Cargando…
Fisheye transformation enhances deep-learning-based single-cell phenotyping by including cellular microenvironment
Incorporating information about the surroundings can have a significant impact on successfully determining the class of an object. This is of particular interest when determining the phenotypes of cells, for example, in the context of high-throughput screens. We hypothesized that an ideal approach w...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9795324/ https://www.ncbi.nlm.nih.gov/pubmed/36590690 http://dx.doi.org/10.1016/j.crmeth.2022.100339 |
_version_ | 1784860235203084288 |
---|---|
author | Toth, Timea Bauer, David Sukosd, Farkas Horvath, Peter |
author_facet | Toth, Timea Bauer, David Sukosd, Farkas Horvath, Peter |
author_sort | Toth, Timea |
collection | PubMed |
description | Incorporating information about the surroundings can have a significant impact on successfully determining the class of an object. This is of particular interest when determining the phenotypes of cells, for example, in the context of high-throughput screens. We hypothesized that an ideal approach would consider the fully featured view of the cell of interest, include its neighboring microenvironment, and give lesser weight to cells that are far from the cell of interest. To satisfy these criteria, we present an approach with a transformation similar to those characteristic of fisheye cameras. Using this transformation with proper settings, we could significantly increase the accuracy of single-cell phenotyping, both in the case of cell culture and tissue-based microscopy images, and we present improved results on a dataset containing images of wild animals. |
format | Online Article Text |
id | pubmed-9795324 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-97953242022-12-29 Fisheye transformation enhances deep-learning-based single-cell phenotyping by including cellular microenvironment Toth, Timea Bauer, David Sukosd, Farkas Horvath, Peter Cell Rep Methods Report Incorporating information about the surroundings can have a significant impact on successfully determining the class of an object. This is of particular interest when determining the phenotypes of cells, for example, in the context of high-throughput screens. We hypothesized that an ideal approach would consider the fully featured view of the cell of interest, include its neighboring microenvironment, and give lesser weight to cells that are far from the cell of interest. To satisfy these criteria, we present an approach with a transformation similar to those characteristic of fisheye cameras. Using this transformation with proper settings, we could significantly increase the accuracy of single-cell phenotyping, both in the case of cell culture and tissue-based microscopy images, and we present improved results on a dataset containing images of wild animals. Elsevier 2022-11-21 /pmc/articles/PMC9795324/ /pubmed/36590690 http://dx.doi.org/10.1016/j.crmeth.2022.100339 Text en © 2022 The Author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Report Toth, Timea Bauer, David Sukosd, Farkas Horvath, Peter Fisheye transformation enhances deep-learning-based single-cell phenotyping by including cellular microenvironment |
title | Fisheye transformation enhances deep-learning-based single-cell phenotyping by including cellular microenvironment |
title_full | Fisheye transformation enhances deep-learning-based single-cell phenotyping by including cellular microenvironment |
title_fullStr | Fisheye transformation enhances deep-learning-based single-cell phenotyping by including cellular microenvironment |
title_full_unstemmed | Fisheye transformation enhances deep-learning-based single-cell phenotyping by including cellular microenvironment |
title_short | Fisheye transformation enhances deep-learning-based single-cell phenotyping by including cellular microenvironment |
title_sort | fisheye transformation enhances deep-learning-based single-cell phenotyping by including cellular microenvironment |
topic | Report |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9795324/ https://www.ncbi.nlm.nih.gov/pubmed/36590690 http://dx.doi.org/10.1016/j.crmeth.2022.100339 |
work_keys_str_mv | AT tothtimea fisheyetransformationenhancesdeeplearningbasedsinglecellphenotypingbyincludingcellularmicroenvironment AT bauerdavid fisheyetransformationenhancesdeeplearningbasedsinglecellphenotypingbyincludingcellularmicroenvironment AT sukosdfarkas fisheyetransformationenhancesdeeplearningbasedsinglecellphenotypingbyincludingcellularmicroenvironment AT horvathpeter fisheyetransformationenhancesdeeplearningbasedsinglecellphenotypingbyincludingcellularmicroenvironment |