Democratising deep learning for microscopy with ZeroCostDL4Mic

Chamier, Lucas von; Laine, Romain F.; Jukkala, Johanna; Spahn, Christoph; Krentzel, Daniel; Nehme, Elias; Lerche, Martina; Hernández-Pérez, Sara; Mattila, Pieta K.; Karinou, Eleni; Holden, Séamus; Solak, Ahmet; Krull, Alexander; Buchholz, Tim-Oliver; Jones, Martin L.; Royer, Loïc; Leterrier, Christophe; Shechtman, Yoav; Jug, Florian; Heilemann, Mike; Jacquemet, Guillaume; Henriques, Ricardo

doi:10.1038/s41467-021-22518-0

Cited by 399 publications

(359 citation statements)

References 101 publications

Supporting

Mentioning

358

Contrasting

Unclassified

Order By: Relevance

“…Many of these, however, begin with some form of cleanup of the raw image—for example, noise filtering. Recently, machine-learning approaches have proven to be well suited for this task and user-friendly packages capable of using machine learning to clean and enhance cytoskeletal images have become available ( von Chamier et al, 2021 ).…”

Section: Quantificationmentioning

confidence: 99%

Super-Resolution Imaging Approaches for Quantifying F-Actin in Immune Cells

Garlick

Thomas

Owen

2021

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

Immune cells comprise a diverse set of cells that undergo a complex array of biological processes that must be tightly regulated. A key component of cellular machinery that achieves this is the cytoskeleton. Therefore, imaging and quantitatively describing the architecture and dynamics of the cytoskeleton is an important research goal. Optical microscopy is well suited to this task. Here, we review the latest in the state-of-the-art methodology for labeling the cytoskeleton, fluorescence microscopy hardware suitable for such imaging and quantitative statistical analysis software applicable to describing cytoskeletal structures. We also highlight ongoing challenges and areas for future development.

show abstract

Section: Quantificationmentioning

confidence: 99%

Super-Resolution Imaging Approaches for Quantifying F-Actin in Immune Cells

Garlick

Thomas

Owen

2021

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

show abstract

“…smart microscopes) are able to cope with the large amount of data generated in the process, as well as independently plan new experiments in order to arrive at even better findings, reduce the number of experiments and minimize the time required for simple tasks such as pipetting. 9 The application of machine learning algorithms in microscopy image analysis potentially helps to find correlations in data with previously trained networks 10,11 or in a completely unsupervised manner. 12 Notable are projects aimed at segmenting cells in micrographs tracking morphological changes, 13 improving the signal-to-noise ratio to enable low-photon dose imaging 14, 15 16,17 or even performing augmented microscopy tasks.…”

Section: Introductionmentioning

confidence: 99%

An Open-Source Modular Framework for Automated Pipetting and Imaging Applications

Ouyang

Bowman

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

The number of samples in biological experiments are continuously increasing, but complex protocols and human experimentation in many cases lead to suboptimal data quality and hence difficulties in reproducing scientific findings. Laboratory automation can alleviate many of these problems by precisely reproducing machine-readable protocols. These instruments generally require high up-front investments and due to lack of open APIs they are notoriously difficult for scientists to customize and control outside of the vendor-supplied software. Here, we demonstrate automated, high-throughput experiments for interdisciplinary research in life science that can be replicated on a modest budget, using open tools to ensure reproducibility by combining the tools Openflexure, Opentrons, ImJoy and UC2. Our automated sample preparation and imaging pipeline can easily be replicated and established in many laboratories as well as in educational contexts through easy-to-understand algorithms and easy-to-build microscopes. Additionally, the creation of feedback loops, with later pipetting or imaging steps depending on analysis of previously acquired images, enables the realization of smart microscopy experiments, featuring completely autonomously performed experiments. All documents and source-files are publicly available (https://beniroquai.github.io/Hi2) to prove the concept of smart lab automation using inexpensive, open tools. We believe this democratizes access to the power and repeatability of automated experiments.

show abstract

“…Consequently, open-source software to facilitate bio-image analysts without a background in computer vision to develop deep learning models have evolved [9,10]. Deep learning methodologies learn feature representations from the data without requiring predefined feature extraction.…”

Section: Introductionmentioning

confidence: 99%

HistoClean: Open-source Software for Histological Image Pre-processing and Augmentation to Improve Development of Robust Convolutional Neural Networks

McCombe¹,

Craig²,

Pulsawatdi³

et al. 2021

Preprint

View full text Add to dashboard Cite

The growth of digital pathology over the past decade has opened new research pathways and insights in cancer prediction and prognosis. In particular, there has been a surge in deep learning and computer vision techniques to analyse digital images. Common practice in this area is to use image pre-processing and augmentation to prevent bias and overfitting, creating a more robust deep learning model. Herein we introduce HistoClean; user-friendly, graphical user interface that brings together multiple image processing modules into one easy to use toolkit. In this study, we utilise HistoClean to pre-process images for a simple convolutional neural network used to detect stromal maturity, improving the accuracy of the model at a tile, region of interest, and patient level. HistoClean is free and open-source and can be downloaded from the Github repository here: https://github.com/HistoCleanQUB/HistoClean.

show abstract

Democratising deep learning for microscopy with ZeroCostDL4Mic

Cited by 399 publications

References 101 publications

Super-Resolution Imaging Approaches for Quantifying F-Actin in Immune Cells

Super-Resolution Imaging Approaches for Quantifying F-Actin in Immune Cells

An Open-Source Modular Framework for Automated Pipetting and Imaging Applications

HistoClean: Open-source Software for Histological Image Pre-processing and Augmentation to Improve Development of Robust Convolutional Neural Networks

Contact Info

Product

Resources

About