{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T04:32:13Z","timestamp":1772166733370,"version":"3.50.1"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UIDB\/00006\/2020"],"award-info":[{"award-number":["UIDB\/00006\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Egypt J Forensic Sci"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The practical employment of Machine Learning in Forensic Odontology remains underexplored, especially in the field of age estimation. Age estimation is essential in legal proceedings to protect the rights of individuals without proper documentation, whether for seeking asylum or when caring for a found child. This study aimed to utilize the VGG16 model to read, analyze, and provide classification of tooth development stages of the third molars from a sample of 876 orthopantomograms (OPGs) 10 to 25\u00a0years old (447 males and 429 females) from the Portuguese population collected from the ULS Santa Maria, University of Lisbon. The third molars 38 and 48 were used to classify individuals into age groups based on thresholds of 16, 18, and 21\u00a0years old. Age estimation was calculated manually using the methods established by Demirjian and by Moorrees, Funning, and Hunt. Furthermore, we trained the VGG16 model to read, analyze, and provide classification of the development stages, and afterwards we evaluated the VGG16 model through overall accuracy, recall, precision, and F-Score. The goal was to compare the accuracy of the traditional age estimation methods established by Demirjian, and by Moorrees, Funning, and Hunt, with a CNN-based approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The VGG16 model provided excellent results for cropped images containing only the third molars (38 and 48) and was able to capture the patterns and the features of development stages, so the overall accuracy obtained was greater than 90%. However, to analyze and classify the development stages defined by Demirjian and by Moorrees, Funning, and Hunt, the VGG16 model faced some limitations due to the insufficient sample of OPGs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The classification of age groups based on the development of third molars 38 and 48 demonstrated promising results with a high degree of accuracy. However, the limited sample size hindered the VGG16 model's ability to accurately differentiate between the various stages of tooth development. To enhance the model's accuracy and reliability, a larger and more diverse dataset is necessary to better capture the nuances of each developmental stage.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s41935-025-00489-3","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T03:40:43Z","timestamp":1760586043000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pre-trained VGG16 model for forensic dental age estimation"],"prefix":"10.1186","volume":"15","author":[{"given":"Valon","family":"Nushi","sequence":"first","affiliation":[]},{"given":"Rui","family":"Santos","sequence":"additional","affiliation":[]},{"given":"Hrvoje","family":"Brki\u0107","sequence":"additional","affiliation":[]},{"given":"Arlindo","family":"Oliveira","sequence":"additional","affiliation":[]},{"given":"Alexandre","family":"Francisco","sequence":"additional","affiliation":[]},{"given":"Cristiana","family":"Palmela Pereira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"key":"489_CR1","doi-asserted-by":"publisher","DOI":"10.3390\/oral5010003","volume":"5","author":"SS Alam","year":"2025","unstructured":"Alam SS, Rashid N, Faiza TA, Ahmed S, Hassan RA, Dudley J, Farook TH (2025) Estimating age and sex from dental panoramic radiographs using neural networks and vision\u2013language models. Oral 5:3. https:\/\/doi.org\/10.3390\/oral5010003","journal-title":"Oral"},{"key":"489_CR2","doi-asserted-by":"publisher","unstructured":"Augusto D, Pereira CP, Rodrigues A, Cameriere R, Salvado F, Santos R (2021) Dental age assessment by I2M and I3M: Portuguese legal age thresholds of 12 and 14 year olds. Acta Stomatol Croat 55(1):46\u201356. https:\/\/doi.org\/10.15644\/asc55\/1\/6","DOI":"10.15644\/asc55\/1\/6"},{"issue":"2","key":"489_CR3","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/s00414-010-0531-8","volume":"125","author":"IM Caldas","year":"2011","unstructured":"Caldas IM, J\u00falio P, Sim\u00f5es RJ, Matos E, Afonso A, Magalh\u00e3es T (2011) Chronological age estimation based on third molar development in a Portuguese population. Int J Legal Med 125(2):235\u2013243. https:\/\/doi.org\/10.1007\/s00414-010-0531-8","journal-title":"Int J Legal Med"},{"key":"489_CR4","unstructured":"Demirjian A (1973) A new system of dental age assessment. Hum Biol 45(2)"},{"key":"489_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-21294-1","volume":"12","author":"A Franco","year":"2022","unstructured":"Franco A, Porto L, Heng D, Murray J, Lygate A, Franco R, Bueno J, Sobania M, Costa MM, Paranhos LR, Manica S, Abade A (2022) Diagnostic performance of convolutional neural networks for dental sexual dimorphism. Sci Rep 12:17279. https:\/\/doi.org\/10.1038\/s41598-022-21294-1","journal-title":"Sci Rep"},{"key":"489_CR6","doi-asserted-by":"publisher","first-page":"4668","DOI":"10.1038\/s41598-024-55497-5","volume":"14","author":"A Franco","year":"2024","unstructured":"Franco A, Murray J, Heng D, Lygate A, Moreira D, Ferreira J, Miranda EP, Machado CP, Bueno J, M\u00e2nica S, Porto L, Abade A, Paranhos LR (2024) Binary decisions of artificial intelligence to classify third molar development around the legal age thresholds of 14, 16 and 18 years. Sci Rep 14:4668. https:\/\/doi.org\/10.1038\/s41598-024-55497-5","journal-title":"Sci Rep"},{"key":"489_CR7","doi-asserted-by":"publisher","first-page":"1589","DOI":"10.1007\/s00414-021-02542-x","volume":"135","author":"YC Guo","year":"2021","unstructured":"Guo YC, Han M, Chi Y et al (2021) Accurate age classification using manual method and deep convolutional neural network based on orthopantomogram images. Int J Legal Med 135:1589\u20131597. https:\/\/doi.org\/10.1007\/s00414-021-02542-x","journal-title":"Int J Legal Med"},{"issue":"3","key":"489_CR8","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1007\/s00414-022-02796-z","volume":"136","author":"M Han","year":"2022","unstructured":"Han M, Du S, Ge Y, Zhang D, Chi Y, Long H, Yang J, Yang Y, Xin J, Chen T, Zheng N, Guo YC (2022) With or without human interference for precise age estimation based on machine learning? Int J Legal Med 136(3):821\u2013831. https:\/\/doi.org\/10.1007\/s00414-022-02796-z","journal-title":"Int J Legal Med"},{"issue":"5","key":"489_CR9","doi-asserted-by":"publisher","first-page":"669","DOI":"10.4103\/njcp.njcp_220_24","volume":"27","author":"EA Kadan","year":"2024","unstructured":"Kadan EA, Kili\u00e7 R, Milo\u011flu \u00d6, \u00d6zbek \u0130Y, Oral EA (2024) Panoramic radiography in the evaluation of the relationship of maxillary molar teeth and maxillary sinuses on the deep learning models improved with the findings obtained by cone beam computed tomography. Niger J Clin Pract 27(5):669\u2013677. https:\/\/doi.org\/10.4103\/njcp.njcp_220_24","journal-title":"Niger J Clin Pract"},{"key":"489_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-025-11373-y","author":"RM Koch","year":"2025","unstructured":"Koch RM, Mentzel HJ, Heinrich A (2025) Deep learning for forensic age estimation using orthopantomograms in children, adolescents, and young adults. Eur Radiol. https:\/\/doi.org\/10.1007\/s00330-025-11373-y","journal-title":"Eur Radiol"},{"issue":"1\u20133","key":"489_CR11","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.forsciint.2009.03.033","volume":"188","author":"SH Lee","year":"2009","unstructured":"Lee SH, Lee JY, Park HK, Kim YK (2009) Development of third molars in Korean juveniles and adolescents. Forensic Sci Int 188(1\u20133):107\u2013111. https:\/\/doi.org\/10.1016\/j.forsciint.2009.03.033","journal-title":"Forensic Sci Int"},{"key":"489_CR12","doi-asserted-by":"crossref","unstructured":"Mincer HH, Harris EF, Berryman HE (1993) The A.B.F.O. study of third molar development and its use as an estimator of chronological age. J Forensic Sci 38(2):379\u2013390. Erratum in: J Forensic Sci 38(6):1524","DOI":"10.1520\/JFS13418J"},{"issue":"6","key":"489_CR13","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.1177\/00220345630420062701","volume":"42","author":"CFA Moorees","year":"1963","unstructured":"Moorees CFA, Fanning EA, Hunt EE (1963) Age variation of formation stages for permanent teeth. J Dent Res 42(6):1490\u20131502","journal-title":"J Dent Res"},{"key":"489_CR14","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1186\/s12903-024-04160-6","volume":"24","author":"SH Ong","year":"2024","unstructured":"Ong SH, Kim H, Song JS et al (2024) Fully automated deep learning approach to dental development assessment in panoramic radiographs. BMC Oral Health 24:426. https:\/\/doi.org\/10.1186\/s12903-024-04160-6","journal-title":"BMC Oral Health"},{"issue":"2","key":"489_CR15","first-page":"51","volume":"2","author":"M Parlak Baydo\u011fan","year":"2022","unstructured":"Parlak Baydo\u011fan M, Co\u015fgun Baybars S, Arslan Tuncer S (2022) Age detection by deep learning from dental panoramic radiographs. Artif Intell Theory Appl 2(2):51\u201358","journal-title":"Artif Intell Theory Appl"},{"key":"489_CR16","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.forsciint.2017.01.011","volume":"272","author":"S Pavlovic","year":"2017","unstructured":"Pavlovic S, Pereira CP, Santos R (2017) Age estimation in Portuguese population: the application of the London atlas of tooth development and eruption. Forensic Sci Int 272:97\u2013103. https:\/\/doi.org\/10.1016\/j.forsciint.2017.01.011","journal-title":"Forensic Sci Int"},{"key":"489_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.archoralbio.2021.105089","volume":"125","author":"CP Pereira","year":"2021","unstructured":"Pereira CP, Rodrigues A, Santos A, Salvado F, Santos R, Cameriere R (2021) Cut-off for the legal ages in the Portuguese population by third maturity index: measures of accuracy. Arch Oral Biol 125:105089. https:\/\/doi.org\/10.1016\/j.archoralbio.2021.105089","journal-title":"Arch Oral Biol"},{"key":"489_CR18","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1186\/s41935-022-00314-1","volume":"12","author":"P Pintana","year":"2022","unstructured":"Pintana P, Upalananda W, Saekho S et al (2022) Fully automated method for dental age estimation using the ACF detector and deep learning. Egypt J Forensic Sci 12:54. https:\/\/doi.org\/10.1186\/s41935-022-00314-1","journal-title":"Egypt J Forensic Sci"},{"key":"489_CR19","doi-asserted-by":"publisher","first-page":"7014","DOI":"10.3390\/app14167014","volume":"14","author":"TN Sahin","year":"2024","unstructured":"Sahin TN, K\u00f6l\u00fc\u015f T (2024) Age and sex estimation in children and young adults using panoramic radiographs with convolutional neural networks. Appl Sci 14:7014. https:\/\/doi.org\/10.3390\/app14167014","journal-title":"Appl Sci"},{"issue":"3","key":"489_CR20","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/s42979-021-00592-x","volume":"2","author":"IH Sarker","year":"2021","unstructured":"Sarker IH (2021) Machine learning: algorithms, real-world applications and research directions. SN Comput Sci 2(3):160. https:\/\/doi.org\/10.1007\/s42979-021-00592-x","journal-title":"SN Comput Sci"},{"issue":"1","key":"489_CR21","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1080\/00450618.2021.1882570","volume":"55","author":"W Upalananda","year":"2023","unstructured":"Upalananda W, Wantanajittikul K, Na Lampang S, Janhom A (2023) Semi-automated technique to assess the developmental stage of mandibular third molars for age estimation. Aust J Forensic Sci 55(1):23\u201333. https:\/\/doi.org\/10.1080\/00450618.2021.1882570","journal-title":"Aust J Forensic Sci"},{"issue":"2","key":"489_CR22","first-page":"30","volume":"41","author":"M Vodanovi\u0107","year":"2023","unstructured":"Vodanovi\u0107 M, Suba\u0161i\u0107 M, Milo\u0161evi\u0107 DP, Gali\u0107 I, Brki\u0107 H (2023) Artificial intelligence in forensic medicine and forensic dentistry. J Forensic Odonto-Stomatol 41(2):30\u201341","journal-title":"J Forensic Odonto-Stomatol"},{"issue":"1","key":"489_CR23","doi-asserted-by":"publisher","first-page":"70","DOI":"10.15644\/asc57\/1\/8","volume":"57","author":"M Vodanovi\u0107","year":"2023","unstructured":"Vodanovi\u0107 M, Suba\u0161i\u0107 M, Milo\u0161evi\u0107 D, Savi\u0107 Pavi\u010din I (2023) Artificial intelligence in medicine and dentistry. Acta Stomatol Croat 57(1):70\u201384. https:\/\/doi.org\/10.15644\/asc57\/1\/8","journal-title":"Acta Stomatol Croat"},{"key":"489_CR24","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1186\/s12903-023-02817-2","volume":"23","author":"J Wang","year":"2023","unstructured":"Wang J, Dou J, Han J et al (2023) A population-based study to assess two convolutional neural networks for dental age estimation. BMC Oral Health 23:109. https:\/\/doi.org\/10.1186\/s12903-023-02817-2","journal-title":"BMC Oral Health"},{"key":"489_CR25","doi-asserted-by":"publisher","DOI":"10.1007\/s12024-025-00962-4","author":"E Yilmaz","year":"2025","unstructured":"Yilmaz E, G\u00f6r\u00fcrg\u00f6z C, K\u0131\u015f HC et al (2025) Forensic dental age estimation with deep learning: a modified Xception model for panoramic X-ray images. Forensic Sci Med Pathol. https:\/\/doi.org\/10.1007\/s12024-025-00962-4","journal-title":"Forensic Sci Med Pathol"}],"container-title":["Egyptian Journal of Forensic Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41935-025-00489-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41935-025-00489-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41935-025-00489-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T03:40:48Z","timestamp":1760586048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ejfs.springeropen.com\/articles\/10.1186\/s41935-025-00489-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["489"],"URL":"https:\/\/doi.org\/10.1186\/s41935-025-00489-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5822184\/v1","asserted-by":"object"}]},"ISSN":["2090-5939"],"issn-type":[{"value":"2090-5939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,16]]},"assertion":[{"value":"13 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The investigation has been approved by the Ethics Committee of the Lisbon Academic Center of Medicine \u2013 Ref.\u00aa N. \u00ba 04\/23, 3rd March 2023 and performed in accordance with the etical standards specified by Ethics Committee of Faculty of Medicine, University of Lisbon, Portugal. All procedures performed in study were in accordance with the ethical standards of the institutional and\/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards. No informed consent was obtained since this was a retrospective study based on anonymized imagological records.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"73"}}