Browse by author
Lookup NU author(s): Dr Eleni Karinou, Dr Seamus Holden
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
© 2021, The Author(s).Deep Learning (DL) methods are powerful analytical tools for microscopy and can outperform conventional image processing pipelines. Despite the enthusiasm and innovations fuelled by DL technology, the need to access powerful and compatible resources to train DL networks leads to an accessibility barrier that novice users often find difficult to overcome. Here, we present ZeroCostDL4Mic, an entry-level platform simplifying DL access by leveraging the free, cloud-based computational resources of Google Colab. ZeroCostDL4Mic allows researchers with no coding expertise to train and apply key DL networks to perform tasks including segmentation (using U-Net and StarDist), object detection (using YOLOv2), denoising (using CARE and Noise2Void), super-resolution microscopy (using Deep-STORM), and image-to-image translation (using Label-free prediction - fnet, pix2pix and CycleGAN). Importantly, we provide suitable quantitative tools for each network to evaluate model performance, allowing model optimisation. We demonstrate the application of the platform to study multiple biological processes.
Author(s): von Chamier L, Laine RF, Jukkala J, Spahn C, Krentzel D, Nehme E, Lerche M, Hernandez-Perez S, Mattila PK, Karinou E, Holden S, Solak AC, Krull A, Buchholz T-O, Jones ML, Royer LA, Leterrier C, Shechtman Y, Jug F, Heilemann M, Jacquemet G, Henriques R
Publication type: Article
Publication status: Published
Journal: Nature Communications
Year: 2021
Volume: 12
Issue: 1
Print publication date: 01/12/2021
Online publication date: 15/04/2021
Acceptance date: 10/03/2021
Date deposited: 06/05/2021
ISSN (electronic): 2041-1723
Publisher: Nature Research
URL: https://doi.org/10.1038/s41467-021-22518-0
DOI: 10.1038/s41467-021-22518-0
PubMed id: 33859193
Altmetrics provided by Altmetric
