Revealing architectural order with quantitative label-free imaging and deep learning
We report quantitative label-free imaging with phase and polarization (QLIPP) for simultaneous measurement of density, anisotropy, and orientation of structures in unlabeled live cells and tissue slices. We combine QLIPP with deep neural networks to predict fluorescence images of diverse cell and ti...
Main Authors: | , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
eLife Sciences Publications Ltd
2020-07-01
|
Series: | eLife |
Subjects: | |
Online Access: | https://elifesciences.org/articles/55502 |
id |
doaj-a5bb255640544314af503134fddf720f |
---|---|
record_format |
Article |
spelling |
doaj-a5bb255640544314af503134fddf720f2021-05-05T21:20:53ZengeLife Sciences Publications LtdeLife2050-084X2020-07-01910.7554/eLife.55502Revealing architectural order with quantitative label-free imaging and deep learningSyuan-Ming Guo0Li-Hao Yeh1https://orcid.org/0000-0003-2803-5996Jenny Folkesson2https://orcid.org/0000-0002-4673-0522Ivan E Ivanov3Anitha P Krishnan4Matthew G Keefe5Ezzat Hashemi6David Shin7Bryant B Chhun8Nathan H Cho9Manuel D Leonetti10May H Han11Tomasz J Nowakowski12Shalin B Mehta13https://orcid.org/0000-0002-2542-3582Chan Zuckerberg Biohub, San Francisco, United StatesChan Zuckerberg Biohub, San Francisco, United StatesChan Zuckerberg Biohub, San Francisco, United StatesChan Zuckerberg Biohub, San Francisco, United StatesChan Zuckerberg Biohub, San Francisco, United StatesDepartment of Anatomy, University of California, San Francisco, San Francisco, United StatesDepartment of Neurology, Stanford University, Stanford, United StatesDepartment of Anatomy, University of California, San Francisco, San Francisco, United StatesChan Zuckerberg Biohub, San Francisco, United StatesChan Zuckerberg Biohub, San Francisco, United StatesChan Zuckerberg Biohub, San Francisco, United StatesDepartment of Neurology, Stanford University, Stanford, United StatesDepartment of Anatomy, University of California, San Francisco, San Francisco, United StatesChan Zuckerberg Biohub, San Francisco, United StatesWe report quantitative label-free imaging with phase and polarization (QLIPP) for simultaneous measurement of density, anisotropy, and orientation of structures 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 U-Net 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.https://elifesciences.org/articles/55502label-free imaginginverse algorithmsdeep learninghuman tissuepolarizationphase |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Syuan-Ming Guo Li-Hao Yeh Jenny Folkesson Ivan E Ivanov Anitha P Krishnan Matthew G Keefe Ezzat Hashemi David Shin Bryant B Chhun Nathan H Cho Manuel D Leonetti May H Han Tomasz J Nowakowski Shalin B Mehta |
spellingShingle |
Syuan-Ming Guo Li-Hao Yeh Jenny Folkesson Ivan E Ivanov Anitha P Krishnan Matthew G Keefe Ezzat Hashemi David Shin Bryant B Chhun Nathan H Cho Manuel D Leonetti May H Han Tomasz J Nowakowski Shalin B Mehta Revealing architectural order with quantitative label-free imaging and deep learning eLife label-free imaging inverse algorithms deep learning human tissue polarization phase |
author_facet |
Syuan-Ming Guo Li-Hao Yeh Jenny Folkesson Ivan E Ivanov Anitha P Krishnan Matthew G Keefe Ezzat Hashemi David Shin Bryant B Chhun Nathan H Cho Manuel D Leonetti May H Han Tomasz J Nowakowski Shalin B Mehta |
author_sort |
Syuan-Ming Guo |
title |
Revealing architectural order with quantitative label-free imaging and deep learning |
title_short |
Revealing architectural order with quantitative label-free imaging and deep learning |
title_full |
Revealing architectural order with quantitative label-free imaging and deep learning |
title_fullStr |
Revealing architectural order with quantitative label-free imaging and deep learning |
title_full_unstemmed |
Revealing architectural order with quantitative label-free imaging and deep learning |
title_sort |
revealing architectural order with quantitative label-free imaging and deep learning |
publisher |
eLife Sciences Publications Ltd |
series |
eLife |
issn |
2050-084X |
publishDate |
2020-07-01 |
description |
We report quantitative label-free imaging with phase and polarization (QLIPP) for simultaneous measurement of density, anisotropy, and orientation of structures 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 U-Net 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. |
topic |
label-free imaging inverse algorithms deep learning human tissue polarization phase |
url |
https://elifesciences.org/articles/55502 |
work_keys_str_mv |
AT syuanmingguo revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT lihaoyeh revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT jennyfolkesson revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT ivaneivanov revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT anithapkrishnan revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT matthewgkeefe revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT ezzathashemi revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT davidshin revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT bryantbchhun revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT nathanhcho revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT manueldleonetti revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT mayhhan revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT tomaszjnowakowski revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning AT shalinbmehta revealingarchitecturalorderwithquantitativelabelfreeimaginganddeeplearning |
_version_ |
1721458160191930368 |