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

Show full item record



Permalink

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

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

Title: Test-time augmentation for deep learning-based cell segmentation on microscopy images
Author: Moshkov, Nikita; Mathe, Botond; Kertesz-Farkas, Attila; Hollandi, Reka; Horvath, Peter
Contributor: University of Helsinki, Institute for Molecular Medicine Finland
Date: 2020-03-19
Language: eng
Number of pages: 7
Belongs to series: Scientific Reports
ISSN: 2045-2322
URI: http://hdl.handle.net/10138/318953
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.
Subject: 1182 Biochemistry, cell and molecular biology
Rights:


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 full item record