A Cluster-then-label Semi-supervised Learning Approach for Pathology Image Classification
Abstract Completely labeled pathology datasets are often challenging and time-consuming to obtain. Semi-supervised learning (SSL) methods are able to learn from fewer labeled data points with the help of a large number of unlabeled data points. In this paper, we investigated the possibility of using...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2018
|
Materias: | |
Acceso en línea: | https://doaj.org/article/792b44f9bc9942699642a822cd3b0d25 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:792b44f9bc9942699642a822cd3b0d25 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:792b44f9bc9942699642a822cd3b0d252021-12-02T16:07:51ZA Cluster-then-label Semi-supervised Learning Approach for Pathology Image Classification10.1038/s41598-018-24876-02045-2322https://doaj.org/article/792b44f9bc9942699642a822cd3b0d252018-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-018-24876-0https://doaj.org/toc/2045-2322Abstract Completely labeled pathology datasets are often challenging and time-consuming to obtain. Semi-supervised learning (SSL) methods are able to learn from fewer labeled data points with the help of a large number of unlabeled data points. In this paper, we investigated the possibility of using clustering analysis to identify the underlying structure of the data space for SSL. A cluster-then-label method was proposed to identify high-density regions in the data space which were then used to help a supervised SVM in finding the decision boundary. We have compared our method with other supervised and semi-supervised state-of-the-art techniques using two different classification tasks applied to breast pathology datasets. We found that compared with other state-of-the-art supervised and semi-supervised methods, our SSL method is able to improve classification performance when a limited number of labeled data instances are made available. We also showed that it is important to examine the underlying distribution of the data space before applying SSL techniques to ensure semi-supervised learning assumptions are not violated by the data.Mohammad PeikariSherine SalamaSharon Nofech-MozesAnne L. MartelNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 8, Iss 1, Pp 1-13 (2018) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Mohammad Peikari Sherine Salama Sharon Nofech-Mozes Anne L. Martel A Cluster-then-label Semi-supervised Learning Approach for Pathology Image Classification |
description |
Abstract Completely labeled pathology datasets are often challenging and time-consuming to obtain. Semi-supervised learning (SSL) methods are able to learn from fewer labeled data points with the help of a large number of unlabeled data points. In this paper, we investigated the possibility of using clustering analysis to identify the underlying structure of the data space for SSL. A cluster-then-label method was proposed to identify high-density regions in the data space which were then used to help a supervised SVM in finding the decision boundary. We have compared our method with other supervised and semi-supervised state-of-the-art techniques using two different classification tasks applied to breast pathology datasets. We found that compared with other state-of-the-art supervised and semi-supervised methods, our SSL method is able to improve classification performance when a limited number of labeled data instances are made available. We also showed that it is important to examine the underlying distribution of the data space before applying SSL techniques to ensure semi-supervised learning assumptions are not violated by the data. |
format |
article |
author |
Mohammad Peikari Sherine Salama Sharon Nofech-Mozes Anne L. Martel |
author_facet |
Mohammad Peikari Sherine Salama Sharon Nofech-Mozes Anne L. Martel |
author_sort |
Mohammad Peikari |
title |
A Cluster-then-label Semi-supervised Learning Approach for Pathology Image Classification |
title_short |
A Cluster-then-label Semi-supervised Learning Approach for Pathology Image Classification |
title_full |
A Cluster-then-label Semi-supervised Learning Approach for Pathology Image Classification |
title_fullStr |
A Cluster-then-label Semi-supervised Learning Approach for Pathology Image Classification |
title_full_unstemmed |
A Cluster-then-label Semi-supervised Learning Approach for Pathology Image Classification |
title_sort |
cluster-then-label semi-supervised learning approach for pathology image classification |
publisher |
Nature Portfolio |
publishDate |
2018 |
url |
https://doaj.org/article/792b44f9bc9942699642a822cd3b0d25 |
work_keys_str_mv |
AT mohammadpeikari aclusterthenlabelsemisupervisedlearningapproachforpathologyimageclassification AT sherinesalama aclusterthenlabelsemisupervisedlearningapproachforpathologyimageclassification AT sharonnofechmozes aclusterthenlabelsemisupervisedlearningapproachforpathologyimageclassification AT annelmartel aclusterthenlabelsemisupervisedlearningapproachforpathologyimageclassification AT mohammadpeikari clusterthenlabelsemisupervisedlearningapproachforpathologyimageclassification AT sherinesalama clusterthenlabelsemisupervisedlearningapproachforpathologyimageclassification AT sharonnofechmozes clusterthenlabelsemisupervisedlearningapproachforpathologyimageclassification AT annelmartel clusterthenlabelsemisupervisedlearningapproachforpathologyimageclassification |
_version_ |
1718384724290830336 |