Computing, 2011
- Temporal Lobe Epilepsy: Anatomical and Effective ConnectivityIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2008
- Granger Causality: Basic Theory and Application to Neuroscience2006
- Short-window spectral analysis of cortical event-related potentials by adaptive multivariate autoregressive modeling: data preprocessing, model validation, and variability assessmentBiological Cybernetics, 2000
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974