Democratising deep learning for microscopy with ZeroCostDL4Mic.

Journal: Nature communications
PMID: 33859193

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.

Authors

  • Lucas von Chamier
    MRC-Laboratory for Molecular Cell Biology, University College London, London, U.K.
  • Romain F Laine
    Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge, United Kingdom.
  • Johanna Jukkala
    Turku Bioscience Centre, University of Turku and Åbo Akademi University, Turku, Finland.
  • Christoph Spahn
    Institute of Physical and Theoretical Chemistry, Goethe-University Frankfurt, Frankfurt, Germany.
  • Daniel Krentzel
    Electron Microscopy Science Technology Platform, The Francis Crick Institute, London, UK.
  • Elias Nehme
    Department of Biomedical Engineering; Lorry I. Lokey Interdisciplinary Center for Life Sciences and Engineering; Department of Electrical Engineering, Technion - Israel Institute of Technology, Haifa, Israel.
  • Martina Lerche
    Turku Bioscience Centre, University of Turku and Åbo Akademi University, Turku, Finland.
  • Sara Hernández-Pérez
    Turku Bioscience Centre, University of Turku and Åbo Akademi University, Turku, Finland.
  • Pieta K Mattila
    Turku Bioscience Centre, University of Turku and Åbo Akademi University, Turku, Finland.
  • Eleni Karinou
    Centre for Bacterial Cell Biology, Biosciences Institute, Faculty of Medical Sciences, Newcastle University, Newcastle, UK.
  • Séamus Holden
    Centre for Bacterial Cell Biology, Biosciences Institute, Faculty of Medical Sciences, Newcastle University, Newcastle, UK.
  • Ahmet Can Solak
    Chan Zuckerberg Biohub, San Francisco, CA, USA.
  • Alexander Krull
    Center for Systems Biology Dresden (CSBD), Dresden, Germany.
  • Tim-Oliver Buchholz
    Center for Systems Biology Dresden (CSBD), Dresden, Germany.
  • Martin L Jones
    Electron Microscopy Science Technology Platform, The Francis Crick Institute, London, UK.
  • Loic A Royer
    Chan Zuckerberg Biohub, San Francisco, CA, USA. loic.royer@czbiohub.org.
  • Christophe Leterrier
    Aix Marseille Université, CNRS, INP UMR7051, NeuroCyto, Marseille, France.
  • Yoav Shechtman
    Department of Biomedical Engineering; Lorry I. Lokey Interdisciplinary Center for Life Sciences and Engineering. Electronic address: yoavsh@bm.technion.ac.il.
  • Florian Jug
    Max Planck Institute of Molecular Cell Biology and Genetics, Dresden, Germany.
  • Mike Heilemann
    Institute of Physical and Theoretical Chemistry, Goethe-University Frankfurt, Frankfurt, Germany.
  • Guillaume Jacquemet
    Turku Bioscience Centre, University of Turku and Åbo Akademi University, Turku, Finland. guillaume.jacquemet@abo.fi.
  • Ricardo Henriques
    MRC-Laboratory for Molecular Cell Biology, University College London, London, U.K. r.laine@ucl.ac.uk r.henriques@ucl.ac.uk.

Keywords

External Resources

Popular Topics
Recent Journals