Accurate staging of chick embryonic tissues via deep learning of salient features

Recent work shows that the developmental potential of progenitor cells in the HH10 chick brain changes rapidly, accompanied by subtle changes in morphology. This demands increased temporal resolution for studies of the brain at this stage, necessitating precise and unbiased staging. Here, we investi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Development (Cambridge) 2023-11, Vol.150 (22)
Hauptverfasser: Groves, Ian, Holmshaw, Jacob, Furley, David, Manning, Elizabeth, Chinnaiya, Kavitha, Towers, Matthew, Evans, Benjamin D., Placzek, Marysia, Fletcher, Alexander G.
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 22
container_start_page
container_title Development (Cambridge)
container_volume 150
creator Groves, Ian
Holmshaw, Jacob
Furley, David
Manning, Elizabeth
Chinnaiya, Kavitha
Towers, Matthew
Evans, Benjamin D.
Placzek, Marysia
Fletcher, Alexander G.
description Recent work shows that the developmental potential of progenitor cells in the HH10 chick brain changes rapidly, accompanied by subtle changes in morphology. This demands increased temporal resolution for studies of the brain at this stage, necessitating precise and unbiased staging. Here, we investigated whether we could train a deep convolutional neural network to sub-stage HH10 chick brains using a small dataset of 151 expertly labelled images. By augmenting our images with biologically informed transformations and data-driven preprocessing steps, we successfully trained a classifier to sub-stage HH10 brains to 87.1% test accuracy. To determine whether our classifier could be generally applied, we re-trained it using images (269) of randomised control and experimental chick wings, and obtained similarly high test accuracy (86.1%). Saliency analyses revealed that biologically relevant features are used for classification. Our strategy enables training of image classifiers for various applications in developmental biology with limited microscopy data.
doi_str_mv 10.1242/dev.202068
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2877388926</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2877388926</sourcerecordid><originalsourceid>FETCH-LOGICAL-c300t-f63fbc388bda2499f03d4d0e42e38b6860c5703af7d42da0ce8efcd1d8d9a9943</originalsourceid><addsrcrecordid>eNotkF1LwzAYRoMoOKc3_oJcitD5Juma5HIMv2Aggl6XNHkzo11bk3Swf29lu3puDoeHQ8gtgwXjJX9wuF9w4FCpMzJjpZSFZlyfkxnoJRRMa3ZJrlL6BgBRSTkj7ytrx2gy0pTNNnRb2ntqv4L9obhr4qHvgqU5pDRiovtgqEMcaIsmdic4mTZgl6lHk8eI6ZpceNMmvDntnHw-PX6sX4rN2_PrerUprADIha-Eb6xQqnGGl1p7EK50gCVHoZpKVWCXEoTx0pXcGbCo0FvHnHLaaF2KObk7eofY_07vcr0LyWLbmg77MdVcSTnpNa8m9P6I2tinFNHXQww7Ew81g_q_Wz11q4_dxB8sgmGy</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2877388926</pqid></control><display><type>article</type><title>Accurate staging of chick embryonic tissues via deep learning of salient features</title><source>EZB-FREE-00999 freely available EZB journals</source><source>Alma/SFX Local Collection</source><source>Company of Biologists</source><creator>Groves, Ian ; Holmshaw, Jacob ; Furley, David ; Manning, Elizabeth ; Chinnaiya, Kavitha ; Towers, Matthew ; Evans, Benjamin D. ; Placzek, Marysia ; Fletcher, Alexander G.</creator><creatorcontrib>Groves, Ian ; Holmshaw, Jacob ; Furley, David ; Manning, Elizabeth ; Chinnaiya, Kavitha ; Towers, Matthew ; Evans, Benjamin D. ; Placzek, Marysia ; Fletcher, Alexander G.</creatorcontrib><description>Recent work shows that the developmental potential of progenitor cells in the HH10 chick brain changes rapidly, accompanied by subtle changes in morphology. This demands increased temporal resolution for studies of the brain at this stage, necessitating precise and unbiased staging. Here, we investigated whether we could train a deep convolutional neural network to sub-stage HH10 chick brains using a small dataset of 151 expertly labelled images. By augmenting our images with biologically informed transformations and data-driven preprocessing steps, we successfully trained a classifier to sub-stage HH10 brains to 87.1% test accuracy. To determine whether our classifier could be generally applied, we re-trained it using images (269) of randomised control and experimental chick wings, and obtained similarly high test accuracy (86.1%). Saliency analyses revealed that biologically relevant features are used for classification. Our strategy enables training of image classifiers for various applications in developmental biology with limited microscopy data.</description><identifier>ISSN: 0950-1991</identifier><identifier>EISSN: 1477-9129</identifier><identifier>DOI: 10.1242/dev.202068</identifier><language>eng</language><ispartof>Development (Cambridge), 2023-11, Vol.150 (22)</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c300t-f63fbc388bda2499f03d4d0e42e38b6860c5703af7d42da0ce8efcd1d8d9a9943</citedby><cites>FETCH-LOGICAL-c300t-f63fbc388bda2499f03d4d0e42e38b6860c5703af7d42da0ce8efcd1d8d9a9943</cites><orcidid>0000-0002-4106-9229 ; 0000-0002-0760-1795 ; 0000-0001-6317-8226 ; 0000-0002-1734-6070 ; 0000-0003-0525-4336 ; 0000-0002-1372-381X ; 0000-0003-2189-4536</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,3678,27924,27925</link.rule.ids></links><search><creatorcontrib>Groves, Ian</creatorcontrib><creatorcontrib>Holmshaw, Jacob</creatorcontrib><creatorcontrib>Furley, David</creatorcontrib><creatorcontrib>Manning, Elizabeth</creatorcontrib><creatorcontrib>Chinnaiya, Kavitha</creatorcontrib><creatorcontrib>Towers, Matthew</creatorcontrib><creatorcontrib>Evans, Benjamin D.</creatorcontrib><creatorcontrib>Placzek, Marysia</creatorcontrib><creatorcontrib>Fletcher, Alexander G.</creatorcontrib><title>Accurate staging of chick embryonic tissues via deep learning of salient features</title><title>Development (Cambridge)</title><description>Recent work shows that the developmental potential of progenitor cells in the HH10 chick brain changes rapidly, accompanied by subtle changes in morphology. This demands increased temporal resolution for studies of the brain at this stage, necessitating precise and unbiased staging. Here, we investigated whether we could train a deep convolutional neural network to sub-stage HH10 chick brains using a small dataset of 151 expertly labelled images. By augmenting our images with biologically informed transformations and data-driven preprocessing steps, we successfully trained a classifier to sub-stage HH10 brains to 87.1% test accuracy. To determine whether our classifier could be generally applied, we re-trained it using images (269) of randomised control and experimental chick wings, and obtained similarly high test accuracy (86.1%). Saliency analyses revealed that biologically relevant features are used for classification. Our strategy enables training of image classifiers for various applications in developmental biology with limited microscopy data.</description><issn>0950-1991</issn><issn>1477-9129</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNotkF1LwzAYRoMoOKc3_oJcitD5Juma5HIMv2Aggl6XNHkzo11bk3Swf29lu3puDoeHQ8gtgwXjJX9wuF9w4FCpMzJjpZSFZlyfkxnoJRRMa3ZJrlL6BgBRSTkj7ytrx2gy0pTNNnRb2ntqv4L9obhr4qHvgqU5pDRiovtgqEMcaIsmdic4mTZgl6lHk8eI6ZpceNMmvDntnHw-PX6sX4rN2_PrerUprADIha-Eb6xQqnGGl1p7EK50gCVHoZpKVWCXEoTx0pXcGbCo0FvHnHLaaF2KObk7eofY_07vcr0LyWLbmg77MdVcSTnpNa8m9P6I2tinFNHXQww7Ew81g_q_Wz11q4_dxB8sgmGy</recordid><startdate>20231115</startdate><enddate>20231115</enddate><creator>Groves, Ian</creator><creator>Holmshaw, Jacob</creator><creator>Furley, David</creator><creator>Manning, Elizabeth</creator><creator>Chinnaiya, Kavitha</creator><creator>Towers, Matthew</creator><creator>Evans, Benjamin D.</creator><creator>Placzek, Marysia</creator><creator>Fletcher, Alexander G.</creator><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-4106-9229</orcidid><orcidid>https://orcid.org/0000-0002-0760-1795</orcidid><orcidid>https://orcid.org/0000-0001-6317-8226</orcidid><orcidid>https://orcid.org/0000-0002-1734-6070</orcidid><orcidid>https://orcid.org/0000-0003-0525-4336</orcidid><orcidid>https://orcid.org/0000-0002-1372-381X</orcidid><orcidid>https://orcid.org/0000-0003-2189-4536</orcidid></search><sort><creationdate>20231115</creationdate><title>Accurate staging of chick embryonic tissues via deep learning of salient features</title><author>Groves, Ian ; Holmshaw, Jacob ; Furley, David ; Manning, Elizabeth ; Chinnaiya, Kavitha ; Towers, Matthew ; Evans, Benjamin D. ; Placzek, Marysia ; Fletcher, Alexander G.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c300t-f63fbc388bda2499f03d4d0e42e38b6860c5703af7d42da0ce8efcd1d8d9a9943</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Groves, Ian</creatorcontrib><creatorcontrib>Holmshaw, Jacob</creatorcontrib><creatorcontrib>Furley, David</creatorcontrib><creatorcontrib>Manning, Elizabeth</creatorcontrib><creatorcontrib>Chinnaiya, Kavitha</creatorcontrib><creatorcontrib>Towers, Matthew</creatorcontrib><creatorcontrib>Evans, Benjamin D.</creatorcontrib><creatorcontrib>Placzek, Marysia</creatorcontrib><creatorcontrib>Fletcher, Alexander G.</creatorcontrib><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Development (Cambridge)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Groves, Ian</au><au>Holmshaw, Jacob</au><au>Furley, David</au><au>Manning, Elizabeth</au><au>Chinnaiya, Kavitha</au><au>Towers, Matthew</au><au>Evans, Benjamin D.</au><au>Placzek, Marysia</au><au>Fletcher, Alexander G.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Accurate staging of chick embryonic tissues via deep learning of salient features</atitle><jtitle>Development (Cambridge)</jtitle><date>2023-11-15</date><risdate>2023</risdate><volume>150</volume><issue>22</issue><issn>0950-1991</issn><eissn>1477-9129</eissn><abstract>Recent work shows that the developmental potential of progenitor cells in the HH10 chick brain changes rapidly, accompanied by subtle changes in morphology. This demands increased temporal resolution for studies of the brain at this stage, necessitating precise and unbiased staging. Here, we investigated whether we could train a deep convolutional neural network to sub-stage HH10 chick brains using a small dataset of 151 expertly labelled images. By augmenting our images with biologically informed transformations and data-driven preprocessing steps, we successfully trained a classifier to sub-stage HH10 brains to 87.1% test accuracy. To determine whether our classifier could be generally applied, we re-trained it using images (269) of randomised control and experimental chick wings, and obtained similarly high test accuracy (86.1%). Saliency analyses revealed that biologically relevant features are used for classification. Our strategy enables training of image classifiers for various applications in developmental biology with limited microscopy data.</abstract><doi>10.1242/dev.202068</doi><orcidid>https://orcid.org/0000-0002-4106-9229</orcidid><orcidid>https://orcid.org/0000-0002-0760-1795</orcidid><orcidid>https://orcid.org/0000-0001-6317-8226</orcidid><orcidid>https://orcid.org/0000-0002-1734-6070</orcidid><orcidid>https://orcid.org/0000-0003-0525-4336</orcidid><orcidid>https://orcid.org/0000-0002-1372-381X</orcidid><orcidid>https://orcid.org/0000-0003-2189-4536</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0950-1991
ispartof Development (Cambridge), 2023-11, Vol.150 (22)
issn 0950-1991
1477-9129
language eng
recordid cdi_proquest_miscellaneous_2877388926
source EZB-FREE-00999 freely available EZB journals; Alma/SFX Local Collection; Company of Biologists
title Accurate staging of chick embryonic tissues via deep learning of salient features
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T19%3A18%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Accurate%20staging%20of%20chick%20embryonic%20tissues%20via%20deep%20learning%20of%20salient%20features&rft.jtitle=Development%20(Cambridge)&rft.au=Groves,%20Ian&rft.date=2023-11-15&rft.volume=150&rft.issue=22&rft.issn=0950-1991&rft.eissn=1477-9129&rft_id=info:doi/10.1242/dev.202068&rft_dat=%3Cproquest_cross%3E2877388926%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2877388926&rft_id=info:pmid/&rfr_iscdi=true