A Deep Convolutional Neural Network Method to Detect Seizures and Characteristic Frequencies Using Epileptic Electroencephalogram (EEG) Data
Background: Diagnosing epileptic seizures using electroencephalogram (EEG) in combination with deep learning computational methods has received much attention in recent years. However, to date, deep learning techniques in seizure detection have not been effectively harnessed due to sub-optimal class...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Translational Engineering in Health and Medicine |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9319690/ |
| _version_ | 1831734988629868544 |
|---|---|
| author | Md. Rashed-Al-Mahfuz Mohammad Ali Moni Shahadat Uddin Salem A. Alyami Matthew A. Summers Valsamma Eapen |
| author_facet | Md. Rashed-Al-Mahfuz Mohammad Ali Moni Shahadat Uddin Salem A. Alyami Matthew A. Summers Valsamma Eapen |
| author_sort | Md. Rashed-Al-Mahfuz |
| collection | DOAJ |
| description | Background: Diagnosing epileptic seizures using electroencephalogram (EEG) in combination with deep learning computational methods has received much attention in recent years. However, to date, deep learning techniques in seizure detection have not been effectively harnessed due to sub-optimal classifier design and improper representation of the time-domain signal. Methods: In this study, we focused on designing and evaluating deep convolutional neural network-based classifiers for seizure detection. Signal-to-image conversion methods are proposed to convert time-domain EEG signal to a time-frequency represented image to prepare the input data for classification. We proposed and evaluated three classification methods comprising of five classifiers to determine which is more accurate for seizure detection. Accuracy data were then compared to previous studies of the same dataset. Results: We found our proposed model and signal-to-image conversion method outperformed all previous studies in the most cases. The proposed FT-VGG16 classifier achieved the highest average classification accuracy of 99.21%. In addition, the Shapley Additive exPlanations (SHAP) analysis approach was employed to uncover the feature frequencies in the EEG that contribute most to improved classification accuracy. To the best of our knowledge, this is the first study to compute the contribution of frequency components to target seizure classification; thus allowing the identification of distinct seizure-related EEG frequency components compared to normal EEG measures. Conclusion: Thus our developed deep convolutional neural network models are useful to detect seizures and characteristic frequencies using EEG data collected from the patients and this model could be clinically applicable for the automated seizures detection. |
| first_indexed | 2024-12-21T12:19:23Z |
| format | Article |
| id | doaj.art-6e4dafc099084d4fb8f86127c9010653 |
| institution | Directory Open Access Journal |
| issn | 2168-2372 |
| language | English |
| last_indexed | 2024-12-21T12:19:23Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Translational Engineering in Health and Medicine |
| spelling | doaj.art-6e4dafc099084d4fb8f86127c90106532022-12-21T19:04:21ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722021-01-01911210.1109/JTEHM.2021.30509259319690A Deep Convolutional Neural Network Method to Detect Seizures and Characteristic Frequencies Using Epileptic Electroencephalogram (EEG) DataMd. Rashed-Al-Mahfuz0https://orcid.org/0000-0001-7039-6176Mohammad Ali Moni1https://orcid.org/0000-0003-0756-1006Shahadat Uddin2https://orcid.org/0000-0003-0091-6919Salem A. Alyami3https://orcid.org/0000-0002-5507-9399Matthew A. Summers4Valsamma Eapen5Department of Computer Science and Engineering, University of Rajshahi, Rajshahi, BangladeshFaculty of Medicine, School of Psychiatry, University of New South Wales, Sydney, NSW, AustraliaComplex Systems Research Group, Faculty of Engineering, The University of Sydney, Darlington, NSW, AustraliaDepartment of Mathematics and Statistics, Imam Mohammad Ibn Saud Islamic University, Riyadh, Saudi ArabiaGarvan Institute of Medical Research, Darlinghurst, NSW, AustraliaFaculty of Medicine, School of Psychiatry, University of New South Wales, Sydney, NSW, AustraliaBackground: Diagnosing epileptic seizures using electroencephalogram (EEG) in combination with deep learning computational methods has received much attention in recent years. However, to date, deep learning techniques in seizure detection have not been effectively harnessed due to sub-optimal classifier design and improper representation of the time-domain signal. Methods: In this study, we focused on designing and evaluating deep convolutional neural network-based classifiers for seizure detection. Signal-to-image conversion methods are proposed to convert time-domain EEG signal to a time-frequency represented image to prepare the input data for classification. We proposed and evaluated three classification methods comprising of five classifiers to determine which is more accurate for seizure detection. Accuracy data were then compared to previous studies of the same dataset. Results: We found our proposed model and signal-to-image conversion method outperformed all previous studies in the most cases. The proposed FT-VGG16 classifier achieved the highest average classification accuracy of 99.21%. In addition, the Shapley Additive exPlanations (SHAP) analysis approach was employed to uncover the feature frequencies in the EEG that contribute most to improved classification accuracy. To the best of our knowledge, this is the first study to compute the contribution of frequency components to target seizure classification; thus allowing the identification of distinct seizure-related EEG frequency components compared to normal EEG measures. Conclusion: Thus our developed deep convolutional neural network models are useful to detect seizures and characteristic frequencies using EEG data collected from the patients and this model could be clinically applicable for the automated seizures detection.https://ieeexplore.ieee.org/document/9319690/EpilepsyseizureEEGdeep learningCWTSTFT |
| spellingShingle | Md. Rashed-Al-Mahfuz Mohammad Ali Moni Shahadat Uddin Salem A. Alyami Matthew A. Summers Valsamma Eapen A Deep Convolutional Neural Network Method to Detect Seizures and Characteristic Frequencies Using Epileptic Electroencephalogram (EEG) Data IEEE Journal of Translational Engineering in Health and Medicine Epilepsy seizure EEG deep learning CWT STFT |
| title | A Deep Convolutional Neural Network Method to Detect Seizures and Characteristic Frequencies Using Epileptic Electroencephalogram (EEG) Data |
| title_full | A Deep Convolutional Neural Network Method to Detect Seizures and Characteristic Frequencies Using Epileptic Electroencephalogram (EEG) Data |
| title_fullStr | A Deep Convolutional Neural Network Method to Detect Seizures and Characteristic Frequencies Using Epileptic Electroencephalogram (EEG) Data |
| title_full_unstemmed | A Deep Convolutional Neural Network Method to Detect Seizures and Characteristic Frequencies Using Epileptic Electroencephalogram (EEG) Data |
| title_short | A Deep Convolutional Neural Network Method to Detect Seizures and Characteristic Frequencies Using Epileptic Electroencephalogram (EEG) Data |
| title_sort | deep convolutional neural network method to detect seizures and characteristic frequencies using epileptic electroencephalogram eeg data |
| topic | Epilepsy seizure EEG deep learning CWT STFT |
| url | https://ieeexplore.ieee.org/document/9319690/ |
| work_keys_str_mv | AT mdrashedalmahfuz adeepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata AT mohammadalimoni adeepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata AT shahadatuddin adeepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata AT salemaalyami adeepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata AT matthewasummers adeepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata AT valsammaeapen adeepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata AT mdrashedalmahfuz deepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata AT mohammadalimoni deepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata AT shahadatuddin deepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata AT salemaalyami deepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata AT matthewasummers deepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata AT valsammaeapen deepconvolutionalneuralnetworkmethodtodetectseizuresandcharacteristicfrequenciesusingepilepticelectroencephalogrameegdata |