{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T04:39:41Z","timestamp":1794890381538,"version":"4.9.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62376176"],"award-info":[{"award-number":["62376176"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Sichuan Science and Technology Program","award":["2023YFG0272"],"award-info":[{"award-number":["2023YFG0272"]}]},{"name":"Sichuan Science and Technology Program","award":["2024NSFSC0659"],"award-info":[{"award-number":["2024NSFSC0659"]}]},{"name":"Research and Develop Program of West China Hospital of Stomatology Sichuan University","award":["RD-03-202303"],"award-info":[{"award-number":["RD-03-202303"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur J Med Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Three-dimensional (3D) landmark detection is essential for assessing craniofacial growth and planning surgeries, such as orthodontic, orthognathic, traumatic, and plastic procedures. This study aimed to develop an automatic 3D landmarking model for oral and maxillofacial regions and to validate its accuracy, robustness and generalizability in both spiral computed tomography (SCT, 41 landmarks) and cone-beam computed tomography (CBCT, 14 landmarks) scans.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      The model was implemented using an optimized lightweight 3D\n                      <jats:italic>U<\/jats:italic>\n                      -Net network architecture. Its accuracy, robustness and generalizability were thoroughly evaluated and validated through a multicenter retrospective diagnostic study. The model was trained and tested on a data set of 480 SCT and 240 CBCT cases. An additional inference on a different data set of 320 SCT and 150 CBCT cases was performed. Mean radial error (MRE) and success detection rate within 2-, 3-, and 4-mm error thresholds were measured as the primary evaluation metrics. Error analyses for landmark detection along each coordinate axis were performed. Consistency tests among observers were conducted.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The average MRE for both SCT and CBCT was consistently below 1.3\u00a0mm and, notably, below 1.4\u00a0mm in complex conditions, such as malocclusion, missing dental landmarks, and the presence of metal artifacts. No significant differences in MRE and SDR at 2\u20134\u00a0mm were observed between external and internal SCT and CBCT sets. SCT bone landmarks were more precise than dental ones, with no difference between bone\/soft tissue and dental\/soft tissue. CBCT dental landmarks exhibited greater precision compared to bone landmarks. A detailed error analysis across the coordinate axes showed that the coronal axis had the highest error rates. The implementation of this model significantly improved the landmarking proficiency of senior and junior specialists by 15.9% and 28.9%, respectively, while also achieving a 6\u20139.5-fold acceleration in GUI interaction time.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study shows that the AI-driven model delivers high-precision 3D localization of oral and maxillofacial landmarks, even in complex scenarios. The model demonstrates potential as a promising computer-aided tool to assist specialists in conducting accurate and efficient localization analyses; however, its robustness and generalizability require prospective clinical validation to ensure utility across varied experience levels.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s40001-025-03198-8","type":"journal-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T10:44:26Z","timestamp":1761043466000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Accuracy and reliability of 3D cephalometric landmark detection with deep learning"],"prefix":"10.1186","volume":"30","author":[{"given":"Boyan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutao","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hailin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinglong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jixiang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,21]]},"reference":[{"key":"3198_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2024.105056","author":"A Polizzi","year":"2024","unstructured":"Polizzi A, Leonardi R. Automatic cephalometric landmark identification with artificial intelligence: an umbrella review of systematic reviews. J Dent. 2024. https:\/\/doi.org\/10.1016\/j.jdent.2024.105056.","journal-title":"J Dent"},{"key":"3198_CR2","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/s00784-023-04978-4","volume":"27","author":"F Blum","year":"2023","unstructured":"Blum F, M\u00f6hlhenrich SC, Raith S, et al. Evaluation of an artificial intelligence\u2013based algorithm for automated localization of craniofacial landmarks. Clin Oral Invest. 2023;27:225. https:\/\/doi.org\/10.1007\/s00784-023-04978-4.","journal-title":"Clin Oral Invest"},{"issue":"1","key":"3198_CR3","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1016\/j.jds.2020.05.022","volume":"16","author":"SB Khanagar","year":"2021","unstructured":"Khanagar SB, Al-Ehaideb A, Vishwanathaiah S, Maganur PC, Patil S, Naik S, et al. Scope and performance of artificial intelligence technology in orthodontic diagnosis, treatment planning, and clinical decision-making\u2014a systematic review. J Dent Sci. 2021;16(1):482\u201392.","journal-title":"J Dent Sci"},{"key":"3198_CR4","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1007\/s00784-024-06021-6","volume":"28","author":"M Sadek","year":"2024","unstructured":"Sadek M, Alaskari O, Hamdan A. Accuracy of web-based automated versus digital manual cephalometric landmark identification. Clin Oral Invest. 2024;28:621. https:\/\/doi.org\/10.1007\/s00784-024-06021-6.","journal-title":"Clin Oral Invest"},{"key":"3198_CR5","doi-asserted-by":"publisher","first-page":"40423","DOI":"10.1038\/srep40423","volume":"7","author":"C-T Ho","year":"2017","unstructured":"Ho C-T, Lin H-H, Liou EJW, Lo L-J. Three-dimensional surgical simulation improves the planning for correction of facial prognathism and asymmetry: a qualitative and quantitative study. Scient Rep. 2017;7:40423. https:\/\/doi.org\/10.1038\/srep40423.","journal-title":"Scient Rep"},{"issue":"4","key":"3198_CR6","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s00056-011-0032-5","volume":"72","author":"J Medelnik","year":"2011","unstructured":"Medelnik J, Hertrich K, Steinh\u00e4user-Andresen S, Hirschfelder U, Hofmann E. Accuracy of anatomical landmark identification using different CBCT- and MSCT-based 3D images: an in vitro study. J Orofac Orthop. 2011;72(4):261\u201378.","journal-title":"J Orofac Orthop"},{"key":"3198_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2022.104052","volume":"119","author":"D Apostolakis","year":"2022","unstructured":"Apostolakis D, Michelinakis G, Kamposiora P, Papavasiliou G. The current state of computer assisted orthognathic surgery: a narrative review. J Dent. 2022;119:104052.","journal-title":"J Dent"},{"issue":"3","key":"3198_CR8","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1016\/j.jds.2020.10.012","volume":"16","author":"S Takeda","year":"2021","unstructured":"Takeda S, Mine Y, Yoshimi Y, Ito S, Tanimoto K, Murayama T. Landmark annotation and mandibular lateral deviation analysis of posteroanterior cephalograms using a convolutional neural network. J Dent Sci. 2021;16(3):957\u201363.","journal-title":"J Dent Sci"},{"issue":"1","key":"3198_CR9","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.4.1.014501","volume":"4","author":"S\u00d6 Arik","year":"2017","unstructured":"Arik S\u00d6, Ibragimov B, Xing L. Fully automated quantitative cephalometry using convolutional neural networks. J Med Imaging. 2017;4(1):014501.","journal-title":"J Med Imaging"},{"issue":"4","key":"3198_CR10","doi-asserted-by":"publisher","first-page":"cjae029","DOI":"10.1093\/ejo\/cjae029","volume":"46","author":"J Hendrickx","year":"2024","unstructured":"Hendrickx J, Gracea RS, Vanheers M, Winderickx N, Preda F, Shujaat S, et al. Can artificial intelligence-driven cephalometric analysis replace manual tracing? A systematic review and meta-analysis. Eur J Orthod. 2024;46(4):cjae029. https:\/\/doi.org\/10.1093\/ejo\/cjae029.","journal-title":"Eur J Orthod"},{"key":"3198_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106380","volume":"210","author":"E Bermejo","year":"2021","unstructured":"Bermejo E, Taniguchi K, Ogawa Y, Martos R, Valsecchi A, Mesejo P, et al. Automatic landmark annotation in 3D surface scans of skulls: methodological proposal and reliability study. Comput Methods Programs Biomed. 2021;210:106380.","journal-title":"Comput Methods Programs Biomed"},{"issue":"5","key":"3198_CR12","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1007\/s11547-023-01629-2","volume":"128","author":"M Serafin","year":"2023","unstructured":"Serafin M, Baldini B, Cabitza F, Carrafiello G, Baselli G, Del Fabbro M, et al. Accuracy of automated 3D cephalometric landmarks by deep learning algorithms: systematic review and meta-analysis. Radiol Med. 2023;128(5):544\u201355.","journal-title":"Radiol Med"},{"issue":"3","key":"3198_CR13","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1177\/0022034520969115","volume":"100","author":"T Shan","year":"2021","unstructured":"Shan T, Tay FR, Gu L. Application of artificial intelligence in dentistry. J Dent Res. 2021;100(3):232\u201344.","journal-title":"J Dent Res"},{"key":"3198_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2024.105043","volume":"147","author":"Y Zhu","year":"2024","unstructured":"Zhu Y, Zhang L, Liu S, Wen A, Gao Z, Qin Q, et al. Automatic three-dimensional facial symmetry reference plane construction based on facial planar reflective symmetry net. J Dent. 2024;147:105043.","journal-title":"J Dent"},{"key":"3198_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2021.103610","volume":"107","author":"F Schwendicke","year":"2021","unstructured":"Schwendicke F, Singh T, Lee JH, Gaudin R, Chaurasia A, Wiegand T, et al. Artificial intelligence in dental research: checklist for authors, reviewers, readers. J Dent. 2021;107:103610.","journal-title":"J Dent"},{"key":"3198_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12916-014-0241-z","volume":"13","author":"GS Collins","year":"2015","unstructured":"Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMC Med. 2015;13:1. https:\/\/doi.org\/10.1186\/s12916-014-0241-z.","journal-title":"BMC Med"},{"issue":"3","key":"3198_CR17","doi-asserted-by":"publisher","first-page":"e250","DOI":"10.1016\/j.ajodo.2021.09.012","volume":"161","author":"J Yao","year":"2022","unstructured":"Yao J, Zeng W, He T, Zhou S, Zhang Y, Guo J, et al. Automatic localization of cephalometric landmarks based on convolutional neural network. Am J Orthod Dentofacial Orthop. 2022;161(3):e250\u20139. https:\/\/doi.org\/10.1016\/j.ajodo.2021.09.012.","journal-title":"Am J Orthod Dentofacial Orthop"},{"issue":"11","key":"3198_CR18","doi-asserted-by":"publisher","first-page":"1380","DOI":"10.1177\/00220345221112333","volume":"101","author":"G Dot","year":"2022","unstructured":"Dot G, Schouman T, Chang S, Rafflenbeul F, Kerbrat A, Rouch P, et al. Automatic 3-dimensional cephalometric landmarking via deep learning. J Dent Res. 2022;101(11):1380\u20137.","journal-title":"J Dent Res"},{"key":"3198_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101621","volume":"60","author":"J Zhang","year":"2020","unstructured":"Zhang J, Liu M, Wang L, Chen S, Yuan P, Li J, et al. Context-guided fully convolutional networks for joint craniomaxillofacial bone segmentation and landmark digitization. Med Image Anal. 2020;60:101621.","journal-title":"Med Image Anal"},{"key":"3198_CR20","first-page":"807","volume":"12264","author":"C Lian","year":"2020","unstructured":"Lian C, Wang F, Deng HH, Wang L, Xiao D, Kuang T, et al. Multi-task dynamic transformer network for concurrent bone segmentation and large-scale landmark localization with dental CBCT. Med Image Comput Comput Assist Interv. 2020;12264:807\u201316.","journal-title":"Med Image Comput Comput Assist Interv"},{"key":"3198_CR21","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1007\/978-3-030-87589-3_62","volume":"12966","author":"Q Liu","year":"2021","unstructured":"Liu Q, Deng H, Lian C, Chen X, Xiao D, Ma L, et al. SkullEngine: a multi-stage CNN framework for collaborative CBCT image segmentation and landmark detection. Mach Learn Med Imaging. 2021;12966:606\u201314.","journal-title":"Mach Learn Med Imaging"},{"issue":"7","key":"3198_CR22","doi-asserted-by":"publisher","first-page":"20170030","DOI":"10.1259\/dmfr.20170030","volume":"46","author":"C Nardi","year":"2017","unstructured":"Nardi C, Talamonti C, Pallotta S, Saletti P, Calistri L, Cordopatri C, et al. Head and neck effective dose and quantitative assessment of image quality: a study to compare Cone Beam CT and Multislice Spiral CT. Dentomaxillofac Radiol. 2017;46(7):20170030.","journal-title":"Dentomaxillofac Radiol"},{"issue":"1","key":"3198_CR23","doi-asserted-by":"publisher","first-page":"1571","DOI":"10.1186\/s12903-024-05395-z","volume":"24","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Liu Y, Liu T, Zhang J, Lin P, Liu D. Evaluation of CBCT reconstructed tooth models at different thresholds and voxels and their accuracy in fusion with IOS data: an in vitro validation study. BMC Oral Health. 2024;24(1):1571. https:\/\/doi.org\/10.1186\/s12903-024-05395-z.","journal-title":"BMC Oral Health"},{"issue":"1","key":"3198_CR24","doi-asserted-by":"publisher","first-page":"17509","DOI":"10.1038\/s41598-021-97116-7","volume":"11","author":"SH Kang","year":"2021","unstructured":"Kang SH, Jeon K, Kang S-H, Lee S-H. 3D cephalometric landmark detection by multiple stage deep reinforcement learning. Sci Rep. 2021;11(1):17509.","journal-title":"Sci Rep"},{"issue":"2","key":"3198_CR25","doi-asserted-by":"publisher","first-page":"505","DOI":"10.3390\/s21020505","volume":"21","author":"M-J Kim","year":"2021","unstructured":"Kim M-J, Liu Y, Oh SH, Ahn H-W, Kim S-H, Nelson G. Automatic cephalometric landmark identification system based on the multi-stage convolutional neural networks with CBCT combination images. Sensors. 2021;21(2):505.","journal-title":"Sensors"},{"issue":"9","key":"3198_CR26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0275114","volume":"17","author":"HS Yun","year":"2022","unstructured":"Yun HS, Hyun CM, Baek SH, Lee S-H, Seo JK. A semi-supervised learning approach for automated 3D cephalometric landmark identification using computed tomography. PLoS ONE. 2022;17(9):e0275114.","journal-title":"PLoS ONE"},{"key":"3198_CR27","volume":"614","author":"C Li","year":"2024","unstructured":"Li C, Liu B, Guikun Xu, Guo J, Tang W, He T. A pseudo-3D coarse-to-fine architecture for 3D medical landmark detection. Neurocomputing. 2024;614:128782.","journal-title":"Neurocomputing"},{"key":"3198_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102529","volume":"81","author":"Y Zhao","year":"2022","unstructured":"Zhao Y, Zeng K, Zhao Y, Bhatia P, Ranganath M, Kozhikkavil ML, et al. Hermosillo G, Deep learning solution for medical image localization and orientation detection. Med Image Anal. 2022;81:102529.","journal-title":"Med Image Anal"},{"issue":"24","key":"3198_CR29","doi-asserted-by":"publisher","first-page":"5350","DOI":"10.3390\/s19245350","volume":"19","author":"S Chim","year":"2019","unstructured":"Chim S, Lee JG, Park HH. Dilated skip convolution for facial landmark detection. Sensors. 2019;19(24):5350.","journal-title":"Sensors"},{"key":"3198_CR30","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.neunet.2022.10.021","volume":"157","author":"Y Huang","year":"2023","unstructured":"Huang Y, Huang H. Stacked attention hourglass network based robust facial landmark detection. Neural Netw. 2023;157:323\u201335.","journal-title":"Neural Netw"},{"issue":"7","key":"3198_CR31","doi-asserted-by":"publisher","first-page":"4299","DOI":"10.1007\/s00784-021-03990-w","volume":"25","author":"F Schwendicke","year":"2021","unstructured":"Schwendicke F, Chaurasia A, Arsiwala L, Lee JH, Elhennawy K, Jost-Brinkmann PG, et al. Deep learning for cephalometric landmark detection: systematic review and meta-analysis. Clin Oral Investig. 2021;25(7):4299\u2013309.","journal-title":"Clin Oral Investig"},{"key":"3198_CR32","doi-asserted-by":"publisher","first-page":"1294","DOI":"10.3390\/electronics14071294","volume":"14","author":"A Thurzo","year":"2025","unstructured":"Thurzo A. Provable AI ethics and explainability in medical and educational AI agents: trustworthy ethical firewall. Electronics. 2025;14:1294.","journal-title":"Electronics"},{"issue":"5","key":"3198_CR33","doi-asserted-by":"publisher","first-page":"101","DOI":"10.3390\/ai6050101","volume":"6","author":"A Thurzo","year":"2025","unstructured":"Thurzo A, Thurzo V. Embedding fear in medical AI: a risk-averse framework for safety and ethics. AI. 2025;6(5):101. https:\/\/doi.org\/10.3390\/ai6050101.","journal-title":"AI"}],"container-title":["European Journal of Medical Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40001-025-03198-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40001-025-03198-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40001-025-03198-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T23:05:03Z","timestamp":1761087903000},"score":1,"resource":{"primary":{"URL":"https:\/\/eurjmedres.biomedcentral.com\/articles\/10.1186\/s40001-025-03198-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["3198"],"URL":"https:\/\/doi.org\/10.1186\/s40001-025-03198-8","relation":{},"ISSN":["2047-783X"],"issn-type":[{"value":"2047-783X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]},"assertion":[{"value":"22 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 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 authors declared no potential conflicts of interest with respect to the research, authorship, and\/or publication of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1000"}}