Identification of Epileptogenic and Non-epileptogenic High-Frequency Oscillations Using a Multi-Feature Convolutional Neural Network Model
Accurately identifying epileptogenic zone (EZ) using high-frequency oscillations (HFOs) is a challenge that must be mastered to transfer HFOs into clinical use. We analyzed the ability of a convolutional neural network (CNN) model to distinguish EZ and non-EZ HFOs. Nineteen medically intractable epi...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-10-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2021.640526/full |
| _version_ | 1818581531636006912 |
|---|---|
| author | Guoping Ren Guoping Ren Yueqian Sun Yueqian Sun Yueqian Sun Dan Wang Jiechuan Ren Jiechuan Ren Jindong Dai Shanshan Mei Yunlin Li Xiaofei Wang Xiaofeng Yang Jiaqing Yan Qun Wang Qun Wang Qun Wang |
| author_facet | Guoping Ren Guoping Ren Yueqian Sun Yueqian Sun Yueqian Sun Dan Wang Jiechuan Ren Jiechuan Ren Jindong Dai Shanshan Mei Yunlin Li Xiaofei Wang Xiaofeng Yang Jiaqing Yan Qun Wang Qun Wang Qun Wang |
| author_sort | Guoping Ren |
| collection | DOAJ |
| description | Accurately identifying epileptogenic zone (EZ) using high-frequency oscillations (HFOs) is a challenge that must be mastered to transfer HFOs into clinical use. We analyzed the ability of a convolutional neural network (CNN) model to distinguish EZ and non-EZ HFOs. Nineteen medically intractable epilepsy patients with good surgical outcomes 2 years after surgery were studied. Five-minute interictal intracranial electroencephalogram epochs of slow-wave sleep were selected randomly. Then 5 s segments of ripples (80–200 Hz) and fast ripples (FRs, 200–500 Hz) were detected automatically. The EZs and non-EZs were identified using the surgery resection range. We innovatively converted all epochs into four types of images using two scales: original waveforms, filtered waveforms, wavelet spectrum images, and smoothed pseudo Wigner–Ville distribution (SPWVD) spectrum images. Two scales were fixed and fitted scales. We then used a CNN model to classify the HFOs into EZ and non-EZ categories. As a result, 7,000 epochs of ripples and 2,000 epochs of FRs were randomly selected from the EZ and non-EZ data for analysis. Our CNN model can distinguish EZ and non-EZ HFOs successfully. Except for original ripple waveforms, the results from CNN models that are trained using fixed-scale images are significantly better than those from models trained using fitted-scale images (p < 0.05). Of the four fixed-scale transformations, the CNN based on the adjusted SPWVD (ASPWVD) produced the best accuracies (80.89 ± 1.43% and 77.85 ± 1.61% for ripples and FRs, respectively, p < 0.05). The CNN using ASPWVD transformation images is an effective deep learning method that can be used to classify EZ and non-EZ HFOs. |
| first_indexed | 2024-12-16T07:34:58Z |
| format | Article |
| id | doaj.art-d2e5b907e6264dc5b4bb7eb6f05f7172 |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-12-16T07:34:58Z |
| publishDate | 2021-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-d2e5b907e6264dc5b4bb7eb6f05f71722022-12-21T22:39:16ZengFrontiers Media S.A.Frontiers in Neurology1664-22952021-10-011210.3389/fneur.2021.640526640526Identification of Epileptogenic and Non-epileptogenic High-Frequency Oscillations Using a Multi-Feature Convolutional Neural Network ModelGuoping Ren0Guoping Ren1Yueqian Sun2Yueqian Sun3Yueqian Sun4Dan Wang5Jiechuan Ren6Jiechuan Ren7Jindong Dai8Shanshan Mei9Yunlin Li10Xiaofei Wang11Xiaofeng Yang12Jiaqing Yan13Qun Wang14Qun Wang15Qun Wang16Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaChina National Clinical Research Center for Neurological Diseases, Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaChina National Clinical Research Center for Neurological Diseases, Beijing, ChinaCollaborative Innovation Center for Brain Disorders, Beijing Institute of Brain Disorders, Capital Medical University, Beijing, ChinaDepartment of Neurology, Xingtai People's Hospital, Hebei, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaChina National Clinical Research Center for Neurological Diseases, Beijing, ChinaDepartment of Functional Neurosurgery, Beijing Haidian Hospital, Beijing, ChinaDepartment of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, ChinaDepartment of Neurosurgery, Capital Institute of Pediatrics, Children's Hospital, Beijing, ChinaDepartment of Neurology, National Center for Children's Health, Beijing Children's Hospital, Capital Medical University, Beijing, ChinaGuangzhou Laboratory, Guangzhou, China0College of Electrical and Control Engineering, North China University of Technology, Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaChina National Clinical Research Center for Neurological Diseases, Beijing, ChinaCollaborative Innovation Center for Brain Disorders, Beijing Institute of Brain Disorders, Capital Medical University, Beijing, ChinaAccurately identifying epileptogenic zone (EZ) using high-frequency oscillations (HFOs) is a challenge that must be mastered to transfer HFOs into clinical use. We analyzed the ability of a convolutional neural network (CNN) model to distinguish EZ and non-EZ HFOs. Nineteen medically intractable epilepsy patients with good surgical outcomes 2 years after surgery were studied. Five-minute interictal intracranial electroencephalogram epochs of slow-wave sleep were selected randomly. Then 5 s segments of ripples (80–200 Hz) and fast ripples (FRs, 200–500 Hz) were detected automatically. The EZs and non-EZs were identified using the surgery resection range. We innovatively converted all epochs into four types of images using two scales: original waveforms, filtered waveforms, wavelet spectrum images, and smoothed pseudo Wigner–Ville distribution (SPWVD) spectrum images. Two scales were fixed and fitted scales. We then used a CNN model to classify the HFOs into EZ and non-EZ categories. As a result, 7,000 epochs of ripples and 2,000 epochs of FRs were randomly selected from the EZ and non-EZ data for analysis. Our CNN model can distinguish EZ and non-EZ HFOs successfully. Except for original ripple waveforms, the results from CNN models that are trained using fixed-scale images are significantly better than those from models trained using fitted-scale images (p < 0.05). Of the four fixed-scale transformations, the CNN based on the adjusted SPWVD (ASPWVD) produced the best accuracies (80.89 ± 1.43% and 77.85 ± 1.61% for ripples and FRs, respectively, p < 0.05). The CNN using ASPWVD transformation images is an effective deep learning method that can be used to classify EZ and non-EZ HFOs.https://www.frontiersin.org/articles/10.3389/fneur.2021.640526/fullhigh frequency oscillationsepileptogenic zoneconvolutional neural networkadjusted smoothed pseudo Wigner–Ville distributionrefractory focal epilepsy |
| spellingShingle | Guoping Ren Guoping Ren Yueqian Sun Yueqian Sun Yueqian Sun Dan Wang Jiechuan Ren Jiechuan Ren Jindong Dai Shanshan Mei Yunlin Li Xiaofei Wang Xiaofeng Yang Jiaqing Yan Qun Wang Qun Wang Qun Wang Identification of Epileptogenic and Non-epileptogenic High-Frequency Oscillations Using a Multi-Feature Convolutional Neural Network Model Frontiers in Neurology high frequency oscillations epileptogenic zone convolutional neural network adjusted smoothed pseudo Wigner–Ville distribution refractory focal epilepsy |
| title | Identification of Epileptogenic and Non-epileptogenic High-Frequency Oscillations Using a Multi-Feature Convolutional Neural Network Model |
| title_full | Identification of Epileptogenic and Non-epileptogenic High-Frequency Oscillations Using a Multi-Feature Convolutional Neural Network Model |
| title_fullStr | Identification of Epileptogenic and Non-epileptogenic High-Frequency Oscillations Using a Multi-Feature Convolutional Neural Network Model |
| title_full_unstemmed | Identification of Epileptogenic and Non-epileptogenic High-Frequency Oscillations Using a Multi-Feature Convolutional Neural Network Model |
| title_short | Identification of Epileptogenic and Non-epileptogenic High-Frequency Oscillations Using a Multi-Feature Convolutional Neural Network Model |
| title_sort | identification of epileptogenic and non epileptogenic high frequency oscillations using a multi feature convolutional neural network model |
| topic | high frequency oscillations epileptogenic zone convolutional neural network adjusted smoothed pseudo Wigner–Ville distribution refractory focal epilepsy |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2021.640526/full |
| work_keys_str_mv | AT guopingren identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT guopingren identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT yueqiansun identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT yueqiansun identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT yueqiansun identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT danwang identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT jiechuanren identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT jiechuanren identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT jindongdai identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT shanshanmei identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT yunlinli identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT xiaofeiwang identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT xiaofengyang identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT jiaqingyan identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT qunwang identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT qunwang identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel AT qunwang identificationofepileptogenicandnonepileptogenichighfrequencyoscillationsusingamultifeatureconvolutionalneuralnetworkmodel |