Applications of Self-Supervised Learning to Biomedical Signals: A Survey
Over the last decade, deep learning applications in biomedical research have exploded, demonstrating their ability to often outperform previous machine learning approaches in various tasks. However, training deep learning models for biomedical applications requires large amounts of data annotated by...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10365170/ |
| _version_ | 1797376389411766272 |
|---|---|
| author | Federico Del Pup Manfredo Atzori |
| author_facet | Federico Del Pup Manfredo Atzori |
| author_sort | Federico Del Pup |
| collection | DOAJ |
| description | Over the last decade, deep learning applications in biomedical research have exploded, demonstrating their ability to often outperform previous machine learning approaches in various tasks. However, training deep learning models for biomedical applications requires large amounts of data annotated by experts, whose collection is often time- and cost- prohibitive. Self-Supervised Learning (SSL) has emerged as a prominent solution for such problems, as it allows learning powerful representations from vast unlabeled data by producing supervisory signals directly from the data. The high number of recent works employing the self-supervised learning paradigm for the analysis of biomedical signals (biosignals) can make it difficult for researchers to have a complete picture of the current research state. Therefore, this paper aims at outlining and clarifying the state-of-the-art in the domain. The article: briefly summarizes the nature and acquisition modality of the main biosignals; introduces the self-supervised learning method, focusing on the different pretraining strategies; provides a concise overview of the works employing SSL for the analysis of different types of biosignals; provides an overall analysis of critical aspects to consider when employing SSL to biosignals, also highlighting current open challenges. The analysis of the scientific literature highlights the importance of SSL, confirming its potential to improve models’ performance and robustness, and to promote the integration of deep learning into clinical tasks. |
| first_indexed | 2024-03-08T19:37:50Z |
| format | Article |
| id | doaj.art-f5510244ff074a99a9cb8788146615f1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T19:37:50Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f5510244ff074a99a9cb8788146615f12023-12-26T00:06:52ZengIEEEIEEE Access2169-35362023-01-011114418014420310.1109/ACCESS.2023.334453110365170Applications of Self-Supervised Learning to Biomedical Signals: A SurveyFederico Del Pup0https://orcid.org/0009-0004-0698-962XManfredo Atzori1https://orcid.org/0000-0001-5397-2063Department of Information Engineering, University of Padua, Padua, ItalyDepartment of Neuroscience, University of Padua, Padua, ItalyOver the last decade, deep learning applications in biomedical research have exploded, demonstrating their ability to often outperform previous machine learning approaches in various tasks. However, training deep learning models for biomedical applications requires large amounts of data annotated by experts, whose collection is often time- and cost- prohibitive. Self-Supervised Learning (SSL) has emerged as a prominent solution for such problems, as it allows learning powerful representations from vast unlabeled data by producing supervisory signals directly from the data. The high number of recent works employing the self-supervised learning paradigm for the analysis of biomedical signals (biosignals) can make it difficult for researchers to have a complete picture of the current research state. Therefore, this paper aims at outlining and clarifying the state-of-the-art in the domain. The article: briefly summarizes the nature and acquisition modality of the main biosignals; introduces the self-supervised learning method, focusing on the different pretraining strategies; provides a concise overview of the works employing SSL for the analysis of different types of biosignals; provides an overall analysis of critical aspects to consider when employing SSL to biosignals, also highlighting current open challenges. The analysis of the scientific literature highlights the importance of SSL, confirming its potential to improve models’ performance and robustness, and to promote the integration of deep learning into clinical tasks.https://ieeexplore.ieee.org/document/10365170/Biosignalscontrastive learning (CL)deep learning (DL)electrocardiography (ECG)electroencephalography (EEG)electromyography (EMG) |
| spellingShingle | Federico Del Pup Manfredo Atzori Applications of Self-Supervised Learning to Biomedical Signals: A Survey IEEE Access Biosignals contrastive learning (CL) deep learning (DL) electrocardiography (ECG) electroencephalography (EEG) electromyography (EMG) |
| title | Applications of Self-Supervised Learning to Biomedical Signals: A Survey |
| title_full | Applications of Self-Supervised Learning to Biomedical Signals: A Survey |
| title_fullStr | Applications of Self-Supervised Learning to Biomedical Signals: A Survey |
| title_full_unstemmed | Applications of Self-Supervised Learning to Biomedical Signals: A Survey |
| title_short | Applications of Self-Supervised Learning to Biomedical Signals: A Survey |
| title_sort | applications of self supervised learning to biomedical signals a survey |
| topic | Biosignals contrastive learning (CL) deep learning (DL) electrocardiography (ECG) electroencephalography (EEG) electromyography (EMG) |
| url | https://ieeexplore.ieee.org/document/10365170/ |
| work_keys_str_mv | AT federicodelpup applicationsofselfsupervisedlearningtobiomedicalsignalsasurvey AT manfredoatzori applicationsofselfsupervisedlearningtobiomedicalsignalsasurvey |