Test-time augmentation for deep learning-based cell segmentation on microscopy images

Show simple item record

dc.contributor.author Moshkov, Nikita
dc.contributor.author Mathe, Botond
dc.contributor.author Kertesz-Farkas, Attila
dc.contributor.author Hollandi, Reka
dc.contributor.author Horvath, Peter
dc.date.accessioned 2020-09-02T06:28:06Z
dc.date.available 2020-09-02T06:28:06Z
dc.date.issued 2020-03-19
dc.identifier.citation Moshkov , N , Mathe , B , Kertesz-Farkas , A , Hollandi , R & Horvath , P 2020 , ' Test-time augmentation for deep learning-based cell segmentation on microscopy images ' , Scientific Reports , vol. 10 , no. 1 , 5068 . https://doi.org/10.1038/s41598-020-61808-3
dc.identifier.other PURE: 135706062
dc.identifier.other PURE UUID: 6dbbc46c-3051-4f1a-913d-646353a1e99e
dc.identifier.other RIS: urn:B32ED896B307278CA0FED23699B342B9
dc.identifier.other RIS: Moshkov2020
dc.identifier.other WOS: 000563443900007
dc.identifier.uri http://hdl.handle.net/10138/318953
dc.description.abstract Recent advancements in deep learning have revolutionized the way microscopy images of cells are processed. Deep learning network architectures have a large number of parameters, thus, in order to reach high accuracy, they require a massive amount of annotated data. A common way of improving accuracy builds on the artificial increase of the training set by using different augmentation techniques. A less common way relies on test-time augmentation (TTA) which yields transformed versions of the image for prediction and the results are merged. In this paper we describe how we have incorporated the test-time argumentation prediction method into two major segmentation approaches utilized in the single-cell analysis of microscopy images. These approaches are semantic segmentation based on the U-Net, and instance segmentation based on the Mask R-CNN models. Our findings show that even if only simple test-time augmentations (such as rotation or flipping and proper merging methods) are applied, TTA can significantly improve prediction accuracy. We have utilized images of tissue and cell cultures from the Data Science Bowl (DSB) 2018 nuclei segmentation competition and other sources. Additionally, boosting the highest-scoring method of the DSB with TTA, we could further improve prediction accuracy, and our method has reached an ever-best score at the DSB. en
dc.format.extent 7
dc.language.iso eng
dc.relation.ispartof Scientific Reports
dc.rights cc_by
dc.rights.uri info:eu-repo/semantics/openAccess
dc.subject 1182 Biochemistry, cell and molecular biology
dc.title Test-time augmentation for deep learning-based cell segmentation on microscopy images en
dc.type Article
dc.contributor.organization Institute for Molecular Medicine Finland
dc.contributor.organization University of Helsinki
dc.description.reviewstatus Peer reviewed
dc.relation.doi https://doi.org/10.1038/s41598-020-61808-3
dc.relation.issn 2045-2322
dc.rights.accesslevel openAccess
dc.type.version publishedVersion

Files in this item

Total number of downloads: Loading...

Files Size Format View
s41598_020_61808_3.pdf 1.779Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record