Deep Learning (DL) methods are increasingly recognised as powerful analytical tools for microscopy. Their potential to outperform conventional image processing pipelines is now well established. Despite the enthusiasm and innovations fuelled by DL technology, the need to access powerful and compatible resources, install multiple computational tools and modify code instructions to train neural networks all lead to an accessibility barrier that novice users often find difficult to cross. Here, we present ZeroCostDL4Mic, an entry-level teaching and deployment DL platform which considerably simplifies access and use of DL for microscopy. It is based on Google Colab which provides the free, cloud-based computational resources needed. ZeroCostDL4Mic allows researchers with little or no coding expertise to quickly test, train and use popular DL networks. In parallel, it guides researchers to acquire more knowledge, to experiment with optimising DL parameters and network architectures. We also highlight the limitations and requirements to use Google Colab. Altogether, ZeroCostDL4Mic accelerates the uptake of DL for new users and promotes their capacity to use increasingly complex DL networks.
:C$\backslash$:/Users/Karoline/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Chamier et al. - 2020 - ZeroCostDL4Mic an open platform to simplify access and use of Deep-Learning in Microscopy.pdf:pdf
%0 Journal Article
%1 Chamier2020
%A von Chamier, Lucas
%A Jukkala, Johanna
%A Spahn, Christoph
%A Lerche, Martina
%A Hernández pérez, Sara
%A Mattila, Pieta
%A Karinou, Eleni
%A Holden, Seamus
%A Solak, Ahmet Can
%A Krull, Alexander
%A Buchholz, Tim-Oliver
%A Jug, Florian
%A Royer, Loic Alain
%A Heilemann, Mike
%A Laine, Romain F.
%A Jacquemet, Guillaume
%A Henriques, Ricardo
%D 2020
%I Cold Spring Harbor Laboratory
%J bioRxiv
%K ML deep-learning imaging microscopy software superresolution
%P 2020.03.20.000133
%R 10.1101/2020.03.20.000133
%T ZeroCostDL4Mic: an open platform to simplify access and use of Deep-Learning in Microscopy
%X Deep Learning (DL) methods are increasingly recognised as powerful analytical tools for microscopy. Their potential to outperform conventional image processing pipelines is now well established. Despite the enthusiasm and innovations fuelled by DL technology, the need to access powerful and compatible resources, install multiple computational tools and modify code instructions to train neural networks all lead to an accessibility barrier that novice users often find difficult to cross. Here, we present ZeroCostDL4Mic, an entry-level teaching and deployment DL platform which considerably simplifies access and use of DL for microscopy. It is based on Google Colab which provides the free, cloud-based computational resources needed. ZeroCostDL4Mic allows researchers with little or no coding expertise to quickly test, train and use popular DL networks. In parallel, it guides researchers to acquire more knowledge, to experiment with optimising DL parameters and network architectures. We also highlight the limitations and requirements to use Google Colab. Altogether, ZeroCostDL4Mic accelerates the uptake of DL for new users and promotes their capacity to use increasingly complex DL networks.
@article{Chamier2020,
abstract = {Deep Learning (DL) methods are increasingly recognised as powerful analytical tools for microscopy. Their potential to outperform conventional image processing pipelines is now well established. Despite the enthusiasm and innovations fuelled by DL technology, the need to access powerful and compatible resources, install multiple computational tools and modify code instructions to train neural networks all lead to an accessibility barrier that novice users often find difficult to cross. Here, we present ZeroCostDL4Mic, an entry-level teaching and deployment DL platform which considerably simplifies access and use of DL for microscopy. It is based on Google Colab which provides the free, cloud-based computational resources needed. ZeroCostDL4Mic allows researchers with little or no coding expertise to quickly test, train and use popular DL networks. In parallel, it guides researchers to acquire more knowledge, to experiment with optimising DL parameters and network architectures. We also highlight the limitations and requirements to use Google Colab. Altogether, ZeroCostDL4Mic accelerates the uptake of DL for new users and promotes their capacity to use increasingly complex DL networks.},
added-at = {2020-04-06T13:11:22.000+0200},
author = {von Chamier, Lucas and Jukkala, Johanna and Spahn, Christoph and Lerche, Martina and Hern{\'{a}}ndez p{\'{e}}rez, Sara and Mattila, Pieta and Karinou, Eleni and Holden, Seamus and Solak, Ahmet Can and Krull, Alexander and Buchholz, Tim-Oliver and Jug, Florian and Royer, Loic Alain and Heilemann, Mike and Laine, Romain F. and Jacquemet, Guillaume and Henriques, Ricardo},
biburl = {https://www.bibsonomy.org/bibtex/24a7f38459f9aad1d2857bb17a9dc7662/kfriedl},
doi = {10.1101/2020.03.20.000133},
file = {:C$\backslash$:/Users/Karoline/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Chamier et al. - 2020 - ZeroCostDL4Mic an open platform to simplify access and use of Deep-Learning in Microscopy.pdf:pdf},
interhash = {45070fdbef43505607fa618846c73e91},
intrahash = {4a7f38459f9aad1d2857bb17a9dc7662},
journal = {bioRxiv},
keywords = {ML deep-learning imaging microscopy software superresolution},
month = mar,
pages = {2020.03.20.000133},
publisher = {Cold Spring Harbor Laboratory},
timestamp = {2020-04-06T14:32:51.000+0200},
title = {{ZeroCostDL4Mic: an open platform to simplify access and use of Deep-Learning in Microscopy}},
year = 2020
}