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

Näytä kaikki kuvailutiedot



Pysyväisosoite

http://hdl.handle.net/10138/318953

Lähdeviite

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

Julkaisun nimi: Test-time augmentation for deep learning-based cell segmentation on microscopy images
Tekijä: Moshkov, Nikita; Mathe, Botond; Kertesz-Farkas, Attila; Hollandi, Reka; Horvath, Peter
Tekijän organisaatio: Institute for Molecular Medicine Finland
University of Helsinki
Päiväys: 2020-03-19
Kieli: eng
Sivumäärä: 7
Kuuluu julkaisusarjaan: Scientific Reports
ISSN: 2045-2322
DOI-tunniste: https://doi.org/10.1038/s41598-020-61808-3
URI: http://hdl.handle.net/10138/318953
Tiivistelmä: 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.
Avainsanat: 1182 Biochemistry, cell and molecular biology
Vertaisarvioitu: Kyllä
Tekijänoikeustiedot: cc_by
Pääsyrajoitteet: openAccess
Rinnakkaistallennettu versio: publishedVersion


Tiedostot

Latausmäärä yhteensä: Ladataan...

Tiedosto(t) Koko Formaatti Näytä
s41598_020_61808_3.pdf 1.779MB PDF Avaa tiedosto

Viite kuuluu kokoelmiin:

Näytä kaikki kuvailutiedot