No Cover Image

Journal article 1254 views 296 downloads

An open-source solution for advanced imaging flow cytometry data analysis using machine learning

Holger Hennig, Paul Rees Orcid Logo, Thomas Blasi, Lee Kamentsky, Jane Hung, David Dao, Anne E. Carpenter, Andrew Filby

Methods, Volume: 112, Pages: 201 - 210

Swansea University Author: Paul Rees Orcid Logo

Check full text

DOI (Published version): 10.1016/j.ymeth.2016.08.018

Abstract

Imaging flow cytometry (IFC) enables the high throughput collection of morphological and spatial information from hundreds of thousands of single cells. This high content, information rich image data can in theory resolve important biological differences among complex, often heterogeneous biological...

Full description

Published in: Methods
ISSN: 1046-2023
Published: 2017
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa29692
first_indexed 2016-09-02T12:54:26Z
last_indexed 2018-02-09T05:14:58Z
id cronfa29692
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2017-07-07T11:09:55.8035323</datestamp><bib-version>v2</bib-version><id>29692</id><entry>2016-09-02</entry><title>An open-source solution for advanced imaging flow cytometry data analysis using machine learning</title><swanseaauthors><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>2016-09-02</date><deptcode>EAAS</deptcode><abstract>Imaging flow cytometry (IFC) enables the high throughput collection of morphological and spatial information from hundreds of thousands of single cells. This high content, information rich image data can in theory resolve important biological differences among complex, often heterogeneous biological samples. However, data analysis is often performed in a highly manual and subjective manner using very limited image analysis techniques in combination with conventional flow cytometry gating strategies. This approach is not scalable to the hundreds of available image-based features per cell and thus makes use of only a fraction of the spatial and morphometric information. As a result, the quality, reproducibility and rigour of results are limited by the skill, experience and ingenuity of the data analyst. Here, we describe a pipeline using open-source software that leverages the rich information in digital imagery using machine learning algorithms. Compensated and corrected raw image files (.rif) data files from an imaging flow cytometer (the proprietary .cif file format) are imported into the open-source software CellProfiler, where an image processing pipeline identifies cells and subcellular compartments allowing hundreds of morphological features to be measured. This high-dimensional data can then be analysed using cutting-edge machine learning and clustering approaches using &#x201C;user-friendly&#x201D; platforms such as CellProfiler Analyst. Researchers can train an automated cell classifier to recognize different cell types, cell cycle phases, drug treatment/control conditions, etc., using supervised machine learning. This workflow should enable the scientific community to leverage the full analytical power of IFC-derived data set. It will help to reveal otherwise unappreciated populations of cells based on features that may be hidden to the human eye that include subtle measured differences in label free detection channels such as bright-field and dark-field imagery.</abstract><type>Journal Article</type><journal>Methods</journal><volume>112</volume><paginationStart>201</paginationStart><paginationEnd>210</paginationEnd><publisher/><issnPrint>1046-2023</issnPrint><keywords/><publishedDay>1</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2017</publishedYear><publishedDate>2017-01-01</publishedDate><doi>10.1016/j.ymeth.2016.08.018</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><degreesponsorsfunders>RCUK, BB/N005163/1</degreesponsorsfunders><apcterm/><lastEdited>2017-07-07T11:09:55.8035323</lastEdited><Created>2016-09-02T10:50:50.7893883</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>Holger</firstname><surname>Hennig</surname><order>1</order></author><author><firstname>Paul</firstname><surname>Rees</surname><orcid>0000-0002-7715-6914</orcid><order>2</order></author><author><firstname>Thomas</firstname><surname>Blasi</surname><order>3</order></author><author><firstname>Lee</firstname><surname>Kamentsky</surname><order>4</order></author><author><firstname>Jane</firstname><surname>Hung</surname><order>5</order></author><author><firstname>David</firstname><surname>Dao</surname><order>6</order></author><author><firstname>Anne E.</firstname><surname>Carpenter</surname><order>7</order></author><author><firstname>Andrew</firstname><surname>Filby</surname><order>8</order></author></authors><documents><document><filename>0029692-06012017111502.pdf</filename><originalFilename>hennig2017.pdf</originalFilename><uploaded>2017-01-06T11:15:02.2630000</uploaded><type>Output</type><contentLength>2021914</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><embargoDate>2017-01-06T00:00:00.0000000</embargoDate><copyrightCorrect>false</copyrightCorrect></document></documents><OutputDurs/></rfc1807>
spelling 2017-07-07T11:09:55.8035323 v2 29692 2016-09-02 An open-source solution for advanced imaging flow cytometry data analysis using machine learning 537a2fe031a796a3bde99679ee8c24f5 0000-0002-7715-6914 Paul Rees Paul Rees true false 2016-09-02 EAAS Imaging flow cytometry (IFC) enables the high throughput collection of morphological and spatial information from hundreds of thousands of single cells. This high content, information rich image data can in theory resolve important biological differences among complex, often heterogeneous biological samples. However, data analysis is often performed in a highly manual and subjective manner using very limited image analysis techniques in combination with conventional flow cytometry gating strategies. This approach is not scalable to the hundreds of available image-based features per cell and thus makes use of only a fraction of the spatial and morphometric information. As a result, the quality, reproducibility and rigour of results are limited by the skill, experience and ingenuity of the data analyst. Here, we describe a pipeline using open-source software that leverages the rich information in digital imagery using machine learning algorithms. Compensated and corrected raw image files (.rif) data files from an imaging flow cytometer (the proprietary .cif file format) are imported into the open-source software CellProfiler, where an image processing pipeline identifies cells and subcellular compartments allowing hundreds of morphological features to be measured. This high-dimensional data can then be analysed using cutting-edge machine learning and clustering approaches using “user-friendly” platforms such as CellProfiler Analyst. Researchers can train an automated cell classifier to recognize different cell types, cell cycle phases, drug treatment/control conditions, etc., using supervised machine learning. This workflow should enable the scientific community to leverage the full analytical power of IFC-derived data set. It will help to reveal otherwise unappreciated populations of cells based on features that may be hidden to the human eye that include subtle measured differences in label free detection channels such as bright-field and dark-field imagery. Journal Article Methods 112 201 210 1046-2023 1 1 2017 2017-01-01 10.1016/j.ymeth.2016.08.018 COLLEGE NANME Engineering and Applied Sciences School COLLEGE CODE EAAS Swansea University RCUK, BB/N005163/1 2017-07-07T11:09:55.8035323 2016-09-02T10:50:50.7893883 Faculty of Science and Engineering School of Engineering and Applied Sciences - Biomedical Engineering Holger Hennig 1 Paul Rees 0000-0002-7715-6914 2 Thomas Blasi 3 Lee Kamentsky 4 Jane Hung 5 David Dao 6 Anne E. Carpenter 7 Andrew Filby 8 0029692-06012017111502.pdf hennig2017.pdf 2017-01-06T11:15:02.2630000 Output 2021914 application/pdf Version of Record true 2017-01-06T00:00:00.0000000 false
title An open-source solution for advanced imaging flow cytometry data analysis using machine learning
spellingShingle An open-source solution for advanced imaging flow cytometry data analysis using machine learning
Paul Rees
title_short An open-source solution for advanced imaging flow cytometry data analysis using machine learning
title_full An open-source solution for advanced imaging flow cytometry data analysis using machine learning
title_fullStr An open-source solution for advanced imaging flow cytometry data analysis using machine learning
title_full_unstemmed An open-source solution for advanced imaging flow cytometry data analysis using machine learning
title_sort An open-source solution for advanced imaging flow cytometry data analysis using machine learning
author_id_str_mv 537a2fe031a796a3bde99679ee8c24f5
author_id_fullname_str_mv 537a2fe031a796a3bde99679ee8c24f5_***_Paul Rees
author Paul Rees
author2 Holger Hennig
Paul Rees
Thomas Blasi
Lee Kamentsky
Jane Hung
David Dao
Anne E. Carpenter
Andrew Filby
format Journal article
container_title Methods
container_volume 112
container_start_page 201
publishDate 2017
institution Swansea University
issn 1046-2023
doi_str_mv 10.1016/j.ymeth.2016.08.018
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 Imaging flow cytometry (IFC) enables the high throughput collection of morphological and spatial information from hundreds of thousands of single cells. This high content, information rich image data can in theory resolve important biological differences among complex, often heterogeneous biological samples. However, data analysis is often performed in a highly manual and subjective manner using very limited image analysis techniques in combination with conventional flow cytometry gating strategies. This approach is not scalable to the hundreds of available image-based features per cell and thus makes use of only a fraction of the spatial and morphometric information. As a result, the quality, reproducibility and rigour of results are limited by the skill, experience and ingenuity of the data analyst. Here, we describe a pipeline using open-source software that leverages the rich information in digital imagery using machine learning algorithms. Compensated and corrected raw image files (.rif) data files from an imaging flow cytometer (the proprietary .cif file format) are imported into the open-source software CellProfiler, where an image processing pipeline identifies cells and subcellular compartments allowing hundreds of morphological features to be measured. This high-dimensional data can then be analysed using cutting-edge machine learning and clustering approaches using “user-friendly” platforms such as CellProfiler Analyst. Researchers can train an automated cell classifier to recognize different cell types, cell cycle phases, drug treatment/control conditions, etc., using supervised machine learning. This workflow should enable the scientific community to leverage the full analytical power of IFC-derived data set. It will help to reveal otherwise unappreciated populations of cells based on features that may be hidden to the human eye that include subtle measured differences in label free detection channels such as bright-field and dark-field imagery.
published_date 2017-01-01T18:59:06Z
_version_ 1821342482270519296
score 11.04748

Similar Items