{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T08:47:29Z","timestamp":1793263649191,"version":"4.5.0"},"reference-count":30,"publisher":"Wiley","issue":"12","license":[{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Acad Dermatol Venereol"],"published-print":{"date-parts":[[2024,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Perceived age (PA) has been associated with mortality, genetic variants linked to ageing and several age\u2010related morbidities. However, estimating PA in large datasets is laborious and costly to generate, limiting its practical applicability.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objectives<\/jats:title><jats:p>To determine if estimating PA using deep learning\u2010based algorithms results in the same associations with morbidities and genetic variants as human\u2010estimated perceived age.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Self\u2010supervised learning (SSL) and deep feature transfer (DFT) deep learning (DL) approaches were trained and tested on human\u2010estimated PAs and their corresponding frontal face images of middle\u2010aged to elderly Dutch participants (<jats:italic>n<\/jats:italic>\u2009=\u20092679) from a population\u2010based study in the Netherlands. We compared the DL\u2010estimated PAs with morbidities previously associated with human\u2010estimated PA as well as genetic variants in the gene MC1R; we additionally tested the PA associations with MC1R in a new validation cohort (<jats:italic>n<\/jats:italic>\u2009=\u20091158).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The DL approaches predicted PA in this population with a mean absolute error of 2.84\u2009years (DFT) and 2.39\u2009years (SSL). In the training\u2013test dataset, we found the same significant (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.05) associations for DL PA with osteoporosis, ARHL, cognition, COPD and cataracts and MC1R, as with human PA. We also found a similar but less significant association for SSL and DFT PAs (0.69 and 0.71\u2009years per allele,<jats:italic>p<\/jats:italic>\u2009=\u20090.008 and 0.011, respectively) with MC1R variants in the validation dataset as that found with human, SSL and DFT PAs in the training\u2013test dataset (0.79, 0.78 and 0.71\u2009years per allele respectively; all<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.0001).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Deep learning methods can automatically estimate PA from facial images with enough accuracy to replicate known links between human\u2010estimated perceived age and several age\u2010related morbidities. Furthermore, DL predicted perceived age associated with MC1R gene variants in a validation cohort. Hence, such DL PA techniques may be used instead of human estimations in perceived age studies thereby reducing time and costs.<\/jats:p><\/jats:sec>","DOI":"10.1111\/jdv.20365","type":"journal-article","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T12:30:16Z","timestamp":1727958616000},"page":"2295-2302","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Deep learning predicted perceived age is a reliable approach for analysis of facial ageing: A proof of principle study"],"prefix":"10.1111","volume":"38","author":[{"given":"Conor","family":"Turner","sequence":"first","affiliation":[{"name":"Interdisciplinary Computing and Complex BioSystems (ICOS) Research Group, School of Computing Newcastle University Newcastle upon Tyne UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0684-3175","authenticated-orcid":false,"given":"Luba M.","family":"Pardo","sequence":"additional","affiliation":[{"name":"Department of Dermatology Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David A.","family":"Gunn","sequence":"additional","affiliation":[{"name":"Unilever King's Biosciences Innovation Hub, King's College London London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruediger","family":"Zillmer","sequence":"additional","affiliation":[{"name":"Unilever Research and Development Port Sunlight UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Selma","family":"Meki\u0107","sequence":"additional","affiliation":[{"name":"Department of Dermatology University Medical Center Utrecht Utrecht The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Genetic Identification, Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Arfan","family":"Ikram","sequence":"additional","affiliation":[{"name":"Department of Epidemiology Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caroline C. W.","family":"Klaver","sequence":"additional","affiliation":[{"name":"Department of Epidemiology Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"},{"name":"Department of Ophthalmology Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pauline H.","family":"Croll","sequence":"additional","affiliation":[{"name":"Department of Epidemiology Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"},{"name":"Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"},{"name":"Department of Otorhinolaryngology, Head and Neck Surgery Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andr\u00e9","family":"Goedegebure","sequence":"additional","affiliation":[{"name":"Department of Otorhinolaryngology, Head and Neck Surgery Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3792-4296","authenticated-orcid":false,"given":"Katerina","family":"Trajanoska","sequence":"additional","affiliation":[{"name":"Department of Epidemiology Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"},{"name":"Department of Internal Medicine Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fernando","family":"Rivadeneira","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maryam","family":"Kavousi","sequence":"additional","affiliation":[{"name":"Department of Epidemiology Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guy G. O.","family":"Brusselle","sequence":"additional","affiliation":[{"name":"Department of Epidemiology Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"},{"name":"Department of Respiratory Medicine Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"},{"name":"Department of Respiratory Medicine Ghent University Hospital Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manfred","family":"Kayser","sequence":"additional","affiliation":[{"name":"Department of Genetic Identification, Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tamar","family":"Nijsten","sequence":"additional","affiliation":[{"name":"Department of Dermatology Erasmus MC University Medical Center Rotterdam Rotterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaume","family":"Bacardit","sequence":"additional","affiliation":[{"name":"Interdisciplinary Computing and Complex BioSystems (ICOS) Research Group, School of Computing Newcastle University Newcastle upon Tyne UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"e_1_2_14_2_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0008021"},{"key":"e_1_2_14_3_1","doi-asserted-by":"publisher","DOI":"10.15252\/embj.2019101982"},{"key":"e_1_2_14_4_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.b5262"},{"key":"e_1_2_14_5_1","doi-asserted-by":"publisher","DOI":"10.1097\/PSY.0b013e318259c33f"},{"key":"e_1_2_14_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/gerona\/glv090"},{"key":"e_1_2_14_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11357-015-9842-5"},{"key":"e_1_2_14_8_1","doi-asserted-by":"publisher","DOI":"10.1093\/bjd\/ljac100"},{"key":"e_1_2_14_9_1","doi-asserted-by":"publisher","DOI":"10.1093\/gerona\/gls154"},{"key":"e_1_2_14_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1447-0594.2011.00824.x"},{"key":"e_1_2_14_11_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1506264112"},{"key":"e_1_2_14_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2016.03.008"},{"key":"e_1_2_14_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jid.2021.06.018"},{"key":"e_1_2_14_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.abb.2014.07.002"},{"key":"e_1_2_14_15_1","unstructured":"GaoB\u2010B LiuX\u2010X ZhouH\u2010Y WuJ GengX.Learning expectation of label distribution for facial age and attractiveness estimation. Pattern recognition.2021."},{"key":"e_1_2_14_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0940-3"},{"key":"e_1_2_14_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10522-008-9141-y"},{"key":"e_1_2_14_18_1","first-page":"1","article-title":"ArcFace: additive angular margin loss for deep face recognition","volume":"44","author":"Deng J","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"e_1_2_14_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10654-023-01094-1"},{"key":"e_1_2_14_20_1","doi-asserted-by":"publisher","DOI":"10.1111\/srt.12205"},{"key":"e_1_2_14_21_1","unstructured":"Foundation B.Blender \u2013 a 3D modelling and rendering package. In: Community BO editor.2018."},{"key":"e_1_2_14_22_1","doi-asserted-by":"crossref","unstructured":"SimonyanK ZissermanA.Very deep convolutional networks for large\u2010scale image recognition. arXiv.2015.","DOI":"10.1109\/ICCV.2015.314"},{"key":"e_1_2_14_23_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. arXiv:151203385 [cs].2015.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_14_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087709"},{"key":"e_1_2_14_25_1","unstructured":"HuangGB MattarM BergT Learned\u2010MillerE.Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Workshop on faces in 'Real\u2010Life' Images: Detection Alignment and Recognition.2008."},{"key":"e_1_2_14_26_1","doi-asserted-by":"crossref","unstructured":"RotheR TimofteR GoolLV.DEX: deep Expectation of apparent age from a single image. 2015 IEEE International Conference on Computer Vision Workshop (ICCVW). IEEE 252\u2013257.2015.","DOI":"10.1109\/ICCVW.2015.41"},{"key":"e_1_2_14_27_1","unstructured":"LinY ShenJ WangY PanticM.FP\u2010Age: leveraging face parsing attention for facial age estimation in the wild.2022."},{"key":"e_1_2_14_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-023-09881-5"},{"key":"e_1_2_14_29_1","doi-asserted-by":"publisher","DOI":"10.1093\/gerona\/glv114"},{"key":"e_1_2_14_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43742-2_8"},{"key":"e_1_2_14_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-04083-2_2"}],"container-title":["Journal of the European Academy of Dermatology and Venereology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/jdv.20365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T01:48:49Z","timestamp":1732844929000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/jdv.20365"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,3]]},"references-count":30,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["10.1111\/jdv.20365"],"URL":"https:\/\/doi.org\/10.1111\/jdv.20365","archive":["Portico"],"relation":{},"ISSN":["0926-9959","1468-3083"],"issn-type":[{"value":"0926-9959","type":"print"},{"value":"1468-3083","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,3]]},"assertion":[{"value":"2024-05-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}