Efficient graph convolutional networks for seizure prediction using scalp EEG
Epilepsy is a chronic brain disease that causes persistent and severe damage to the physical and mental health of patients. Daily effective prediction of epileptic seizures is crucial for epilepsy patients especially those with refractory epilepsy. At present, a large number of deep learning algorit...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2022.967116/full |
| _version_ | 1828430209028718592 |
|---|---|
| author | Manhua Jia Wenjian Liu Junwei Duan Long Chen C. L. Philip Chen Qun Wang Zhiguo Zhou |
| author_facet | Manhua Jia Wenjian Liu Junwei Duan Long Chen C. L. Philip Chen Qun Wang Zhiguo Zhou |
| author_sort | Manhua Jia |
| collection | DOAJ |
| description | Epilepsy is a chronic brain disease that causes persistent and severe damage to the physical and mental health of patients. Daily effective prediction of epileptic seizures is crucial for epilepsy patients especially those with refractory epilepsy. At present, a large number of deep learning algorithms such as Convolutional Neural Networks and Recurrent Neural Networks have been used to predict epileptic seizures and have obtained better performance than traditional machine learning methods. However, these methods usually transform the Electroencephalogram (EEG) signal into a Euclidean grid structure. The conversion suffers from loss of adjacent spatial information, which results in deep learning models requiring more storage and computational consumption in the process of information fusion after information extraction. This study proposes a general Graph Convolutional Networks (GCN) model architecture for predicting seizures to solve the problem of oversized seizure prediction models based on exploring the graph structure of EEG signals. As a graph classification task, the network architecture includes graph convolution layers that extract node features with one-hop neighbors, pooling layers that summarize abstract node features; and fully connected layers that implement classification, resulting in superior prediction performance and smaller network size. The experiment shows that the model has an average sensitivity of 96.51%, an average AUC of 0.92, and a model size of 15.5 k on 18 patients in the CHB-MIT scalp EEG dataset. Compared with traditional deep learning methods, which require a large number of parameters and computational effort and are demanding in terms of storage space and energy consumption, this method is more suitable for implementation on compact, low-power wearable devices as a standard process for building a generic low-consumption graph network model on similar biomedical signals. Furthermore, the edge features of graphs can be used to make a preliminary determination of locations and types of discharge, making it more clinically interpretable. |
| first_indexed | 2024-12-10T17:44:22Z |
| format | Article |
| id | doaj.art-03a25b64619c49eabcf9f4ee6b53fa1d |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-10T17:44:22Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-03a25b64619c49eabcf9f4ee6b53fa1d2022-12-22T01:39:16ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-08-011610.3389/fnins.2022.967116967116Efficient graph convolutional networks for seizure prediction using scalp EEGManhua Jia0Wenjian Liu1Junwei Duan2Long Chen3C. L. Philip Chen4Qun Wang5Zhiguo Zhou6School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, ChinaDepartment of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, ChinaCollege of Information Science and Technology, Jinan University, Guangzhou, ChinaFaculty of Science and Technology, University of Macau, Taipa, Macau SAR, ChinaSchool of Computer Science and Engineering, South China University of Technology, Guangzhou, ChinaSchool of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, ChinaSchool of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, ChinaEpilepsy is a chronic brain disease that causes persistent and severe damage to the physical and mental health of patients. Daily effective prediction of epileptic seizures is crucial for epilepsy patients especially those with refractory epilepsy. At present, a large number of deep learning algorithms such as Convolutional Neural Networks and Recurrent Neural Networks have been used to predict epileptic seizures and have obtained better performance than traditional machine learning methods. However, these methods usually transform the Electroencephalogram (EEG) signal into a Euclidean grid structure. The conversion suffers from loss of adjacent spatial information, which results in deep learning models requiring more storage and computational consumption in the process of information fusion after information extraction. This study proposes a general Graph Convolutional Networks (GCN) model architecture for predicting seizures to solve the problem of oversized seizure prediction models based on exploring the graph structure of EEG signals. As a graph classification task, the network architecture includes graph convolution layers that extract node features with one-hop neighbors, pooling layers that summarize abstract node features; and fully connected layers that implement classification, resulting in superior prediction performance and smaller network size. The experiment shows that the model has an average sensitivity of 96.51%, an average AUC of 0.92, and a model size of 15.5 k on 18 patients in the CHB-MIT scalp EEG dataset. Compared with traditional deep learning methods, which require a large number of parameters and computational effort and are demanding in terms of storage space and energy consumption, this method is more suitable for implementation on compact, low-power wearable devices as a standard process for building a generic low-consumption graph network model on similar biomedical signals. Furthermore, the edge features of graphs can be used to make a preliminary determination of locations and types of discharge, making it more clinically interpretable.https://www.frontiersin.org/articles/10.3389/fnins.2022.967116/fullseizure predictionEEGGCNgeometric deep learningwearable devices |
| spellingShingle | Manhua Jia Wenjian Liu Junwei Duan Long Chen C. L. Philip Chen Qun Wang Zhiguo Zhou Efficient graph convolutional networks for seizure prediction using scalp EEG Frontiers in Neuroscience seizure prediction EEG GCN geometric deep learning wearable devices |
| title | Efficient graph convolutional networks for seizure prediction using scalp EEG |
| title_full | Efficient graph convolutional networks for seizure prediction using scalp EEG |
| title_fullStr | Efficient graph convolutional networks for seizure prediction using scalp EEG |
| title_full_unstemmed | Efficient graph convolutional networks for seizure prediction using scalp EEG |
| title_short | Efficient graph convolutional networks for seizure prediction using scalp EEG |
| title_sort | efficient graph convolutional networks for seizure prediction using scalp eeg |
| topic | seizure prediction EEG GCN geometric deep learning wearable devices |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2022.967116/full |
| work_keys_str_mv | AT manhuajia efficientgraphconvolutionalnetworksforseizurepredictionusingscalpeeg AT wenjianliu efficientgraphconvolutionalnetworksforseizurepredictionusingscalpeeg AT junweiduan efficientgraphconvolutionalnetworksforseizurepredictionusingscalpeeg AT longchen efficientgraphconvolutionalnetworksforseizurepredictionusingscalpeeg AT clphilipchen efficientgraphconvolutionalnetworksforseizurepredictionusingscalpeeg AT qunwang efficientgraphconvolutionalnetworksforseizurepredictionusingscalpeeg AT zhiguozhou efficientgraphconvolutionalnetworksforseizurepredictionusingscalpeeg |