Cargando…

Graphical-model framework for automated annotation of cell identities in dense cellular images

Although identifying cell names in dense image stacks is critical in analyzing functional whole-brain data enabling comparison across experiments, unbiased identification is very difficult, and relies heavily on researchers’ experiences. Here, we present a probabilistic-graphical-model framework, CR...

Descripción completa

Detalles Bibliográficos
Autores principales: Chaudhary, Shivesh, Lee, Sol Ah, Li, Yueyi, Patel, Dhaval S, Lu, Hang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: eLife Sciences Publications, Ltd 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8032398/
https://www.ncbi.nlm.nih.gov/pubmed/33625357
http://dx.doi.org/10.7554/eLife.60321
_version_ 1783676211238535168
author Chaudhary, Shivesh
Lee, Sol Ah
Li, Yueyi
Patel, Dhaval S
Lu, Hang
author_facet Chaudhary, Shivesh
Lee, Sol Ah
Li, Yueyi
Patel, Dhaval S
Lu, Hang
author_sort Chaudhary, Shivesh
collection PubMed
description Although identifying cell names in dense image stacks is critical in analyzing functional whole-brain data enabling comparison across experiments, unbiased identification is very difficult, and relies heavily on researchers’ experiences. Here, we present a probabilistic-graphical-model framework, CRF_ID, based on Conditional Random Fields, for unbiased and automated cell identification. CRF_ID focuses on maximizing intrinsic similarity between shapes. Compared to existing methods, CRF_ID achieves higher accuracy on simulated and ground-truth experimental datasets, and better robustness against challenging noise conditions common in experimental data. CRF_ID can further boost accuracy by building atlases from annotated data in highly computationally efficient manner, and by easily adding new features (e.g. from new strains). We demonstrate cell annotation in Caenorhabditis elegans images across strains, animal orientations, and tasks including gene-expression localization, multi-cellular and whole-brain functional imaging experiments. Together, these successes demonstrate that unbiased cell annotation can facilitate biological discovery, and this approach may be valuable to annotation tasks for other systems.
format Online
Article
Text
id pubmed-8032398
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher eLife Sciences Publications, Ltd
record_format MEDLINE/PubMed
spelling pubmed-80323982021-04-12 Graphical-model framework for automated annotation of cell identities in dense cellular images Chaudhary, Shivesh Lee, Sol Ah Li, Yueyi Patel, Dhaval S Lu, Hang eLife Computational and Systems Biology Although identifying cell names in dense image stacks is critical in analyzing functional whole-brain data enabling comparison across experiments, unbiased identification is very difficult, and relies heavily on researchers’ experiences. Here, we present a probabilistic-graphical-model framework, CRF_ID, based on Conditional Random Fields, for unbiased and automated cell identification. CRF_ID focuses on maximizing intrinsic similarity between shapes. Compared to existing methods, CRF_ID achieves higher accuracy on simulated and ground-truth experimental datasets, and better robustness against challenging noise conditions common in experimental data. CRF_ID can further boost accuracy by building atlases from annotated data in highly computationally efficient manner, and by easily adding new features (e.g. from new strains). We demonstrate cell annotation in Caenorhabditis elegans images across strains, animal orientations, and tasks including gene-expression localization, multi-cellular and whole-brain functional imaging experiments. Together, these successes demonstrate that unbiased cell annotation can facilitate biological discovery, and this approach may be valuable to annotation tasks for other systems. eLife Sciences Publications, Ltd 2021-02-24 /pmc/articles/PMC8032398/ /pubmed/33625357 http://dx.doi.org/10.7554/eLife.60321 Text en © 2021, Chaudhary et al https://creativecommons.org/licenses/by/4.0/This article is distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use and redistribution provided that the original author and source are credited.
spellingShingle Computational and Systems Biology
Chaudhary, Shivesh
Lee, Sol Ah
Li, Yueyi
Patel, Dhaval S
Lu, Hang
Graphical-model framework for automated annotation of cell identities in dense cellular images
title Graphical-model framework for automated annotation of cell identities in dense cellular images
title_full Graphical-model framework for automated annotation of cell identities in dense cellular images
title_fullStr Graphical-model framework for automated annotation of cell identities in dense cellular images
title_full_unstemmed Graphical-model framework for automated annotation of cell identities in dense cellular images
title_short Graphical-model framework for automated annotation of cell identities in dense cellular images
title_sort graphical-model framework for automated annotation of cell identities in dense cellular images
topic Computational and Systems Biology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8032398/
https://www.ncbi.nlm.nih.gov/pubmed/33625357
http://dx.doi.org/10.7554/eLife.60321
work_keys_str_mv AT chaudharyshivesh graphicalmodelframeworkforautomatedannotationofcellidentitiesindensecellularimages
AT leesolah graphicalmodelframeworkforautomatedannotationofcellidentitiesindensecellularimages
AT liyueyi graphicalmodelframeworkforautomatedannotationofcellidentitiesindensecellularimages
AT pateldhavals graphicalmodelframeworkforautomatedannotationofcellidentitiesindensecellularimages
AT luhang graphicalmodelframeworkforautomatedannotationofcellidentitiesindensecellularimages