Democratising deep learning for microscopy with ZeroCostDL4Mic

Lucas von Chamier, Romain F. Laine, Johanna Jukkala, Christoph Spahn, Daniel Krentzel, Elias Nehme, Martina Lerche, Sara Hernández-Pérez, Pieta K. Mattila, Eleni Karinou, Séamus Holden, Ahmet Can Solak, Alexander Krull, Tim-Oliver Buchholz, Martin L. Jones, Loïc A. Royer, Christophe Leterrier, Yoav Shechtman, Florian Jug, Mike Heilemann, Guillaume Jacquemet () and Ricardo Henriques ()
Additional contact information
Lucas von Chamier: University College London
Romain F. Laine: University College London
Johanna Jukkala: University of Turku and Åbo Akademi University
Christoph Spahn: Institute of Physical and Theoretical Chemistry, Goethe-University Frankfurt
Daniel Krentzel: The Francis Crick Institute
Elias Nehme: Technion—Israel Institute of Technology
Martina Lerche: University of Turku and Åbo Akademi University
Sara Hernández-Pérez: University of Turku and Åbo Akademi University
Pieta K. Mattila: University of Turku and Åbo Akademi University
Eleni Karinou: Newcastle University
Séamus Holden: Newcastle University
Ahmet Can Solak: Chan Zuckerberg Biohub
Alexander Krull: Center for Systems Biology Dresden (CSBD)
Tim-Oliver Buchholz: Center for Systems Biology Dresden (CSBD)
Martin L. Jones: The Francis Crick Institute
Loïc A. Royer: Chan Zuckerberg Biohub
Christophe Leterrier: Aix Marseille Université, CNRS, INP UMR7051, NeuroCyto
Yoav Shechtman: Technion—Israel Institute of Technology
Florian Jug: Center for Systems Biology Dresden (CSBD)
Mike Heilemann: Institute of Physical and Theoretical Chemistry, Goethe-University Frankfurt
Guillaume Jacquemet: University of Turku and Åbo Akademi University
Ricardo Henriques: University College London

Nature Communications, 2021, vol. 12, issue 1, 1-18

Abstract: Abstract 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.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (10)

Downloads: (external link)
https://www.nature.com/articles/s41467-021-22518-0 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:12:y:2021:i:1:d:10.1038_s41467-021-22518-0

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-021-22518-0

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().