Automated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN-LSTM
Abstract Intelligent recognition methods for classifying non-stationary and non-invasive epileptic diagnoses are essential tools in neurological research. Electroencephalogram (EEG) signals exhibit better temporal characteristics in the detection of epilepsy compared to radiation medical images like...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-09-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-41537-z |
| _version_ | 1827710946729000960 |
|---|---|
| author | Xiashuang Wang Yinglei Wang Dunwei Liu Ying Wang Zhengjun Wang |
| author_facet | Xiashuang Wang Yinglei Wang Dunwei Liu Ying Wang Zhengjun Wang |
| author_sort | Xiashuang Wang |
| collection | DOAJ |
| description | Abstract Intelligent recognition methods for classifying non-stationary and non-invasive epileptic diagnoses are essential tools in neurological research. Electroencephalogram (EEG) signals exhibit better temporal characteristics in the detection of epilepsy compared to radiation medical images like computed tomography (CT) and magnetic resonance imaging (MRI), as they provide real-time insights into the disease’ condition. While classical machine learning methods have been used for epilepsy EEG classification, they still often require manual parameter adjustments. Previous studies primarily focused on binary epilepsy recognition (epilepsy vs. healthy subjects) rather than as ternary status recognition (continuous epilepsy vs. intermittent epilepsy vs. healthy subjects). In this study, we propose a novel deep learning method that combines a convolution neural network (CNN) with a long short-term memory (LSTM) network for multi-class classification including both binary and ternary tasks, using a publicly available benchmark database on epilepsy EEGs. The hybrid CNN-LSTM automatically acquires knowledge without the need for extra pre-processing or manual intervention. Besides, the joint network method benefits from memory function and stronger feature extraction ability. Our proposed hybrid CNN-LSTM achieves state-of-the-art performance in ternary classification, outperforming classical machine learning and the latest deep learning models. For the three-class classification, in the method achieves an accuracy, specificity, sensitivity, and ROC of 98%, 97.4, 98.3% and 96.8%, respectively. In binary classification, the method achieves better results, with ACC of 100%, 100%, and 99.8%, respectively. Our dual stream spatiotemporal hybrid network demonstrates superior performance compared to other methods. Notably, it eliminates the need for manual operations, making it more efficient for doctors to diagnose during the clinical process and alleviating the workload of neurologists. |
| first_indexed | 2024-03-10T17:46:58Z |
| format | Article |
| id | doaj.art-77973847029f454f8ccab884bc5ffe2b |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-10T17:46:58Z |
| publishDate | 2023-09-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-77973847029f454f8ccab884bc5ffe2b2023-11-20T09:30:27ZengNature PortfolioScientific Reports2045-23222023-09-0113111210.1038/s41598-023-41537-zAutomated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN-LSTMXiashuang Wang0Yinglei Wang1Dunwei Liu2Ying Wang3Zhengjun Wang4The Second Academy of China Aerospace Science and Industry Corporation (CASIC)The Second Academy of China Aerospace Science and Industry Corporation (CASIC)The Second Academy of China Aerospace Science and Industry Corporation (CASIC)The Second Academy of China Aerospace Science and Industry Corporation (CASIC)The Second Academy of China Aerospace Science and Industry Corporation (CASIC)Abstract Intelligent recognition methods for classifying non-stationary and non-invasive epileptic diagnoses are essential tools in neurological research. Electroencephalogram (EEG) signals exhibit better temporal characteristics in the detection of epilepsy compared to radiation medical images like computed tomography (CT) and magnetic resonance imaging (MRI), as they provide real-time insights into the disease’ condition. While classical machine learning methods have been used for epilepsy EEG classification, they still often require manual parameter adjustments. Previous studies primarily focused on binary epilepsy recognition (epilepsy vs. healthy subjects) rather than as ternary status recognition (continuous epilepsy vs. intermittent epilepsy vs. healthy subjects). In this study, we propose a novel deep learning method that combines a convolution neural network (CNN) with a long short-term memory (LSTM) network for multi-class classification including both binary and ternary tasks, using a publicly available benchmark database on epilepsy EEGs. The hybrid CNN-LSTM automatically acquires knowledge without the need for extra pre-processing or manual intervention. Besides, the joint network method benefits from memory function and stronger feature extraction ability. Our proposed hybrid CNN-LSTM achieves state-of-the-art performance in ternary classification, outperforming classical machine learning and the latest deep learning models. For the three-class classification, in the method achieves an accuracy, specificity, sensitivity, and ROC of 98%, 97.4, 98.3% and 96.8%, respectively. In binary classification, the method achieves better results, with ACC of 100%, 100%, and 99.8%, respectively. Our dual stream spatiotemporal hybrid network demonstrates superior performance compared to other methods. Notably, it eliminates the need for manual operations, making it more efficient for doctors to diagnose during the clinical process and alleviating the workload of neurologists.https://doi.org/10.1038/s41598-023-41537-z |
| spellingShingle | Xiashuang Wang Yinglei Wang Dunwei Liu Ying Wang Zhengjun Wang Automated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN-LSTM Scientific Reports |
| title | Automated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN-LSTM |
| title_full | Automated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN-LSTM |
| title_fullStr | Automated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN-LSTM |
| title_full_unstemmed | Automated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN-LSTM |
| title_short | Automated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN-LSTM |
| title_sort | automated recognition of epilepsy from eeg signals using a combining space time algorithm of cnn lstm |
| url | https://doi.org/10.1038/s41598-023-41537-z |
| work_keys_str_mv | AT xiashuangwang automatedrecognitionofepilepsyfromeegsignalsusingacombiningspacetimealgorithmofcnnlstm AT yingleiwang automatedrecognitionofepilepsyfromeegsignalsusingacombiningspacetimealgorithmofcnnlstm AT dunweiliu automatedrecognitionofepilepsyfromeegsignalsusingacombiningspacetimealgorithmofcnnlstm AT yingwang automatedrecognitionofepilepsyfromeegsignalsusingacombiningspacetimealgorithmofcnnlstm AT zhengjunwang automatedrecognitionofepilepsyfromeegsignalsusingacombiningspacetimealgorithmofcnnlstm |