Robust Colon Tissue Cartography with Semi-Supervision
We explore the task of tissue classification for colon cancer histology in a low label regime comparing a semi-supervised and a supervised learning strategy in a series of experiments. Further, we investigate the model robustness w.r.t. distribution shifts in the unlabeled data and domain shifts acr...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2022-09-01
|
| Series: | Current Directions in Biomedical Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/cdbme-2022-1088 |
| _version_ | 1798013996026036224 |
|---|---|
| author | Dexl Jakob Benz Michaela Kuritcyn Petr Wittenberg Thomas Bruns Volker Geppert Carol Hartmann Arndt Bischl Bernd Goschenhofer Jann |
| author_facet | Dexl Jakob Benz Michaela Kuritcyn Petr Wittenberg Thomas Bruns Volker Geppert Carol Hartmann Arndt Bischl Bernd Goschenhofer Jann |
| author_sort | Dexl Jakob |
| collection | DOAJ |
| description | We explore the task of tissue classification for colon cancer histology in a low label regime comparing a semi-supervised and a supervised learning strategy in a series of experiments. Further, we investigate the model robustness w.r.t. distribution shifts in the unlabeled data and domain shifts across different scanners to prove their practicality in a histology context. By utilizing unlabeled data in addition to nl = 1000 labeled tiles per class, we yield a substantial increase in accuracy from 89.9% to 91.4%. |
| first_indexed | 2024-04-11T15:11:36Z |
| format | Article |
| id | doaj.art-3a436ac07def4f1294c9db3081cb1688 |
| institution | Directory Open Access Journal |
| issn | 2364-5504 |
| language | English |
| last_indexed | 2024-04-11T15:11:36Z |
| publishDate | 2022-09-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Current Directions in Biomedical Engineering |
| spelling | doaj.art-3a436ac07def4f1294c9db3081cb16882022-12-22T04:16:38ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042022-09-018234434710.1515/cdbme-2022-1088Robust Colon Tissue Cartography with Semi-SupervisionDexl Jakob0Benz Michaela1Kuritcyn Petr2Wittenberg Thomas3Bruns Volker4Geppert Carol5Hartmann Arndt6Bischl Bernd7Goschenhofer Jann8Fraunhofer Institute for Integrated Circuits IIS, Am Wolfsmantel 33,Erlangen, GermanyFraunhofer Institute for Integrated Circuits IIS, Am Wolfsmantel 33,Erlangen, GermanyFraunhofer Institute for Integrated Circuits IIS, Am Wolfsmantel 33,Erlangen, GermanyFraunhofer Institute for Integrated Circuits IIS, Am Wolfsmantel 33,Erlangen, GermanyFraunhofer Institute for Integrated Circuits IIS, Am Wolfsmantel 33,Erlangen, GermanyInstitut fur Pathologie, Universitatsklinikum Erlangen; Friedrich-Alexander-Universitat (FAU),Erlangen-Nurnberg, GermanyInstitut fur Pathologie, Universitatsklinikum Erlangen; Friedrich-Alexander-Universitat (FAU),Erlangen-Nurnberg, GermanyDepartment of Statistics, Ludwig-Maximilians-Universitat,Munich, GermanyDepartment of Statistics, Ludwig-Maximilians-Universitat,Munich, GermanyWe explore the task of tissue classification for colon cancer histology in a low label regime comparing a semi-supervised and a supervised learning strategy in a series of experiments. Further, we investigate the model robustness w.r.t. distribution shifts in the unlabeled data and domain shifts across different scanners to prove their practicality in a histology context. By utilizing unlabeled data in addition to nl = 1000 labeled tiles per class, we yield a substantial increase in accuracy from 89.9% to 91.4%.https://doi.org/10.1515/cdbme-2022-1088computational pathologysemi-supervised learningcolon cancermodel robustness |
| spellingShingle | Dexl Jakob Benz Michaela Kuritcyn Petr Wittenberg Thomas Bruns Volker Geppert Carol Hartmann Arndt Bischl Bernd Goschenhofer Jann Robust Colon Tissue Cartography with Semi-Supervision Current Directions in Biomedical Engineering computational pathology semi-supervised learning colon cancer model robustness |
| title | Robust Colon Tissue Cartography with Semi-Supervision |
| title_full | Robust Colon Tissue Cartography with Semi-Supervision |
| title_fullStr | Robust Colon Tissue Cartography with Semi-Supervision |
| title_full_unstemmed | Robust Colon Tissue Cartography with Semi-Supervision |
| title_short | Robust Colon Tissue Cartography with Semi-Supervision |
| title_sort | robust colon tissue cartography with semi supervision |
| topic | computational pathology semi-supervised learning colon cancer model robustness |
| url | https://doi.org/10.1515/cdbme-2022-1088 |
| work_keys_str_mv | AT dexljakob robustcolontissuecartographywithsemisupervision AT benzmichaela robustcolontissuecartographywithsemisupervision AT kuritcynpetr robustcolontissuecartographywithsemisupervision AT wittenbergthomas robustcolontissuecartographywithsemisupervision AT brunsvolker robustcolontissuecartographywithsemisupervision AT geppertcarol robustcolontissuecartographywithsemisupervision AT hartmannarndt robustcolontissuecartographywithsemisupervision AT bischlbernd robustcolontissuecartographywithsemisupervision AT goschenhoferjann robustcolontissuecartographywithsemisupervision |