Democratising deep learning for microscopy with ZeroCostDL4Mic - Aix-Marseille Université Access content directly
Journal Articles Nature Communications Year : 2021

Democratising deep learning for microscopy with ZeroCostDL4Mic

Ricardo Henriques

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.

Domains

Neurobiology
Fichier principal
Vignette du fichier
www.nature.com 15_04_2021, 11_32_44.pdf (17.76 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-03233449 , version 1 (24-05-2021)

Licence

Attribution

Identifiers

Cite

Lucas von Chamier, Romain F Laine, Johanna Jukkala, Christoph Spahn, Daniel Krentzel, et al.. Democratising deep learning for microscopy with ZeroCostDL4Mic. Nature Communications, 2021, 12, ⟨10.1038/s41467-021-22518-0⟩. ⟨hal-03233449⟩
163 View
31 Download

Altmetric

Share

Gmail Facebook X LinkedIn More