EEG Signal Epilepsy Detection With a Weighted Neighbor Graph Representation and Two-Stream Graph-Based Framework

Epilepsy detection is a critical medical task, but traditional methods face challenges in accuracy and reliability due to the difficulty of EEG data acquisition and the limitation of the number of sample seizures. To overcome these challenges, this paper proposes a new model for epilepsy detection that combines Graph Convolutional Neural Network (Graph Convolutional Network, GCN) and Transformer, aiming to significantly improve the accuracy and sensitivity of detection. The core of the model adopts GCN, which utilizes its powerful inter-node relationship capturing capability and graph feature learning mechanism. However, due to the limitation of traditional GCN in integrating global features, this model incorporates the Transformer structure to enhance global feature aggregation and reduce irrelevant feature interactions. After multiple rounds of testing of the GHB-MIT dataset, the model demonstrated excellent performance, with an average sensitivity of 92.97%, specificity of 94.60%, and accuracy of 94.59%, which was significantly better than the traditional method. Further comparison with the latest literature also confirms the advantages of the present method. In summary, the epilepsy detection model we developed based on graph convolutional neural network and Transformer not only shows significant improvement in accuracy and sensitivity, but also provides more accurate and reliable technical support for epilepsy diagnosis, which provides a valuable reference for research in related fields.

show abstract

SNSDeepNet: spike and non-spike detection in epilepsy

Kumar,

Kumar Upadhyay,

Kumar Panda

2024

Eng. Res. Express

View full text Add to dashboard Cite

Epilepsy, a severe neurological condition is marked by sharp waveforms known as spikes in electroencephalogram (EEG) signals. Prompt detection of these spikes is crucial for reducing accidental injuries and safeguarding the lives of epilepsy patients. This article proposes an innovative deep-learning approach for epileptic spike detection using Spike and Non-spike Deep Convolutional Neural Networks (SNSDeepNet). Our method utilizes CNNs alongside an adaptive Layer-wise Adaptive Moments (LAMB) optimizer to effectively extract relevant features from time-domain (TD) and frequency-domain (FD) representations of spike and non-spike signals. The adaptive LAMB optimizer enhances the training process and accelerates convergence compared to traditional optimizers. The proposed model is evaluated using EEG recordings from three datasets: the Children's Hospital Boston (CHB-MIT) dataset, the Siena Scalp EEG dataset (Physionet Siena Scalp EEG Database), and the Bonn EEG dataset from the University of Bonn. After pre-processing and applying a peak detection algorithm, we extract TD and FD features from the signals. Our model demonstrates impressive performance. The CHB-MIT dataset achieved an average accuracy of 99.69%, sensitivity of 99.68%, F1-score of 99.11%, and a false positive rate (FPR) of 0.02698. For the Siena dataset, the model achieved an accuracy of 99.62%, specificity of 99.04%, sensitivity of 99.93%, F1-score of 99.48%, and an FPR of 0.009208. The Bonn dataset achieved an average accuracy of 94.10%, specificity of 92.39%, sensitivity of 97.35%, and an FPR of 0.0764. These findings underscore the effectiveness of the proposed architecture in accurately identifying epileptic spikes, highlighting its potential to enhance epilepsy diagnosis and treatment.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

EEG Signal Epilepsy Detection With a Weighted Neighbor Graph Representation and Two-Stream Graph-Based Framework

Cited by 4 publications

References 37 publications

A review of graph theory-based diagnosis of neurological disorders based on EEG and MRI

A review of graph theory-based diagnosis of neurological disorders based on EEG and MRI

Epilepsy Detection Based on Graph Convolutional Neural Network and Transformer

SNSDeepNet: spike and non-spike detection in epilepsy

Contact Info

Product

Resources

About