Investigation of semi- and self-supervised learning methods in the histopathological domain
Training models with semi- or self-supervised learning methods is one way to reduce annotation effort since they rely on unlabeled or sparsely labeled datasets. Such approaches are particularly promising for domains with a time-consuming annotation process requiring specialized expertise and where h...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | Journal of Pathology Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2153353923001190 |
| _version_ | 1827976034708881408 |
|---|---|
| author | Benjamin Voigt Oliver Fischer Bruno Schilling Christian Krumnow Christian Herta |
| author_facet | Benjamin Voigt Oliver Fischer Bruno Schilling Christian Krumnow Christian Herta |
| author_sort | Benjamin Voigt |
| collection | DOAJ |
| description | Training models with semi- or self-supervised learning methods is one way to reduce annotation effort since they rely on unlabeled or sparsely labeled datasets. Such approaches are particularly promising for domains with a time-consuming annotation process requiring specialized expertise and where high-quality labeled machine learning datasets are scarce, like in computational pathology. Even though some of these methods have been used in the histopathological domain, there is, so far, no comprehensive study comparing different approaches. Therefore, this work compares feature extractors models trained with state-of-the-art semi- or self-supervised learning methods PAWS, SimCLR, and SimSiam within a unified framework. We show that such models, across different architectures and network configurations, have a positive performance impact on histopathological classification tasks, even in low data regimes. Moreover, our observations suggest that features learned from a particular dataset, i.e., tissue type, are only in-domain transferable to a certain extent. Finally, we share our experience using each method in computational pathology and provide recommendations for its use. |
| first_indexed | 2024-04-09T20:21:00Z |
| format | Article |
| id | doaj.art-832664bd47be4d319de7a2eac106ab07 |
| institution | Directory Open Access Journal |
| issn | 2153-3539 |
| language | English |
| last_indexed | 2024-04-09T20:21:00Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Pathology Informatics |
| spelling | doaj.art-832664bd47be4d319de7a2eac106ab072023-03-31T05:53:11ZengElsevierJournal of Pathology Informatics2153-35392023-01-0114100305Investigation of semi- and self-supervised learning methods in the histopathological domainBenjamin Voigt0Oliver Fischer1Bruno Schilling2Christian Krumnow3Christian Herta4Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Charitéplatz 1, 10117 Berlin, Germany; University of Applied Sciences (HTW) Berlin, Center for Biomedical Image and Information Processing, Ostendstraße 25, 12459 Berlin, Germany; Corresponding author.Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Charitéplatz 1, 10117 Berlin, Germany; University of Applied Sciences (HTW) Berlin, Center for Biomedical Image and Information Processing, Ostendstraße 25, 12459 Berlin, GermanyUniversity of Applied Sciences (HTW) Berlin, Center for Biomedical Image and Information Processing, Ostendstraße 25, 12459 Berlin, GermanyUniversity of Applied Sciences (HTW) Berlin, Center for Biomedical Image and Information Processing, Ostendstraße 25, 12459 Berlin, GermanyUniversity of Applied Sciences (HTW) Berlin, Center for Biomedical Image and Information Processing, Ostendstraße 25, 12459 Berlin, GermanyTraining models with semi- or self-supervised learning methods is one way to reduce annotation effort since they rely on unlabeled or sparsely labeled datasets. Such approaches are particularly promising for domains with a time-consuming annotation process requiring specialized expertise and where high-quality labeled machine learning datasets are scarce, like in computational pathology. Even though some of these methods have been used in the histopathological domain, there is, so far, no comprehensive study comparing different approaches. Therefore, this work compares feature extractors models trained with state-of-the-art semi- or self-supervised learning methods PAWS, SimCLR, and SimSiam within a unified framework. We show that such models, across different architectures and network configurations, have a positive performance impact on histopathological classification tasks, even in low data regimes. Moreover, our observations suggest that features learned from a particular dataset, i.e., tissue type, are only in-domain transferable to a certain extent. Finally, we share our experience using each method in computational pathology and provide recommendations for its use.http://www.sciencedirect.com/science/article/pii/S2153353923001190Neural networksDeep learningSelf-supervised learningSemi-supervised learningComputational pathologyTissue analysis |
| spellingShingle | Benjamin Voigt Oliver Fischer Bruno Schilling Christian Krumnow Christian Herta Investigation of semi- and self-supervised learning methods in the histopathological domain Journal of Pathology Informatics Neural networks Deep learning Self-supervised learning Semi-supervised learning Computational pathology Tissue analysis |
| title | Investigation of semi- and self-supervised learning methods in the histopathological domain |
| title_full | Investigation of semi- and self-supervised learning methods in the histopathological domain |
| title_fullStr | Investigation of semi- and self-supervised learning methods in the histopathological domain |
| title_full_unstemmed | Investigation of semi- and self-supervised learning methods in the histopathological domain |
| title_short | Investigation of semi- and self-supervised learning methods in the histopathological domain |
| title_sort | investigation of semi and self supervised learning methods in the histopathological domain |
| topic | Neural networks Deep learning Self-supervised learning Semi-supervised learning Computational pathology Tissue analysis |
| url | http://www.sciencedirect.com/science/article/pii/S2153353923001190 |
| work_keys_str_mv | AT benjaminvoigt investigationofsemiandselfsupervisedlearningmethodsinthehistopathologicaldomain AT oliverfischer investigationofsemiandselfsupervisedlearningmethodsinthehistopathologicaldomain AT brunoschilling investigationofsemiandselfsupervisedlearningmethodsinthehistopathologicaldomain AT christiankrumnow investigationofsemiandselfsupervisedlearningmethodsinthehistopathologicaldomain AT christianherta investigationofsemiandselfsupervisedlearningmethodsinthehistopathologicaldomain |