IC-U-Net: A U-Net-based Denoising Autoencoder Using Mixtures of Independent Components for Automatic EEG Artifact Removal
ABSTRACT: Electroencephalography (EEG) signals are often contaminated with artifacts. It is imperative to develop a practical and reliable artifact removal method to prevent the misinterpretation of neural signals and the underperformance of brain–computer interfaces. Based on the U-Net architecture...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811922007017 |
| _version_ | 1811192577975648256 |
|---|---|
| author | Chun-Hsiang Chuang Kong-Yi Chang Chih-Sheng Huang Tzyy-Ping Jung |
| author_facet | Chun-Hsiang Chuang Kong-Yi Chang Chih-Sheng Huang Tzyy-Ping Jung |
| author_sort | Chun-Hsiang Chuang |
| collection | DOAJ |
| description | ABSTRACT: Electroencephalography (EEG) signals are often contaminated with artifacts. It is imperative to develop a practical and reliable artifact removal method to prevent the misinterpretation of neural signals and the underperformance of brain–computer interfaces. Based on the U-Net architecture, we developed a new artifact removal model, IC-U-Net, for removing pervasive EEG artifacts and reconstructing brain signals. IC-U-Net was trained using mixtures of brain and non-brain components decomposed by independent component analysis. It uses an ensemble of loss functions to model complex signal fluctuations in EEG recordings. The effectiveness of the proposed method in recovering brain activities and removing various artifacts (e.g., eye blinks/movements, muscle activities, and line/channel noise) was demonstrated in a simulation study and four real-world EEG experiments. IC-U-Net can reconstruct a multi-channel EEG signal and is applicable to most artifact types, offering a promising end-to-end solution for automatically removing artifacts from EEG recordings. It also meets the increasing need to image natural brain dynamics in a mobile setting. The code and pre-trained IC-U-Net model are available at https://github.com/roseDwayane/AIEEG. |
| first_indexed | 2024-04-11T23:54:56Z |
| format | Article |
| id | doaj.art-2db39ce80d4a40fd8625063e50e431fb |
| institution | Directory Open Access Journal |
| issn | 1095-9572 |
| language | English |
| last_indexed | 2024-04-11T23:54:56Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj.art-2db39ce80d4a40fd8625063e50e431fb2022-12-22T03:56:23ZengElsevierNeuroImage1095-95722022-11-01263119586IC-U-Net: A U-Net-based Denoising Autoencoder Using Mixtures of Independent Components for Automatic EEG Artifact RemovalChun-Hsiang Chuang0Kong-Yi Chang1Chih-Sheng Huang2Tzyy-Ping Jung3Research Center for Education and Mind Sciences, College of Education, National Tsing Hua University, Hsinchu, Taiwan; Institute of Information Systems and Applications, College of Electrical Engineering and Computer Science, National Tsing Hua University, Hsinchu, Taiwan; Department of Education and Learning Technology, National Tsing Hua University, Hsinchu, Taiwan; Correspondence to: Dr. Chun-Hsiang Chuang, National Tsing Hua University, Hsinchu 300193, Taiwan.Research Center for Education and Mind Sciences, College of Education, National Tsing Hua University, Hsinchu, Taiwan; Institute of Information Systems and Applications, College of Electrical Engineering and Computer Science, National Tsing Hua University, Hsinchu, Taiwan; Department of Computer Science and Engineering, National Taiwan Ocean University, Keelung, Taiwan.Department of Artificial Intelligence Research and Development, Elan Microelectronics Corporation, Hsinchu, Taiwan; College of Artificial Intelligence and Green Energy, National Yang Ming Chiao Tung University, Hsinchu, Taiwan; College of Electrical Engineering and Computer Science, National Taipei University of Technology, Taipei, TaiwanInstitute of Engineering in Medicine and Institute for Neural Computation, University of California San Diego, La Jolla, USAABSTRACT: Electroencephalography (EEG) signals are often contaminated with artifacts. It is imperative to develop a practical and reliable artifact removal method to prevent the misinterpretation of neural signals and the underperformance of brain–computer interfaces. Based on the U-Net architecture, we developed a new artifact removal model, IC-U-Net, for removing pervasive EEG artifacts and reconstructing brain signals. IC-U-Net was trained using mixtures of brain and non-brain components decomposed by independent component analysis. It uses an ensemble of loss functions to model complex signal fluctuations in EEG recordings. The effectiveness of the proposed method in recovering brain activities and removing various artifacts (e.g., eye blinks/movements, muscle activities, and line/channel noise) was demonstrated in a simulation study and four real-world EEG experiments. IC-U-Net can reconstruct a multi-channel EEG signal and is applicable to most artifact types, offering a promising end-to-end solution for automatically removing artifacts from EEG recordings. It also meets the increasing need to image natural brain dynamics in a mobile setting. The code and pre-trained IC-U-Net model are available at https://github.com/roseDwayane/AIEEG.http://www.sciencedirect.com/science/article/pii/S1053811922007017EEGArtifact RemovalSignal ReconstructionU-NetIndependent Component AnalysisICLabel |
| spellingShingle | Chun-Hsiang Chuang Kong-Yi Chang Chih-Sheng Huang Tzyy-Ping Jung IC-U-Net: A U-Net-based Denoising Autoencoder Using Mixtures of Independent Components for Automatic EEG Artifact Removal NeuroImage EEG Artifact Removal Signal Reconstruction U-Net Independent Component Analysis ICLabel |
| title | IC-U-Net: A U-Net-based Denoising Autoencoder Using Mixtures of Independent Components for Automatic EEG Artifact Removal |
| title_full | IC-U-Net: A U-Net-based Denoising Autoencoder Using Mixtures of Independent Components for Automatic EEG Artifact Removal |
| title_fullStr | IC-U-Net: A U-Net-based Denoising Autoencoder Using Mixtures of Independent Components for Automatic EEG Artifact Removal |
| title_full_unstemmed | IC-U-Net: A U-Net-based Denoising Autoencoder Using Mixtures of Independent Components for Automatic EEG Artifact Removal |
| title_short | IC-U-Net: A U-Net-based Denoising Autoencoder Using Mixtures of Independent Components for Automatic EEG Artifact Removal |
| title_sort | ic u net a u net based denoising autoencoder using mixtures of independent components for automatic eeg artifact removal |
| topic | EEG Artifact Removal Signal Reconstruction U-Net Independent Component Analysis ICLabel |
| url | http://www.sciencedirect.com/science/article/pii/S1053811922007017 |
| work_keys_str_mv | AT chunhsiangchuang icunetaunetbaseddenoisingautoencoderusingmixturesofindependentcomponentsforautomaticeegartifactremoval AT kongyichang icunetaunetbaseddenoisingautoencoderusingmixturesofindependentcomponentsforautomaticeegartifactremoval AT chihshenghuang icunetaunetbaseddenoisingautoencoderusingmixturesofindependentcomponentsforautomaticeegartifactremoval AT tzyypingjung icunetaunetbaseddenoisingautoencoderusingmixturesofindependentcomponentsforautomaticeegartifactremoval |