{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T11:03:44Z","timestamp":1789470224957,"version":"build-2803163510"},"reference-count":12,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:00:00Z","timestamp":1780444800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:00:00Z","timestamp":1780444800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pediatr Radiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Radiographic bone age estimation is routinely performed in children to evaluate short stature, early or late puberty, and endocrine disorders, as well as for surgical planning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To evaluate agreement between three state-of-the-art deep learning bone age estimation models and chronological age in a large contemporary pediatric cohort.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>\n                      We retrospectively identified a large contemporary cohort of children (\n                      <jats:italic>n<\/jats:italic>\n                      =7,189; 3,669 females and 3,520 males) aged 24\u2013216\u00a0months (mean 143.6\u00b146.2\u00a0months) with consecutive radiologically normal hand (including\u00a0the\u00a0wrist) radiographs that were evaluated for trauma between November 1, 2010, and October 31, 2020. Bone age was estimated according to Greulich and Pyle (GP)\u00a0Atlas standards using three state-of-the-art deep learning models (Stanford\u00a0University,\u00a0Cincinnati Children's Hospital Medical Center (CCHMC) , and MedImageInsight models), each producing continuous bone age estimates in months. Mean and proportional bias relative to chronological age were assessed.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      All three models systematically overestimated chronological age, although the magnitude of bias varied by model and sex. The CCHMC model demonstrated the smallest overall mean bias (+3.20\u00a0months), followed by the MedImageInsight (+4.60\u00a0months) and Stanford (+7.03\u00a0months) models. Mean differences compared with chronological age were statistically significant for all models (\n                      <jats:italic>P<\/jats:italic>\n                      &lt;0.0001). Evidence of proportional bias was observed in most models and subgroups. For all three models, the difference between predicted bone age and chronological age was greater for Black compared to White and Hispanic compared to non-Hispanic children.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>GP Atlas\u2013based bone age models systematically overestimate chronological age in a large contemporary cohort of children undergoing hand radiography for trauma, with biases related to age, sex, race, and ethnicity.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00247-026-06661-8","type":"journal-article","created":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T12:52:31Z","timestamp":1780491151000},"page":"2275-2282","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Agreement between three state-of-the-art deep learning bone age estimation models and chronological age in a large contemporary pediatric cohort"],"prefix":"10.1007","volume":"56","author":[{"given":"Elanchezhian","family":"Somasundaram","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rama S.","family":"Ayyala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William","family":"Tepe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bryan","family":"Luna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan R.","family":"Dillman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,3]]},"reference":[{"key":"6661_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1159\/000329372","volume":"76","author":"DD Martin","year":"2011","unstructured":"Martin DD, Wit JM, Hochberg Z, S\u00e4vendahl L, van Rijn RR, Fricke O, Cameron N, Caliebe J, Hertel T, Kiepe D, Albertsson-Wikland K, Thodberg HH, Binder G, Ranke MB (2011) The use of bone age in clinical practice - Part 1. Horm Res Paediatr 76:1\u20139","journal-title":"Horm Res Paediatr"},{"key":"6661_CR2","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1159\/000271910","volume":"73","author":"GL Spadoni","year":"2010","unstructured":"Spadoni GL, Cianfarani S (2010) Bone age assessment in the workup of children with endocrine disorders. Horm Res Paediatr 73:2\u20135","journal-title":"Horm Res Paediatr"},{"key":"6661_CR3","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1007\/s00247-016-3618-7","volume":"46","author":"MA Breen","year":"2016","unstructured":"Breen MA, Tsai A, Stamm A, Kleinman PK (2016) Bone age assessment practices in infants and older children among Society for Pediatric Radiology members. Pediatr Radiol 46:1269\u20131274","journal-title":"Pediatr Radiol"},{"key":"6661_CR4","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.12854","volume":"7","author":"Z Wang","year":"2024","unstructured":"Wang Z, Asokan G, Onnela JP, Baird DD, Jukic AMZ, Wilcox AJ, Curry CL, Fischer-Colbrie T, Williams MA, Hauser R, Coull BA, Mahalingaiah S (2024) Menarche and time to cycle regularity among individuals born between 1950 and 2005 in the US. JAMA Netw Open 7:e2412854","journal-title":"JAMA Netw Open"},{"key":"6661_CR5","doi-asserted-by":"publisher","first-page":"2026","DOI":"10.1093\/aje\/kwac148","volume":"191","author":"S Aghaee","year":"2022","unstructured":"Aghaee S, Deardorff J, Quesenberry CP, Greenspan LC, Kushi LH, Kubo A (2022) Associations between childhood obesity and pubertal timing stratified by sex and race\/ethnicity. Am J Epidemiol 191:2026\u20132036","journal-title":"Am J Epidemiol"},{"key":"6661_CR6","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020190198","volume":"2","author":"I Pan","year":"2020","unstructured":"Pan I, Baird GL, Mutasa S, Merck D, Ruzal-Shapiro C, Swenson DW, Ayyala RS (2020) Rethinking Greulich and Pyle: a deep learning approach to pediatric bone age assessment using pediatric trauma hand radiographs. Radiol Artif Intell 2:e190198","journal-title":"Radiol Artif Intell"},{"key":"6661_CR7","doi-asserted-by":"publisher","first-page":"2936","DOI":"10.1007\/s00330-018-5718-2","volume":"29","author":"PS Dahlberg","year":"2019","unstructured":"Dahlberg PS, Mosd\u00f8l A, Ding Y, Bleka \u00d8, Rolseth V, Straumann GH, Skjerven-Martinsen M, Delaveris GJM, Vist GE (2019) A systematic review of the agreement between chronological age and skeletal age based on the Greulich and Pyle atlas. Eur Radiol 29:2936\u20132948","journal-title":"Eur Radiol"},{"key":"6661_CR8","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019190053","volume":"1","author":"I Pan","year":"2019","unstructured":"Pan I, Thodberg HH, Halabi SS, Kalpathy-Cramer J, Larson DB (2019) Improving automated pediatric bone age estimation using ensembles of models from the 2017 RSNA machine learning challenge. Radiol Artif Intell 1:e190053","journal-title":"Radiol Artif Intell"},{"key":"6661_CR9","doi-asserted-by":"publisher","first-page":"2112","DOI":"10.1097\/CORR.0000000000000446","volume":"476","author":"ME Boeyer","year":"2018","unstructured":"Boeyer ME, Sherwood RJ, Deroche CB, Duren DL (2018) Early maturity as the new normal: a century-long study of bone age. Clin Orthop Relat Res 476:2112\u20132122","journal-title":"Clin Orthop Relat Res"},{"key":"6661_CR10","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.220505","volume":"306","author":"E Beheshtian","year":"2023","unstructured":"Beheshtian E, Putman K, Santomartino SM, Parekh VS, Yi PH (2023) Generalizability and bias in a deep learning pediatric bone age prediction model using hand radiographs. Radiology 306:e220505","journal-title":"Radiology"},{"key":"6661_CR11","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.3348\/kjr.2023.0092","volume":"24","author":"PH Kim","year":"2023","unstructured":"Kim PH, Yoon HM, Kim JR, Hwang JY, Choi JH, Hwang J, Lee J, Sung J, Jung KH, Bae B, Jung AY, Cho YA, Shim WH, Bak B, Lee JS (2023) Bone age assessment using artificial intelligence in Korean pediatric population: a comparison of deep-learning models trained with healthy chronological and Greulich-Pyle ages as labels. Korean J Radiol 24:1151\u20131163","journal-title":"Korean J Radiol"},{"key":"6661_CR12","doi-asserted-by":"publisher","first-page":"2559","DOI":"10.1007\/s11999-015-4213-1","volume":"473","author":"DL Duren","year":"2015","unstructured":"Duren DL, Nahhas RW, Sherwood RJ (2015) Do secular trends in skeletal maturity occur equally in both sexes? Clin Orthop Relat Res 473:2559\u20132567","journal-title":"Clin Orthop Relat Res"}],"container-title":["Pediatric Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00247-026-06661-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00247-026-06661-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00247-026-06661-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T10:17:29Z","timestamp":1789467449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00247-026-06661-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,3]]},"references-count":12,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["6661"],"URL":"https:\/\/doi.org\/10.1007\/s00247-026-06661-8","relation":{},"ISSN":["1432-1998"],"issn-type":[{"value":"1432-1998","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,3]]},"assertion":[{"value":"9 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"None","order":1,"name":"Ethics","label":"Conflicts of interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}