{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T20:51:22Z","timestamp":1793047882107,"version":"4.5.0"},"reference-count":22,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T00:00:00Z","timestamp":1673308800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Despite improvements in diagnostic methods, acromegaly is still a late-diagnosed disease. In this study, it was aimed to automatically recognize acromegaly disease from facial images by using deep learning methods and to facilitate the detection of the disease.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>Cross-sectional, single-centre study<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The study included 77 acromegaly (52.56 \u00b1 11.74, 34 males\/43 females) patients and 71 healthy controls (48.47 \u00b1 8.91, 39 males\/32 females), considering gender and age compatibility. At the time of the photography, 56\/77 (73%) of the acromegaly patients were in remission. Normalized images were obtained by scaling, aligning, and cropping video frames. Three architectures named ResNet50, DenseNet121, and InceptionV3 were used for the transfer learning-based convolutional neural network (CNN) model developed to classify face images as \u201cHealthy\u201d or \u201cAcromegaly\u201d. Additionally, we trained and integrated these CNN machine learning methods to create an Ensemble Method (EM) for facial detection of acromegaly.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The positive predictive values obtained for acromegaly with the ResNet50, DenseNet121, InceptionV3, and EM were calculated as 0.958, 0.965, 0.962, and 0.997, respectively. The average sensitivity, specificity, precision, and correlation coefficient values calculated for each of the ResNet50, DenseNet121, and InceptionV3 models are quite close. On the other hand, EM outperformed these three CNN architectures and provided the best overall performance in terms of sensitivity, specificity, accuracy, and precision as 0.997, 0.997, 0.997, and 0.998, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The present study provided evidence that the proposed AcroEnsemble Model might detect acromegaly from facial images with high performance. This highlights that artificial intelligence programs are promising methods for detecting acromegaly in the future.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ejendo\/lvad005","type":"journal-article","created":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T16:36:43Z","timestamp":1673455003000},"page":"158-165","source":"Crossref","is-referenced-by-count":28,"title":["Real-time detection of acromegaly from facial images with artificial intelligence"],"prefix":"10.1093","volume":"188","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8468-9196","authenticated-orcid":false,"given":"Muhammed","family":"Kizilgul","sequence":"first","affiliation":[{"name":"University of Health Sciences, Diskapi Yildirim Beyazit Training and Research Hospital, Department of Endocrinology , Ankara , Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rukiye","family":"Karakis","sequence":"additional","affiliation":[{"name":"Sivas Cumhuriyet University, Faculty of Technology, Software Engineering Department , Sivas , Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nurettin","family":"Dogan","sequence":"additional","affiliation":[{"name":"Sel\u00e7uk University, Faculty of Technology, Computer Engineering Department , Konya , Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4957-9856","authenticated-orcid":false,"given":"Hayri","family":"Bostan","sequence":"additional","affiliation":[{"name":"University of Health Sciences, Diskapi Yildirim Beyazit Training and Research Hospital, Department of Endocrinology , Ankara , Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammed Mutlu","family":"Yapici","sequence":"additional","affiliation":[{"name":"Ankara University, Elmada\u011f Vocational School, Computer Technologies Department , Ankara , Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Umran","family":"Gul","sequence":"additional","affiliation":[{"name":"University of Health Sciences, Diskapi Yildirim Beyazit Training and Research Hospital, Department of Endocrinology , Ankara , Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bekir","family":"Ucan","sequence":"additional","affiliation":[{"name":"University of Health Sciences, Diskapi Yildirim Beyazit Training and Research Hospital, Department of Endocrinology , Ankara , Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elvan","family":"Duman","sequence":"additional","affiliation":[{"name":"Burdur Mehmet Akif Ersoy University, Faculty of Technology, Software Engineering Department , Burdur , Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hakan","family":"Duger","sequence":"additional","affiliation":[{"name":"University of Health Sciences, Diskapi Yildirim Beyazit Training and Research Hospital, Department of Endocrinology , Ankara , Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erman","family":"Cakal","sequence":"additional","affiliation":[{"name":"University of Health Sciences, Diskapi Yildirim Beyazit Training and Research Hospital, Department of Endocrinology , Ankara , Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omer","family":"Akin","sequence":"additional","affiliation":[{"name":"TOBB ETU, Faculty of Science and Literature, Mathematics Department , Ankara , Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"issue":"1","key":"2023072118405542500_lvad005-B1","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1038\/s41572-019-0071-6","article-title":"Acromegaly","volume":"5","author":"Colao","year":"2019","journal-title":"Nat Rev Dis Primers"},{"issue":"10","key":"2023072118405542500_lvad005-B2","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1530\/ERC-17-0253","article-title":"Acromegaly at diagnosis in 3173 patients from the li\u00e8ge acromegaly survey (LAS) database","volume":"24","author":"Petrossians","year":"2017","journal-title":"Endocr Relat Cancer."},{"issue":"2","key":"2023072118405542500_lvad005-B3","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1111\/j.1365-2265.2009.03626.x","article-title":"Features at diagnosis of 324 patients with acromegaly did not change from 1981 to 2006: acromegaly remains under-recognized and under-diagnosed","volume":"72","author":"Reid","year":"2010","journal-title":"Clin Endocrinol (Oxf)"},{"issue":"4","key":"2023072118405542500_lvad005-B4","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1007\/s11102-012-0447-z","article-title":"Diagnostic delay is associated with psychosocial impairment in acromegaly","volume":"16","author":"Siegel","year":"2013","journal-title":"Pituitary"},{"issue":"1","key":"2023072118405542500_lvad005-B5","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1007\/s11102-016-0772-8","article-title":"Acromegaly: clinical features at diagnosis","volume":"20","author":"Vilar","year":"2017","journal-title":"Pituitary"},{"key":"2023072118405542500_lvad005-B6","doi-asserted-by":"crossref","first-page":"2074","DOI":"10.1210\/jc.2011-0237","article-title":"A novel approach to the detection of acromegaly: accuracy of diagnosis by automatic face classification","volume":"96","author":"Schneider","year":"2011","journal-title":"J Clin Endocrinol Metab"},{"key":"2023072118405542500_lvad005-B7","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.ebiom.2017.12.015","article-title":"Automatic detection of acromegaly from facial photographs using machine learning methods","volume":"27","author":"Kong","year":"2018","journal-title":"eBioMedicine"},{"key":"2023072118405542500_lvad005-B8","first-page":"278","article-title":"Efficacy of cabergoline add-on therapy in patients with acromegaly resistance to somatostatin analogs treatment and the review of literature","volume":"66","author":"Kizilgul","year":"2022","journal-title":"Arch Endocrinol Metab"},{"key":"2023072118405542500_lvad005-B9","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"2023072118405542500_lvad005-B10","first-page":"2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"2023072118405542500_lvad005-B11","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"issue":"1","key":"2023072118405542500_lvad005-B12","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s11102-016-0754-x","article-title":"Epidemiology of acromegaly: review of population studies","volume":"20","author":"Lavrentaki","year":"2017","journal-title":"Pituitary"},{"issue":"6","key":"2023072118405542500_lvad005-B13","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1530\/EJE-20-0019","article-title":"Prolonged diagnostic delay in acromegaly is associated with increased morbidity and mortality","volume":"182","author":"Esposito","year":"2020","journal-title":"Eur J Endocrinol"},{"issue":"2","key":"2023072118405542500_lvad005-B14","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.mayocp.2021.11.007","article-title":"Diagnosis and treatment of acromegaly: an update","volume":"97","author":"Ershadinia","year":"2022","journal-title":"Mayo Clin Proc."},{"issue":"3","key":"2023072118405542500_lvad005-B15","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1111\/j.1365-2265.2008.03221.x","article-title":"High prevalence of biochemical acromegaly in primary care patients with elevated IGF-1 levels","volume":"69","author":"Schneider","year":"2008","journal-title":"Clin Endocrinol (Oxf)"},{"issue":"10","key":"2023072118405542500_lvad005-B16","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1038\/nrendo.2012.101","article-title":"The changing face of acromegaly\u2014advances in diagnosis and treatment","volume":"8","author":"Ribeiro-Oliveira","year":"2012","journal-title":"Nat Rev Endocrinol"},{"key":"2023072118405542500_lvad005-B17","doi-asserted-by":"crossref","first-page":"722","DOI":"10.3389\/fendo.2018.00722","article-title":"3D Facial analysis in acromegaly: gender-specific features and clinical correlations","volume":"9","author":"Guo","year":"2018","journal-title":"Front Endocrinol (Lausanne)"},{"key":"2023072118405542500_lvad005-B18","doi-asserted-by":"crossref","first-page":"492","DOI":"10.3389\/fendo.2020.00492","article-title":"Identifying facial features and predicting patients of acromegaly using three-dimensional imaging techniques and machine learning","volume":"11","author":"Meng","year":"2020","journal-title":"Front Endocrinol (Lausanne)"},{"issue":"4","key":"2023072118405542500_lvad005-B19","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1002\/ajmg.a.38199","article-title":"22q11.2 Deletion syndrome in diverse populations","volume":"173","author":"Kruszka","year":"2017","journal-title":"Am J Med Genet"},{"issue":"1","key":"2023072118405542500_lvad005-B20","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1007\/s11102-014-0565-x","article-title":"Three-dimensional facial analysis in acromegaly: a novel tool to quantify craniofacial characteristics after long-term remission","volume":"18","author":"Wagenmakers","year":"2015","journal-title":"Pituitary"},{"issue":"2","key":"2023072118405542500_lvad005-B21","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1111\/j.1365-2265.2011.04020.x","article-title":"Early diagnosis of acromegaly: computers vs clinicians","volume":"75","author":"Miller","year":"2011","journal-title":"Clin Endocrinol (Oxf)"},{"issue":"2","key":"2023072118405542500_lvad005-B22","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1530\/EJE-20-0962","article-title":"Long-term facial changes and clinical correlations in patients with treated acromegaly: a cohort study","volume":"184","author":"Du","year":"2021","journal-title":"Eur J Endocrinol"}],"container-title":["European Journal of Endocrinology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ejendo\/advance-article-pdf\/doi\/10.1093\/ejendo\/lvad005\/48688172\/lvad005.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ejendo\/article-pdf\/188\/1\/158\/50927964\/lvad005.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ejendo\/article-pdf\/188\/1\/158\/50927964\/lvad005.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T14:41:14Z","timestamp":1689950474000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ejendo\/article\/188\/1\/158\/6986588"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,10]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,10]]}},"URL":"https:\/\/doi.org\/10.1093\/ejendo\/lvad005","relation":{},"ISSN":["0804-4643","1479-683X"],"issn-type":[{"value":"0804-4643","type":"print"},{"value":"1479-683X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1,10]]},"published":{"date-parts":[[2023,1,10]]}}}