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.

Reviewing Editor

  1. Birte Forstmann, University of Amsterdam, Netherlands

Version history

  1. Received: January 27, 2020
  2. Accepted: July 24, 2020
  3. Accepted Manuscript published: July 27, 2020 (version 1)
  4. Version of Record published: August 17, 2020 (version 2)

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

  • 6,116
    Page views
  • 722
    Downloads
  • 33
    Citations

Article citation count generated by polling the highest count across the following sources: Crossref, Scopus, PubMed Central.

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

Further reading

    1. Cell Biology
    2. Neuroscience
    Elisabeth Jongsma, Anita Goyala ... Collin Yvès Ewald
    Research Article Updated

    The amyloid beta (Aβ) plaques found in Alzheimer’s disease (AD) patients’ brains contain collagens and are embedded extracellularly. Several collagens have been proposed to influence Aβ aggregate formation, yet their role in clearance is unknown. To investigate the potential role of collagens in forming and clearance of extracellular aggregates in vivo, we created a transgenic Caenorhabditis elegans strain that expresses and secretes human Aβ1-42. This secreted Aβ forms aggregates in two distinct places within the extracellular matrix. In a screen for extracellular human Aβ aggregation regulators, we identified different collagens to ameliorate or potentiate Aβ aggregation. We show that a disintegrin and metalloprotease a disintegrin and metalloprotease 2 (ADM-2), an ortholog of ADAM9, reduces the load of extracellular Aβ aggregates. ADM-2 is required and sufficient to remove the extracellular Aβ aggregates. Thus, we provide in vivo evidence of collagens essential for aggregate formation and metalloprotease participating in extracellular Aβ aggregate removal.

    1. Computational and Systems Biology
    2. Neuroscience
    Marjorie Xie, Samuel P Muscinelli ... Ashok Litwin-Kumar
    Research Article Updated

    The cerebellar granule cell layer has inspired numerous theoretical models of neural representations that support learned behaviors, beginning with the work of Marr and Albus. In these models, granule cells form a sparse, combinatorial encoding of diverse sensorimotor inputs. Such sparse representations are optimal for learning to discriminate random stimuli. However, recent observations of dense, low-dimensional activity across granule cells have called into question the role of sparse coding in these neurons. Here, we generalize theories of cerebellar learning to determine the optimal granule cell representation for tasks beyond random stimulus discrimination, including continuous input-output transformations as required for smooth motor control. We show that for such tasks, the optimal granule cell representation is substantially denser than predicted by classical theories. Our results provide a general theory of learning in cerebellum-like systems and suggest that optimal cerebellar representations are task-dependent.