Revealing architectural order with quantitative label-free imaging and deep learning

Abstract

We report quantitative label-free imaging with phase and polarization (QLIPP) for simultaneous measurement of density, anisotropy, and orientation in unlabeled live cells and tissue slices. We combine QLIPP with deep neural networks to predict fluorescence images of diverse cell and tissue structures. QLIPP images reveal anatomical regions and axon tract orientation in prenatal human brain tissue sections that are not visible using brightfield imaging. We report a variant of UNet architecture, multi-channel 2.5D U-Net, for computationally efficient prediction of fluorescence images in three dimensions and over large fields of view. Further, we develop data normalization methods for accurate prediction of myelin distribution over large brain regions. We show that experimental defects in labeling the human tissue can be rescued with quantitative label-free imaging and neural network model. We anticipate that the proposed method will enable new studies of architectural order at spatial scales ranging from organelles to tissue.

Data availability

Our experiments generated imaging data from mouse kidney tissue and human brain tissue slices that are useful for machine learning and other analyses. We are in the process of uploading them to a public image archive.

Article and author information

Author details

  1. Syuan-Ming Guo

    Computational Microscopy, Chan Zuckerberg Biohub, San Francisco, United States
    Competing interests
    The authors declare that no competing interests exist.
  2. Li-Hao Yeh

    Computational Microscopy, Chan Zuckerberg Biohub, San Francisco, United States
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0003-2803-5996
  3. Jenny Folkesson

    Data Science, Chan Zuckerberg Biohub, San Francisco, United States
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-4673-0522
  4. Ivan E Ivanov

    Computational Microscopy, Chan Zuckerberg Biohub, San Francisco, United States
    Competing interests
    The authors declare that no competing interests exist.
  5. Anitha P Krishnan

    Data Science, Chan Zuckerberg Biohub, San Francisco, United States
    Competing interests
    The authors declare that no competing interests exist.
  6. Matthew G Keefe

    Anatomy, UCSF School of Medicine, San Francisco, United States
    Competing interests
    The authors declare that no competing interests exist.
  7. Ezzat Hashemi

    Department of Neurology, Stanford University, Stanford, United States
    Competing interests
    The authors declare that no competing interests exist.
  8. David Shin

    Anatomy, UCSF School of Medicine, San Francisco, United States
    Competing interests
    The authors declare that no competing interests exist.
  9. Bryant B Chhun

    Computational Microscopy, Chan Zuckerberg Biohub, San Francisco, United States
    Competing interests
    The authors declare that no competing interests exist.
  10. Nathan H Cho

    Cell Atlas, Chan Zuckerberg Biohub, San Francisco, United States
    Competing interests
    The authors declare that no competing interests exist.
  11. Manuel D Leonetti

    Cell Atlas, Chan Zuckerberg Biohub, San Francisco, United States
    Competing interests
    The authors declare that no competing interests exist.
  12. May H Han

    Department of Neurology, Stanford University, Stanford, United States
    Competing interests
    The authors declare that no competing interests exist.
  13. Tomasz Nowakowski

    Anatomy, UCSF School of Medicine, San Francisco, United States
    Competing interests
    The authors declare that no competing interests exist.
  14. Shalin B Mehta

    Computational Microscopy, Chan Zuckerberg Biohub, San Francisco, United States
    For correspondence
    shalin.mehta@czbiohub.org
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-2542-3582

Funding

Chan Zuckerberg Biohub

  • Syuan-Ming Guo
  • Li-Hao Yeh
  • Jenny Folkesson
  • Ivan E Ivanov
  • Matthew G Keefe
  • David Shin
  • Bryant B Chhun
  • Nathan H Cho
  • Tomasz Nowakowski
  • Shalin B Mehta

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Ethics

Human subjects: De-identified brain tissue samples were received with patient consent in accordance with a protocol approved by the Human Gamete, Embryo, and Stem Cell Research Committee (institutional review board) at the University of California, San Francisco.

Copyright

© 2020, Guo et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 7,074
    views
  • 845
    downloads
  • 70
    citations

Views, downloads and citations are aggregated across all versions of this paper published by eLife.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Syuan-Ming Guo
  2. Li-Hao Yeh
  3. Jenny Folkesson
  4. Ivan E Ivanov
  5. Anitha P Krishnan
  6. Matthew G Keefe
  7. Ezzat Hashemi
  8. David Shin
  9. Bryant B Chhun
  10. Nathan H Cho
  11. Manuel D Leonetti
  12. May H Han
  13. Tomasz Nowakowski
  14. Shalin B Mehta
(2020)
Revealing architectural order with quantitative label-free imaging and deep learning
eLife 9:e55502.
https://doi.org/10.7554/eLife.55502

Share this article

https://doi.org/10.7554/eLife.55502

Further reading

    1. Computational and Systems Biology
    2. Neuroscience
    Anna Cattani, Don B Arnold ... Nancy Kopell
    Research Article

    The basolateral amygdala (BLA) is a key site where fear learning takes place through synaptic plasticity. Rodent research shows prominent low theta (~3–6 Hz), high theta (~6–12 Hz), and gamma (>30 Hz) rhythms in the BLA local field potential recordings. However, it is not understood what role these rhythms play in supporting the plasticity. Here, we create a biophysically detailed model of the BLA circuit to show that several classes of interneurons (PV, SOM, and VIP) in the BLA can be critically involved in producing the rhythms; these rhythms promote the formation of a dedicated fear circuit shaped through spike-timing-dependent plasticity. Each class of interneurons is necessary for the plasticity. We find that the low theta rhythm is a biomarker of successful fear conditioning. The model makes use of interneurons commonly found in the cortex and, hence, may apply to a wide variety of associative learning situations.

    1. Neuroscience
    Bharath Krishnan, Noah Cowan
    Insight

    Mice can generate a cognitive map of an environment based on self-motion signals when there is a fixed association between their starting point and the location of their goal.