Deep Learning Approach for Automatic Classification of Ocular and Cardiac Artifacts in MEG Data
We propose an artifact classification scheme based on a combined deep and convolutional neural network (DCNN) model, to automatically identify cardiac and ocular artifacts from neuromagnetic data, without the need for additional electrocardiogram (ECG) and electrooculogram (EOG) recordings. From ind...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-01-01
|
| Series: | Journal of Engineering |
| Online Access: | http://dx.doi.org/10.1155/2018/1350692 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832551681243480064 |
|---|---|
| author | Ahmad Hasasneh Nikolas Kampel Praveen Sripad N. Jon Shah Jürgen Dammers |
| author_facet | Ahmad Hasasneh Nikolas Kampel Praveen Sripad N. Jon Shah Jürgen Dammers |
| author_sort | Ahmad Hasasneh |
| collection | DOAJ |
| description | We propose an artifact classification scheme based on a combined deep and convolutional neural network (DCNN) model, to automatically identify cardiac and ocular artifacts from neuromagnetic data, without the need for additional electrocardiogram (ECG) and electrooculogram (EOG) recordings. From independent components, the model uses both the spatial and temporal information of the decomposed magnetoencephalography (MEG) data. In total, 7122 samples were used after data augmentation, in which task and nontask related MEG recordings from 48 subjects served as the database for this study. Artifact rejection was applied using the combined model, which achieved a sensitivity and specificity of 91.8% and 97.4%, respectively. The overall accuracy of the model was validated using a cross-validation test and revealed a median accuracy of 94.4%, indicating high reliability of the DCNN-based artifact removal in task and nontask related MEG experiments. The major advantages of the proposed method are as follows: (1) it is a fully automated and user independent workflow of artifact classification in MEG data; (2) once the model is trained there is no need for auxiliary signal recordings; (3) the flexibility in the model design and training allows for various modalities (MEG/EEG) and various sensor types. |
| format | Article |
| id | doaj-art-7ba7c605ab8d4f3881eab44b1af950dd |
| institution | Kabale University |
| issn | 2314-4904 2314-4912 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Engineering |
| spelling | doaj-art-7ba7c605ab8d4f3881eab44b1af950dd2025-02-03T06:00:53ZengWileyJournal of Engineering2314-49042314-49122018-01-01201810.1155/2018/13506921350692Deep Learning Approach for Automatic Classification of Ocular and Cardiac Artifacts in MEG DataAhmad Hasasneh0Nikolas Kampel1Praveen Sripad2N. Jon Shah3Jürgen Dammers4Information Technology Department, Palestine Ahliya University College, Bethlehem, West Bank, State of PalestineInstitute of Neurosciences and Medicine, Forschungszentrum Jülich GmbH, 52425 Jülich, GermanyInstitute of Neurosciences and Medicine, Forschungszentrum Jülich GmbH, 52425 Jülich, GermanyInstitute of Neurosciences and Medicine, Forschungszentrum Jülich GmbH, 52425 Jülich, GermanyInstitute of Neurosciences and Medicine, Forschungszentrum Jülich GmbH, 52425 Jülich, GermanyWe propose an artifact classification scheme based on a combined deep and convolutional neural network (DCNN) model, to automatically identify cardiac and ocular artifacts from neuromagnetic data, without the need for additional electrocardiogram (ECG) and electrooculogram (EOG) recordings. From independent components, the model uses both the spatial and temporal information of the decomposed magnetoencephalography (MEG) data. In total, 7122 samples were used after data augmentation, in which task and nontask related MEG recordings from 48 subjects served as the database for this study. Artifact rejection was applied using the combined model, which achieved a sensitivity and specificity of 91.8% and 97.4%, respectively. The overall accuracy of the model was validated using a cross-validation test and revealed a median accuracy of 94.4%, indicating high reliability of the DCNN-based artifact removal in task and nontask related MEG experiments. The major advantages of the proposed method are as follows: (1) it is a fully automated and user independent workflow of artifact classification in MEG data; (2) once the model is trained there is no need for auxiliary signal recordings; (3) the flexibility in the model design and training allows for various modalities (MEG/EEG) and various sensor types.http://dx.doi.org/10.1155/2018/1350692 |
| spellingShingle | Ahmad Hasasneh Nikolas Kampel Praveen Sripad N. Jon Shah Jürgen Dammers Deep Learning Approach for Automatic Classification of Ocular and Cardiac Artifacts in MEG Data Journal of Engineering |
| title | Deep Learning Approach for Automatic Classification of Ocular and Cardiac Artifacts in MEG Data |
| title_full | Deep Learning Approach for Automatic Classification of Ocular and Cardiac Artifacts in MEG Data |
| title_fullStr | Deep Learning Approach for Automatic Classification of Ocular and Cardiac Artifacts in MEG Data |
| title_full_unstemmed | Deep Learning Approach for Automatic Classification of Ocular and Cardiac Artifacts in MEG Data |
| title_short | Deep Learning Approach for Automatic Classification of Ocular and Cardiac Artifacts in MEG Data |
| title_sort | deep learning approach for automatic classification of ocular and cardiac artifacts in meg data |
| url | http://dx.doi.org/10.1155/2018/1350692 |
| work_keys_str_mv | AT ahmadhasasneh deeplearningapproachforautomaticclassificationofocularandcardiacartifactsinmegdata AT nikolaskampel deeplearningapproachforautomaticclassificationofocularandcardiacartifactsinmegdata AT praveensripad deeplearningapproachforautomaticclassificationofocularandcardiacartifactsinmegdata AT njonshah deeplearningapproachforautomaticclassificationofocularandcardiacartifactsinmegdata AT jurgendammers deeplearningapproachforautomaticclassificationofocularandcardiacartifactsinmegdata |