English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Democratising deep learning for microscopy with ZeroCostDL4Mic.

Chamier, L. v., Laine, R. F., Jukkala, J., Spahn, C., Krentzel, D., Nehme, E., et al. (2021). Democratising deep learning for microscopy with ZeroCostDL4Mic. Nature communications, 12(1), 2276-2276. doi:10.1038/s41467-021-22518-0.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Chamier, Lucas von, Author
Laine, Romain F, Author
Jukkala, Johanna, Author
Spahn, Christoph, Author
Krentzel, Daniel, Author
Nehme, Elias, Author
Lerche, Martina, Author
Hernández-Pérez, Sara, Author
Mattila, Pieta K, Author
Karinou, Eleni, Author
Holden, Séamus, Author
Solak, Ahmet Can, Author
Krull, Alexander1, Author           
Buchholz, Tim-Oliver, Author
Jones, Martin L, Author
Royer, Loic1, Author           
Leterrier, Christophe, Author
Shechtman, Yoav, Author
Jug, Florian1, Author           
Heilemann, Mike, Author
Jacquemet, Guillaume, AuthorHenriques, Ricardo, Author more..
Affiliations:
1Max Planck Institute for Molecular Cell Biology and Genetics, Max Planck Society, ou_2340692              

Content

show
hide
Free keywords: -
 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.

Details

show
hide
Language(s):
 Dates: 2021-04-15
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1038/s41467-021-22518-0
Other: cbg-8030
PMID: 33859193
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Nature communications
  Other : Nat Commun
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 12 (1) Sequence Number: - Start / End Page: 2276 - 2276 Identifier: -