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.

Reviewing Editor

  1. Birte Forstmann, University of Amsterdam, Netherlands

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.

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

  • 6,561
    Page views
  • 787
    Downloads
  • 43
    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

Share this article

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

Further reading

    1. Neuroscience
    Kiwamu Kudo, Kamalini G Ranasinghe ... Srikantan S Nagarajan
    Research Article

    Alzheimer’s disease (AD) is characterized by the accumulation of amyloid-β and misfolded tau proteins causing synaptic dysfunction, and progressive neurodegeneration and cognitive decline. Altered neural oscillations have been consistently demonstrated in AD. However, the trajectories of abnormal neural oscillations in AD progression and their relationship to neurodegeneration and cognitive decline are unknown. Here, we deployed robust event-based sequencing models (EBMs) to investigate the trajectories of long-range and local neural synchrony across AD stages, estimated from resting-state magnetoencephalography. The increases in neural synchrony in the delta-theta band and the decreases in the alpha and beta bands showed progressive changes throughout the stages of the EBM. Decreases in alpha and beta band synchrony preceded both neurodegeneration and cognitive decline, indicating that frequency-specific neuronal synchrony abnormalities are early manifestations of AD pathophysiology. The long-range synchrony effects were greater than the local synchrony, indicating a greater sensitivity of connectivity metrics involving multiple regions of the brain. These results demonstrate the evolution of functional neuronal deficits along the sequence of AD progression.

    1. Medicine
    2. Neuroscience
    Luisa Fassi, Shachar Hochman ... Roi Cohen Kadosh
    Research Article

    In recent years, there has been debate about the effectiveness of treatments from different fields, such as neurostimulation, neurofeedback, brain training, and pharmacotherapy. This debate has been fuelled by contradictory and nuanced experimental findings. Notably, the effectiveness of a given treatment is commonly evaluated by comparing the effect of the active treatment versus the placebo on human health and/or behaviour. However, this approach neglects the individual’s subjective experience of the type of treatment she or he received in establishing treatment efficacy. Here, we show that individual differences in subjective treatment - the thought of receiving the active or placebo condition during an experiment - can explain variability in outcomes better than the actual treatment. We analysed four independent datasets (N = 387 participants), including clinical patients and healthy adults from different age groups who were exposed to different neurostimulation treatments (transcranial magnetic stimulation: Studies 1 and 2; transcranial direct current stimulation: Studies 3 and 4). Our findings show that the inclusion of subjective treatment can provide a better model fit either alone or in interaction with objective treatment (defined as the condition to which participants are assigned in the experiment). These results demonstrate the significant contribution of subjective experience in explaining the variability of clinical, cognitive, and behavioural outcomes. We advocate for existing and future studies in clinical and non-clinical research to start accounting for participants’ subjective beliefs and their interplay with objective treatment when assessing the efficacy of treatments. This approach will be crucial in providing a more accurate estimation of the treatment effect and its source, allowing the development of effective and reproducible interventions.