No Cover Image

Journal article 1149 views 626 downloads

Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry

Minh Doan, Claire Barnes Orcid Logo, Claire McQuin, Juan C. Caicedo, Allen Goodman, Anne E. Carpenter, Paul Rees Orcid Logo

Nature Protocols, Volume: 16, Issue: 7, Pages: 3572 - 3595

Swansea University Authors: Claire Barnes Orcid Logo, Paul Rees Orcid Logo

Check full text

DOI (Published version): 10.1038/s41596-021-00549-7

Abstract

Deep learning offers the potential to extract more than meets the eye from images captured by imaging flow cytometry. This protocol describes the application of deep learning to single-cell images to perform supervised cell classification and weakly supervised learning, using example data from an ex...

Full description

Published in: Nature Protocols
ISSN: 1754-2189 1750-2799
Published: Springer Science and Business Media LLC 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57174
first_indexed 2021-06-28T11:30:22Z
last_indexed 2023-01-11T14:36:54Z
id cronfa57174
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-10-31T17:27:22.4553778</datestamp><bib-version>v2</bib-version><id>57174</id><entry>2021-06-18</entry><title>Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry</title><swanseaauthors><author><sid>024232879fc13d5ceac584360af8742c</sid><ORCID>0000-0003-1031-7127</ORCID><firstname>Claire</firstname><surname>Barnes</surname><name>Claire Barnes</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>537a2fe031a796a3bde99679ee8c24f5</sid><ORCID>0000-0002-7715-6914</ORCID><firstname>Paul</firstname><surname>Rees</surname><name>Paul Rees</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-06-18</date><deptcode>EAAS</deptcode><abstract>Deep learning offers the potential to extract more than meets the eye from images captured by imaging flow cytometry. This protocol describes the application of deep learning to single-cell images to perform supervised cell classification and weakly supervised learning, using example data from an experiment exploring red blood cell morphology. We describe how to acquire and transform suitable input data as well as the steps required for deep learning training and inference using an open-source web-based application. All steps of the protocol are provided as open-source Python as well as MATLAB runtime scripts, through both command-line and graphic user interfaces. The protocol enables a flexible and friendly environment for morphological phenotyping using supervised and weakly supervised learning and the subsequent exploration of the deep learning features using multi-dimensional visualization tools. The protocol requires 40 h when training from scratch and 1 h when using a pre-trained model.</abstract><type>Journal Article</type><journal>Nature Protocols</journal><volume>16</volume><journalNumber>7</journalNumber><paginationStart>3572</paginationStart><paginationEnd>3595</paginationEnd><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1754-2189</issnPrint><issnElectronic>1750-2799</issnElectronic><keywords/><publishedDay>1</publishedDay><publishedMonth>7</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-07-01</publishedDate><doi>10.1038/s41596-021-00549-7</doi><url/><notes/><college>COLLEGE NANME</college><department>Engineering and Applied Sciences School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EAAS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2022-10-31T17:27:22.4553778</lastEdited><Created>2021-06-18T19:09:16.3766544</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Biomedical Engineering</level></path><authors><author><firstname>Minh</firstname><surname>Doan</surname><order>1</order></author><author><firstname>Claire</firstname><surname>Barnes</surname><orcid>0000-0003-1031-7127</orcid><order>2</order></author><author><firstname>Claire</firstname><surname>McQuin</surname><order>3</order></author><author><firstname>Juan C.</firstname><surname>Caicedo</surname><order>4</order></author><author><firstname>Allen</firstname><surname>Goodman</surname><order>5</order></author><author><firstname>Anne E.</firstname><surname>Carpenter</surname><order>6</order></author><author><firstname>Paul</firstname><surname>Rees</surname><orcid>0000-0002-7715-6914</orcid><order>7</order></author></authors><documents><document><filename>57174__20281__ee00ca50945542edadf41cc704a2171e.pdf</filename><originalFilename>57174.pdf</originalFilename><uploaded>2021-06-28T15:44:15.6272273</uploaded><type>Output</type><contentLength>2081684</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2021-12-18T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2022-10-31T17:27:22.4553778 v2 57174 2021-06-18 Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry 024232879fc13d5ceac584360af8742c 0000-0003-1031-7127 Claire Barnes Claire Barnes true false 537a2fe031a796a3bde99679ee8c24f5 0000-0002-7715-6914 Paul Rees Paul Rees true false 2021-06-18 EAAS Deep learning offers the potential to extract more than meets the eye from images captured by imaging flow cytometry. This protocol describes the application of deep learning to single-cell images to perform supervised cell classification and weakly supervised learning, using example data from an experiment exploring red blood cell morphology. We describe how to acquire and transform suitable input data as well as the steps required for deep learning training and inference using an open-source web-based application. All steps of the protocol are provided as open-source Python as well as MATLAB runtime scripts, through both command-line and graphic user interfaces. The protocol enables a flexible and friendly environment for morphological phenotyping using supervised and weakly supervised learning and the subsequent exploration of the deep learning features using multi-dimensional visualization tools. The protocol requires 40 h when training from scratch and 1 h when using a pre-trained model. Journal Article Nature Protocols 16 7 3572 3595 Springer Science and Business Media LLC 1754-2189 1750-2799 1 7 2021 2021-07-01 10.1038/s41596-021-00549-7 COLLEGE NANME Engineering and Applied Sciences School COLLEGE CODE EAAS Swansea University 2022-10-31T17:27:22.4553778 2021-06-18T19:09:16.3766544 Faculty of Science and Engineering School of Engineering and Applied Sciences - Biomedical Engineering Minh Doan 1 Claire Barnes 0000-0003-1031-7127 2 Claire McQuin 3 Juan C. Caicedo 4 Allen Goodman 5 Anne E. Carpenter 6 Paul Rees 0000-0002-7715-6914 7 57174__20281__ee00ca50945542edadf41cc704a2171e.pdf 57174.pdf 2021-06-28T15:44:15.6272273 Output 2081684 application/pdf Accepted Manuscript true 2021-12-18T00:00:00.0000000 true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry
spellingShingle Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry
Claire Barnes
Paul Rees
title_short Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry
title_full Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry
title_fullStr Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry
title_full_unstemmed Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry
title_sort Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry
author_id_str_mv 024232879fc13d5ceac584360af8742c
537a2fe031a796a3bde99679ee8c24f5
author_id_fullname_str_mv 024232879fc13d5ceac584360af8742c_***_Claire Barnes
537a2fe031a796a3bde99679ee8c24f5_***_Paul Rees
author Claire Barnes
Paul Rees
author2 Minh Doan
Claire Barnes
Claire McQuin
Juan C. Caicedo
Allen Goodman
Anne E. Carpenter
Paul Rees
format Journal article
container_title Nature Protocols
container_volume 16
container_issue 7
container_start_page 3572
publishDate 2021
institution Swansea University
issn 1754-2189
1750-2799
doi_str_mv 10.1038/s41596-021-00549-7
publisher Springer Science and Business Media LLC
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Engineering and Applied Sciences - Biomedical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Biomedical Engineering
document_store_str 1
active_str 0
description Deep learning offers the potential to extract more than meets the eye from images captured by imaging flow cytometry. This protocol describes the application of deep learning to single-cell images to perform supervised cell classification and weakly supervised learning, using example data from an experiment exploring red blood cell morphology. We describe how to acquire and transform suitable input data as well as the steps required for deep learning training and inference using an open-source web-based application. All steps of the protocol are provided as open-source Python as well as MATLAB runtime scripts, through both command-line and graphic user interfaces. The protocol enables a flexible and friendly environment for morphological phenotyping using supervised and weakly supervised learning and the subsequent exploration of the deep learning features using multi-dimensional visualization tools. The protocol requires 40 h when training from scratch and 1 h when using a pre-trained model.
published_date 2021-07-01T08:02:38Z
_version_ 1821391777938014208
score 11.04748

Similar Items