Applying Self-Supervised Learning to Medicine: Review of the State of the Art and Medical Implementations
Machine learning has become an increasingly ubiquitous technology, as big data continues to inform and influence everyday life and decision-making. Currently, in medicine and healthcare, as well as in most other industries, the two most prevalent machine learning paradigms are supervised learning an...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Informatics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9709/8/3/59 |
| _version_ | 1797518834219876352 |
|---|---|
| author | Alexander Chowdhury Jacob Rosenthal Jonathan Waring Renato Umeton |
| author_facet | Alexander Chowdhury Jacob Rosenthal Jonathan Waring Renato Umeton |
| author_sort | Alexander Chowdhury |
| collection | DOAJ |
| description | Machine learning has become an increasingly ubiquitous technology, as big data continues to inform and influence everyday life and decision-making. Currently, in medicine and healthcare, as well as in most other industries, the two most prevalent machine learning paradigms are supervised learning and transfer learning. Both practices rely on large-scale, manually annotated datasets to train increasingly complex models. However, the requirement of data to be manually labeled leaves an excess of unused, unlabeled data available in both public and private data repositories. Self-supervised learning (SSL) is a growing area of machine learning that can take advantage of unlabeled data. Contrary to other machine learning paradigms, SSL algorithms create artificial supervisory signals from unlabeled data and pretrain algorithms on these signals. The aim of this review is two-fold: firstly, we provide a formal definition of SSL, divide SSL algorithms into their four unique subsets, and review the state of the art published in each of those subsets between the years of 2014 and 2020. Second, this work surveys recent SSL algorithms published in healthcare, in order to provide medical experts with a clearer picture of how they can integrate SSL into their research, with the objective of leveraging unlabeled data. |
| first_indexed | 2024-03-10T07:35:01Z |
| format | Article |
| id | doaj.art-92f2df9d103749ddbc425298e68f03e1 |
| institution | Directory Open Access Journal |
| issn | 2227-9709 |
| language | English |
| last_indexed | 2024-03-10T07:35:01Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Informatics |
| spelling | doaj.art-92f2df9d103749ddbc425298e68f03e12023-11-22T13:34:54ZengMDPI AGInformatics2227-97092021-09-01835910.3390/informatics8030059Applying Self-Supervised Learning to Medicine: Review of the State of the Art and Medical ImplementationsAlexander Chowdhury0Jacob Rosenthal1Jonathan Waring2Renato Umeton3Department of Informatics & Analytics, Dana-Farber Cancer Institute, Boston, MA 02215, USADepartment of Informatics & Analytics, Dana-Farber Cancer Institute, Boston, MA 02215, USADepartment of Informatics & Analytics, Dana-Farber Cancer Institute, Boston, MA 02215, USADepartment of Informatics & Analytics, Dana-Farber Cancer Institute, Boston, MA 02215, USAMachine learning has become an increasingly ubiquitous technology, as big data continues to inform and influence everyday life and decision-making. Currently, in medicine and healthcare, as well as in most other industries, the two most prevalent machine learning paradigms are supervised learning and transfer learning. Both practices rely on large-scale, manually annotated datasets to train increasingly complex models. However, the requirement of data to be manually labeled leaves an excess of unused, unlabeled data available in both public and private data repositories. Self-supervised learning (SSL) is a growing area of machine learning that can take advantage of unlabeled data. Contrary to other machine learning paradigms, SSL algorithms create artificial supervisory signals from unlabeled data and pretrain algorithms on these signals. The aim of this review is two-fold: firstly, we provide a formal definition of SSL, divide SSL algorithms into their four unique subsets, and review the state of the art published in each of those subsets between the years of 2014 and 2020. Second, this work surveys recent SSL algorithms published in healthcare, in order to provide medical experts with a clearer picture of how they can integrate SSL into their research, with the objective of leveraging unlabeled data.https://www.mdpi.com/2227-9709/8/3/59self-supervised learninghealthcarerepresentation learningmedicinecomputer visionpathology |
| spellingShingle | Alexander Chowdhury Jacob Rosenthal Jonathan Waring Renato Umeton Applying Self-Supervised Learning to Medicine: Review of the State of the Art and Medical Implementations Informatics self-supervised learning healthcare representation learning medicine computer vision pathology |
| title | Applying Self-Supervised Learning to Medicine: Review of the State of the Art and Medical Implementations |
| title_full | Applying Self-Supervised Learning to Medicine: Review of the State of the Art and Medical Implementations |
| title_fullStr | Applying Self-Supervised Learning to Medicine: Review of the State of the Art and Medical Implementations |
| title_full_unstemmed | Applying Self-Supervised Learning to Medicine: Review of the State of the Art and Medical Implementations |
| title_short | Applying Self-Supervised Learning to Medicine: Review of the State of the Art and Medical Implementations |
| title_sort | applying self supervised learning to medicine review of the state of the art and medical implementations |
| topic | self-supervised learning healthcare representation learning medicine computer vision pathology |
| url | https://www.mdpi.com/2227-9709/8/3/59 |
| work_keys_str_mv | AT alexanderchowdhury applyingselfsupervisedlearningtomedicinereviewofthestateoftheartandmedicalimplementations AT jacobrosenthal applyingselfsupervisedlearningtomedicinereviewofthestateoftheartandmedicalimplementations AT jonathanwaring applyingselfsupervisedlearningtomedicinereviewofthestateoftheartandmedicalimplementations AT renatoumeton applyingselfsupervisedlearningtomedicinereviewofthestateoftheartandmedicalimplementations |