Automatic Detection of Scalp High-Frequency Oscillations Based on Deep Learning
Scalp high-frequency oscillations (sHFOs) are a promising non-invasive biomarker of epilepsy. However, the visual marking of sHFOs is a time-consuming and subjective process, existing automatic detectors based on single-dimensional analysis have difficulty with accurately eliminating artifacts and t...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10500367/ |
| _version_ | 1797197362546868224 |
|---|---|
| author | Yutang Li Dezhi Cao Junda Qu Wei Wang Xinhui Xu Lingyu Kong Jianxiang Liao Wenhan Hu Kai Zhang Jihan Wang Chunlin Li Xiaofeng Yang Xu Zhang |
| author_facet | Yutang Li Dezhi Cao Junda Qu Wei Wang Xinhui Xu Lingyu Kong Jianxiang Liao Wenhan Hu Kai Zhang Jihan Wang Chunlin Li Xiaofeng Yang Xu Zhang |
| author_sort | Yutang Li |
| collection | DOAJ |
| description | Scalp high-frequency oscillations (sHFOs) are a promising non-invasive biomarker of epilepsy. However, the visual marking of sHFOs is a time-consuming and subjective process, existing automatic detectors based on single-dimensional analysis have difficulty with accurately eliminating artifacts and thus do not provide sufficient reliability to meet clinical needs. Therefore, we propose a high-performance sHFOs detector based on a deep learning algorithm. An initial detection module was designed to extract candidate high-frequency oscillations. Then, one-dimensional (1D) and two-dimensional (2D) deep learning models were designed, respectively. Finally, the weighted voting method is used to combine the outputs of the two model. In experiments, the precision, recall, specificity and F1-score were 83.44%, 83.60%, 96.61% and 83.42%, respectively, on average and the kappa coefficient was 80.02%. In addition, the proposed detector showed a stable performance on multi-centre datasets. Our sHFOs detector demonstrated high robustness and generalisation ability, which indicates its potential applicability as a clinical assistance tool. The proposed sHFOs detector achieves an accurate and robust method via deep learning algorithm. |
| first_indexed | 2024-04-24T06:42:46Z |
| format | Article |
| id | doaj.art-ed59fe2013fc4a75a18beb6a85358b1a |
| institution | Directory Open Access Journal |
| issn | 1534-4320 1558-0210 |
| language | English |
| last_indexed | 2024-04-24T06:42:46Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-ed59fe2013fc4a75a18beb6a85358b1a2024-04-22T23:00:07ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102024-01-01321627163610.1109/TNSRE.2024.338901010500367Automatic Detection of Scalp High-Frequency Oscillations Based on Deep LearningYutang Li0https://orcid.org/0000-0003-1378-3916Dezhi Cao1Junda Qu2https://orcid.org/0000-0001-8714-0900Wei Wang3Xinhui Xu4Lingyu Kong5Jianxiang Liao6Wenhan Hu7Kai Zhang8Jihan Wang9Chunlin Li10Xiaofeng Yang11Xu Zhang12https://orcid.org/0000-0002-4354-5591School of Biomedical Engineering, Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Capital Medical University, Beijing, ChinaDepartment of Neurology, Shenzhen Children’s Hospital, Shenzhen, ChinaSchool of Biomedical Engineering, Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Capital Medical University, Beijing, ChinaSchool of Biomedical Engineering, Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Capital Medical University, Beijing, ChinaDepartment of Neurology, Shenzhen Children’s Hospital, Shenzhen, ChinaDepartment of Neurology, Shenzhen Children’s Hospital, Shenzhen, ChinaDepartment of Neurology, Shenzhen Children’s Hospital, Shenzhen, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaSchool of Biomedical Engineering, Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Capital Medical University, Beijing, ChinaSchool of Biomedical Engineering, Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Capital Medical University, Beijing, ChinaSchool of Biomedical Engineering, Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Capital Medical University, Beijing, ChinaGuangzhou Laboratory, Guangzhou, ChinaSchool of Biomedical Engineering, Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Capital Medical University, Beijing, ChinaScalp high-frequency oscillations (sHFOs) are a promising non-invasive biomarker of epilepsy. However, the visual marking of sHFOs is a time-consuming and subjective process, existing automatic detectors based on single-dimensional analysis have difficulty with accurately eliminating artifacts and thus do not provide sufficient reliability to meet clinical needs. Therefore, we propose a high-performance sHFOs detector based on a deep learning algorithm. An initial detection module was designed to extract candidate high-frequency oscillations. Then, one-dimensional (1D) and two-dimensional (2D) deep learning models were designed, respectively. Finally, the weighted voting method is used to combine the outputs of the two model. In experiments, the precision, recall, specificity and F1-score were 83.44%, 83.60%, 96.61% and 83.42%, respectively, on average and the kappa coefficient was 80.02%. In addition, the proposed detector showed a stable performance on multi-centre datasets. Our sHFOs detector demonstrated high robustness and generalisation ability, which indicates its potential applicability as a clinical assistance tool. The proposed sHFOs detector achieves an accurate and robust method via deep learning algorithm.https://ieeexplore.ieee.org/document/10500367/Deep learningepilepsyscalp electroencephalographyscalp high-frequency oscillations |
| spellingShingle | Yutang Li Dezhi Cao Junda Qu Wei Wang Xinhui Xu Lingyu Kong Jianxiang Liao Wenhan Hu Kai Zhang Jihan Wang Chunlin Li Xiaofeng Yang Xu Zhang Automatic Detection of Scalp High-Frequency Oscillations Based on Deep Learning IEEE Transactions on Neural Systems and Rehabilitation Engineering Deep learning epilepsy scalp electroencephalography scalp high-frequency oscillations |
| title | Automatic Detection of Scalp High-Frequency Oscillations Based on Deep Learning |
| title_full | Automatic Detection of Scalp High-Frequency Oscillations Based on Deep Learning |
| title_fullStr | Automatic Detection of Scalp High-Frequency Oscillations Based on Deep Learning |
| title_full_unstemmed | Automatic Detection of Scalp High-Frequency Oscillations Based on Deep Learning |
| title_short | Automatic Detection of Scalp High-Frequency Oscillations Based on Deep Learning |
| title_sort | automatic detection of scalp high frequency oscillations based on deep learning |
| topic | Deep learning epilepsy scalp electroencephalography scalp high-frequency oscillations |
| url | https://ieeexplore.ieee.org/document/10500367/ |
| work_keys_str_mv | AT yutangli automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT dezhicao automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT jundaqu automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT weiwang automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT xinhuixu automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT lingyukong automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT jianxiangliao automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT wenhanhu automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT kaizhang automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT jihanwang automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT chunlinli automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT xiaofengyang automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning AT xuzhang automaticdetectionofscalphighfrequencyoscillationsbasedondeeplearning |