Nuclear morphology is a deep learning biomarker of cellular senescence
Cellular senescence is an important factor in aging and many age-related diseases, but understanding its role in health is challenging due to the lack of exclusive or universal markers. Using neural networks, we predict senescence from the nuclear morphology of human fibroblasts with up to 95% accur...
Gespeichert in:
| Veröffentlicht in: | Nature aging 2022-08, Vol.2 (8), p.742-755 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 755 |
|---|---|
| container_issue | 8 |
| container_start_page | 742 |
| container_title | Nature aging |
| container_volume | 2 |
| creator | Heckenbach, Indra Mkrtchyan, Garik V Ezra, Michael Ben Bakula, Daniela Madsen, Jakob Sture Nielsen, Malte Hasle Oró, Denise Osborne, Brenna Covarrubias, Anthony J Idda, M Laura Gorospe, Myriam Mortensen, Laust Verdin, Eric Westendorp, Rudi Scheibye-Knudsen, Morten |
| description | Cellular senescence is an important factor in aging and many age-related diseases, but understanding its role in health is challenging due to the lack of exclusive or universal markers. Using neural networks, we predict senescence from the nuclear morphology of human fibroblasts with up to 95% accuracy, and investigate murine astrocytes, murine neurons, and fibroblasts with premature aging in culture. After generalizing our approach, the predictor recognizes higher rates of senescence in p21-positive and ethynyl-2'-deoxyuridine (EdU)-negative nuclei in tissues and shows an increasing rate of senescent cells with age in H&E-stained murine liver tissue and human dermal biopsies. Evaluating medical records reveals that higher rates of senescent cells correspond to decreased rates of malignant neoplasms and increased rates of osteoporosis, osteoarthritis, hypertension and cerebral infarction. In sum, we show that morphological alterations of the nucleus can serve as a deep learning predictor of senescence that is applicable across tissues and species and is associated with health outcomes in humans. |
| doi_str_mv | 10.1038/s43587-022-00263-3 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_10154217</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2807915547</sourcerecordid><originalsourceid>FETCH-LOGICAL-c497t-d539e621775f4f61057f2501a5c30217bbe78e7fa5782b1aa1be4c44d1a82df43</originalsourceid><addsrcrecordid>eNpdUctOwzAQtBCIVqU_wAFF4sIl4PUjTk8IVRSQKrjA2XKSTZuSxMVukPr3OLRUwMkr78zsjIaQc6DXQHl64wWXqYopYzGlLOExPyJDliQsTkUij3_NAzL2fkUDSgKnCTslA64AUuBiSGbPXV6jcVFj3Xppa7vYRpWPTFQgrqN-01btIsoq2xj3ji6yZZRjXXd14Hhs0efY5nhGTkpTexzv3xF5m92_Th_j-cvD0_RuHudiojZxIfkEEwZKyVKUCVCpSiYpGJlzGr6zDFWKqjRSpSwDYyBDkQtRgElZUQo-Irc73XWXNViE2xtnar12VbC31dZU-u-mrZZ6YT81UJAiXAgKV3sFZz869BvdVL5PZFq0ndcspWoCUooeevkPurKda0M-zYEyKiRMektsh8qd9d5heXADVPdV6V1VOlSlv6vSPJAufuc4UH6K4V-60o6C</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3102045194</pqid></control><display><type>article</type><title>Nuclear morphology is a deep learning biomarker of cellular senescence</title><source>MEDLINE</source><source>Alma/SFX Local Collection</source><creator>Heckenbach, Indra ; Mkrtchyan, Garik V ; Ezra, Michael Ben ; Bakula, Daniela ; Madsen, Jakob Sture ; Nielsen, Malte Hasle ; Oró, Denise ; Osborne, Brenna ; Covarrubias, Anthony J ; Idda, M Laura ; Gorospe, Myriam ; Mortensen, Laust ; Verdin, Eric ; Westendorp, Rudi ; Scheibye-Knudsen, Morten</creator><creatorcontrib>Heckenbach, Indra ; Mkrtchyan, Garik V ; Ezra, Michael Ben ; Bakula, Daniela ; Madsen, Jakob Sture ; Nielsen, Malte Hasle ; Oró, Denise ; Osborne, Brenna ; Covarrubias, Anthony J ; Idda, M Laura ; Gorospe, Myriam ; Mortensen, Laust ; Verdin, Eric ; Westendorp, Rudi ; Scheibye-Knudsen, Morten</creatorcontrib><description>Cellular senescence is an important factor in aging and many age-related diseases, but understanding its role in health is challenging due to the lack of exclusive or universal markers. Using neural networks, we predict senescence from the nuclear morphology of human fibroblasts with up to 95% accuracy, and investigate murine astrocytes, murine neurons, and fibroblasts with premature aging in culture. After generalizing our approach, the predictor recognizes higher rates of senescence in p21-positive and ethynyl-2'-deoxyuridine (EdU)-negative nuclei in tissues and shows an increasing rate of senescent cells with age in H&E-stained murine liver tissue and human dermal biopsies. Evaluating medical records reveals that higher rates of senescent cells correspond to decreased rates of malignant neoplasms and increased rates of osteoporosis, osteoarthritis, hypertension and cerebral infarction. In sum, we show that morphological alterations of the nucleus can serve as a deep learning predictor of senescence that is applicable across tissues and species and is associated with health outcomes in humans.</description><identifier>ISSN: 2662-8465</identifier><identifier>EISSN: 2662-8465</identifier><identifier>DOI: 10.1038/s43587-022-00263-3</identifier><identifier>PMID: 37118134</identifier><language>eng</language><publisher>United States: Nature Publishing Group</publisher><subject>Aging ; Aging, Premature ; Animals ; Biomarkers ; Cellular Senescence - physiology ; Deep Learning ; Fibroblasts ; Humans ; Mice ; Morphology ; Neural networks ; Senescence</subject><ispartof>Nature aging, 2022-08, Vol.2 (8), p.742-755</ispartof><rights>2022. The Author(s).</rights><rights>The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>The Author(s) 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c497t-d539e621775f4f61057f2501a5c30217bbe78e7fa5782b1aa1be4c44d1a82df43</citedby><cites>FETCH-LOGICAL-c497t-d539e621775f4f61057f2501a5c30217bbe78e7fa5782b1aa1be4c44d1a82df43</cites><orcidid>0000-0002-2348-5747 ; 0000-0002-0197-3010 ; 0000-0001-5439-3434 ; 0000-0002-6637-1280 ; 0000-0002-2841-7284</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37118134$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Heckenbach, Indra</creatorcontrib><creatorcontrib>Mkrtchyan, Garik V</creatorcontrib><creatorcontrib>Ezra, Michael Ben</creatorcontrib><creatorcontrib>Bakula, Daniela</creatorcontrib><creatorcontrib>Madsen, Jakob Sture</creatorcontrib><creatorcontrib>Nielsen, Malte Hasle</creatorcontrib><creatorcontrib>Oró, Denise</creatorcontrib><creatorcontrib>Osborne, Brenna</creatorcontrib><creatorcontrib>Covarrubias, Anthony J</creatorcontrib><creatorcontrib>Idda, M Laura</creatorcontrib><creatorcontrib>Gorospe, Myriam</creatorcontrib><creatorcontrib>Mortensen, Laust</creatorcontrib><creatorcontrib>Verdin, Eric</creatorcontrib><creatorcontrib>Westendorp, Rudi</creatorcontrib><creatorcontrib>Scheibye-Knudsen, Morten</creatorcontrib><title>Nuclear morphology is a deep learning biomarker of cellular senescence</title><title>Nature aging</title><addtitle>Nat Aging</addtitle><description>Cellular senescence is an important factor in aging and many age-related diseases, but understanding its role in health is challenging due to the lack of exclusive or universal markers. Using neural networks, we predict senescence from the nuclear morphology of human fibroblasts with up to 95% accuracy, and investigate murine astrocytes, murine neurons, and fibroblasts with premature aging in culture. After generalizing our approach, the predictor recognizes higher rates of senescence in p21-positive and ethynyl-2'-deoxyuridine (EdU)-negative nuclei in tissues and shows an increasing rate of senescent cells with age in H&E-stained murine liver tissue and human dermal biopsies. Evaluating medical records reveals that higher rates of senescent cells correspond to decreased rates of malignant neoplasms and increased rates of osteoporosis, osteoarthritis, hypertension and cerebral infarction. In sum, we show that morphological alterations of the nucleus can serve as a deep learning predictor of senescence that is applicable across tissues and species and is associated with health outcomes in humans.</description><subject>Aging</subject><subject>Aging, Premature</subject><subject>Animals</subject><subject>Biomarkers</subject><subject>Cellular Senescence - physiology</subject><subject>Deep Learning</subject><subject>Fibroblasts</subject><subject>Humans</subject><subject>Mice</subject><subject>Morphology</subject><subject>Neural networks</subject><subject>Senescence</subject><issn>2662-8465</issn><issn>2662-8465</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><recordid>eNpdUctOwzAQtBCIVqU_wAFF4sIl4PUjTk8IVRSQKrjA2XKSTZuSxMVukPr3OLRUwMkr78zsjIaQc6DXQHl64wWXqYopYzGlLOExPyJDliQsTkUij3_NAzL2fkUDSgKnCTslA64AUuBiSGbPXV6jcVFj3Xppa7vYRpWPTFQgrqN-01btIsoq2xj3ji6yZZRjXXd14Hhs0efY5nhGTkpTexzv3xF5m92_Th_j-cvD0_RuHudiojZxIfkEEwZKyVKUCVCpSiYpGJlzGr6zDFWKqjRSpSwDYyBDkQtRgElZUQo-Irc73XWXNViE2xtnar12VbC31dZU-u-mrZZ6YT81UJAiXAgKV3sFZz869BvdVL5PZFq0ndcspWoCUooeevkPurKda0M-zYEyKiRMektsh8qd9d5heXADVPdV6V1VOlSlv6vSPJAufuc4UH6K4V-60o6C</recordid><startdate>20220801</startdate><enddate>20220801</enddate><creator>Heckenbach, Indra</creator><creator>Mkrtchyan, Garik V</creator><creator>Ezra, Michael Ben</creator><creator>Bakula, Daniela</creator><creator>Madsen, Jakob Sture</creator><creator>Nielsen, Malte Hasle</creator><creator>Oró, Denise</creator><creator>Osborne, Brenna</creator><creator>Covarrubias, Anthony J</creator><creator>Idda, M Laura</creator><creator>Gorospe, Myriam</creator><creator>Mortensen, Laust</creator><creator>Verdin, Eric</creator><creator>Westendorp, Rudi</creator><creator>Scheibye-Knudsen, Morten</creator><general>Nature Publishing Group</general><general>Nature Publishing Group US</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>8C1</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-2348-5747</orcidid><orcidid>https://orcid.org/0000-0002-0197-3010</orcidid><orcidid>https://orcid.org/0000-0001-5439-3434</orcidid><orcidid>https://orcid.org/0000-0002-6637-1280</orcidid><orcidid>https://orcid.org/0000-0002-2841-7284</orcidid></search><sort><creationdate>20220801</creationdate><title>Nuclear morphology is a deep learning biomarker of cellular senescence</title><author>Heckenbach, Indra ; Mkrtchyan, Garik V ; Ezra, Michael Ben ; Bakula, Daniela ; Madsen, Jakob Sture ; Nielsen, Malte Hasle ; Oró, Denise ; Osborne, Brenna ; Covarrubias, Anthony J ; Idda, M Laura ; Gorospe, Myriam ; Mortensen, Laust ; Verdin, Eric ; Westendorp, Rudi ; Scheibye-Knudsen, Morten</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c497t-d539e621775f4f61057f2501a5c30217bbe78e7fa5782b1aa1be4c44d1a82df43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Aging</topic><topic>Aging, Premature</topic><topic>Animals</topic><topic>Biomarkers</topic><topic>Cellular Senescence - physiology</topic><topic>Deep Learning</topic><topic>Fibroblasts</topic><topic>Humans</topic><topic>Mice</topic><topic>Morphology</topic><topic>Neural networks</topic><topic>Senescence</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Heckenbach, Indra</creatorcontrib><creatorcontrib>Mkrtchyan, Garik V</creatorcontrib><creatorcontrib>Ezra, Michael Ben</creatorcontrib><creatorcontrib>Bakula, Daniela</creatorcontrib><creatorcontrib>Madsen, Jakob Sture</creatorcontrib><creatorcontrib>Nielsen, Malte Hasle</creatorcontrib><creatorcontrib>Oró, Denise</creatorcontrib><creatorcontrib>Osborne, Brenna</creatorcontrib><creatorcontrib>Covarrubias, Anthony J</creatorcontrib><creatorcontrib>Idda, M Laura</creatorcontrib><creatorcontrib>Gorospe, Myriam</creatorcontrib><creatorcontrib>Mortensen, Laust</creatorcontrib><creatorcontrib>Verdin, Eric</creatorcontrib><creatorcontrib>Westendorp, Rudi</creatorcontrib><creatorcontrib>Scheibye-Knudsen, Morten</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Public Health Database</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Nature aging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Heckenbach, Indra</au><au>Mkrtchyan, Garik V</au><au>Ezra, Michael Ben</au><au>Bakula, Daniela</au><au>Madsen, Jakob Sture</au><au>Nielsen, Malte Hasle</au><au>Oró, Denise</au><au>Osborne, Brenna</au><au>Covarrubias, Anthony J</au><au>Idda, M Laura</au><au>Gorospe, Myriam</au><au>Mortensen, Laust</au><au>Verdin, Eric</au><au>Westendorp, Rudi</au><au>Scheibye-Knudsen, Morten</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Nuclear morphology is a deep learning biomarker of cellular senescence</atitle><jtitle>Nature aging</jtitle><addtitle>Nat Aging</addtitle><date>2022-08-01</date><risdate>2022</risdate><volume>2</volume><issue>8</issue><spage>742</spage><epage>755</epage><pages>742-755</pages><issn>2662-8465</issn><eissn>2662-8465</eissn><abstract>Cellular senescence is an important factor in aging and many age-related diseases, but understanding its role in health is challenging due to the lack of exclusive or universal markers. Using neural networks, we predict senescence from the nuclear morphology of human fibroblasts with up to 95% accuracy, and investigate murine astrocytes, murine neurons, and fibroblasts with premature aging in culture. After generalizing our approach, the predictor recognizes higher rates of senescence in p21-positive and ethynyl-2'-deoxyuridine (EdU)-negative nuclei in tissues and shows an increasing rate of senescent cells with age in H&E-stained murine liver tissue and human dermal biopsies. Evaluating medical records reveals that higher rates of senescent cells correspond to decreased rates of malignant neoplasms and increased rates of osteoporosis, osteoarthritis, hypertension and cerebral infarction. In sum, we show that morphological alterations of the nucleus can serve as a deep learning predictor of senescence that is applicable across tissues and species and is associated with health outcomes in humans.</abstract><cop>United States</cop><pub>Nature Publishing Group</pub><pmid>37118134</pmid><doi>10.1038/s43587-022-00263-3</doi><tpages>14</tpages><orcidid>https://orcid.org/0000-0002-2348-5747</orcidid><orcidid>https://orcid.org/0000-0002-0197-3010</orcidid><orcidid>https://orcid.org/0000-0001-5439-3434</orcidid><orcidid>https://orcid.org/0000-0002-6637-1280</orcidid><orcidid>https://orcid.org/0000-0002-2841-7284</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2662-8465 |
| ispartof | Nature aging, 2022-08, Vol.2 (8), p.742-755 |
| issn | 2662-8465 2662-8465 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_10154217 |
| source | MEDLINE; Alma/SFX Local Collection |
| subjects | Aging Aging, Premature Animals Biomarkers Cellular Senescence - physiology Deep Learning Fibroblasts Humans Mice Morphology Neural networks Senescence |
| title | Nuclear morphology is a deep learning biomarker of cellular senescence |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T06%3A08%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Nuclear%20morphology%20is%20a%20deep%20learning%20biomarker%20of%20cellular%20senescence&rft.jtitle=Nature%20aging&rft.au=Heckenbach,%20Indra&rft.date=2022-08-01&rft.volume=2&rft.issue=8&rft.spage=742&rft.epage=755&rft.pages=742-755&rft.issn=2662-8465&rft.eissn=2662-8465&rft_id=info:doi/10.1038/s43587-022-00263-3&rft_dat=%3Cproquest_pubme%3E2807915547%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3102045194&rft_id=info:pmid/37118134&rfr_iscdi=true |