{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:15:50Z","timestamp":1792782950490,"version":"4.5.0"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Sivas Cumhuriyet University","id":[{"id":"https:\/\/ror.org\/04f81fm77","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Odontology"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This study aimed to develop and evaluate a multi-task deep learning model for the simultaneous classification of sagittal, vertical, and transverse malocclusion components, as well as midline deviation, using three-dimensional (3D) intraoral scan (IOS) data. A total of 801 anonymized 3D IOS datasets were retrospectively collected. Surface mesh (STL) files were standardized and converted into six-view two-dimensional (2D) representations. This approach preserved morphological information while enabling the use of transfer learning-based convolutional neural networks (CNNs). A shared-backbone, multi-head architecture was designed to perform simultaneous classification tasks. Six CNN backbones were evaluated using accuracy, precision, recall, F1-score, and ROC-AUC. EfficientNetV2B3 achieved the highest performance in anterior bite classification (accuracy: 80%, ROC-AUC\u2009\u2248\u20090.89). ResNet50 provided the most balanced results for sagittal and midline classification. Transverse occlusion classification showed comparatively lower performance across all models. Multi-view representations derived from 3D intraoral scans enable simultaneous and clinically relevant classification of multiple malocclusion components. While strong performance was observed for anterior bite and midline tasks, sagittal and transverse classifications remain more challenging. IOS-based multi-task AI systems may serve as supportive tools in orthodontic diagnosis and digital workflows.<\/jats:p>","DOI":"10.1007\/s10266-026-01400-9","type":"journal-article","created":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T03:14:29Z","timestamp":1778642069000},"page":"2722-2732","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automated classification of sagittal, vertical, and transverse malocclusions from 3D intraoral scans via a multi-head CNN framework"],"prefix":"10.1007","volume":"114","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0496-8564","authenticated-orcid":false,"given":"Yunus","family":"Balel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaan","family":"Sa\u011fta\u015f","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatih","family":"Teke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehmet Ali","family":"Kurt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,13]]},"reference":[{"key":"1400_CR1","doi-asserted-by":"publisher","first-page":"2716","DOI":"10.3390\/ijerph20032716","volume":"20","author":"D R\u00f3\u017ca\u0144ska-Perli\u0144ska","year":"2023","unstructured":"R\u00f3\u017ca\u0144ska-Perli\u0144ska D, Jaszczur-Nowicki J, Kruczkowski D, Bukowska JM. Dental malocclusion in mixed dentition children and its relation to podal system and gait parameters. Int J Environ Res Public Health MDPI. 2023;20:2716.","journal-title":"Int J Environ Res Public Health MDPI"},{"key":"1400_CR2","volume-title":"Applications of Artificial Intelligence in Dental Malocclusion: A Scoping Review of Recent Advances (2020\u20132025).\u00a0AI","author":"M Hung","year":"2026","unstructured":"Hung M, Cohen O, Beasley N, Ziebarth C, Schwartz C, Parry A, et al. Applications of Artificial Intelligence in Dental Malocclusion: A Scoping Review of Recent Advances (2020\u20132025).\u00a0AI. Multidisciplinary Digital Publishing Institute; 2026."},{"key":"1400_CR3","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1111\/jcpe.13062","volume":"46","author":"O Bernhardt","year":"2019","unstructured":"Bernhardt O, Krey K, Daboul A, Voelzke H, Kindler S, Kocher T, et al. New insights in the link between malocclusion and periodontal disease. J Clin Periodontol Wiley Online Libr. 2019;46:144\u201359.","journal-title":"J Clin Periodontol Wiley Online Libr"},{"key":"1400_CR4","first-page":"1","volume":"21","author":"L Huang","year":"2025","unstructured":"Huang L, Xu Y, Xiao Z, Liu Y, Luo F. Temporomandibular disorder prevalence in malocclusion patients: a meta-analysis. Head Face Med Springer. 2025;21:1\u201312.","journal-title":"Head Face Med Springer"},{"key":"1400_CR5","first-page":"21","volume":"14","author":"OD Otuyemi","year":"1995","unstructured":"Otuyemi OD, Jones SP. Methods of assessing and grading malocclusion: a review. Aust Orthod J. 1995;14:21\u20137.","journal-title":"Aust Orthod J"},{"key":"1400_CR6","doi-asserted-by":"publisher","first-page":"984","DOI":"10.58600\/eurjther1691","volume":"29","author":"Y Balel","year":"2023","unstructured":"Balel Y. The role of artificial intelligence in academic paper writing and its potential as a co-author. Eur J Ther. 2023;29:984\u20135.","journal-title":"Eur J Ther"},{"key":"1400_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jormas.2023.101471","volume":"124","author":"Y Balel","year":"2023","unstructured":"Balel Y. Can ChatGPT be used in oral and maxillofacial surgery? J Stomatol Oral Maxillofac Surg. 2023;124:101471. https:\/\/doi.org\/10.1016\/j.jormas.2023.101471.","journal-title":"J Stomatol Oral Maxillofac Surg"},{"key":"1400_CR8","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.ajodo.2024.03.012","volume":"166","author":"E Bardideh","year":"2024","unstructured":"Bardideh E, Alizadeh FL, Amiri M, Ghorbani M. Designing an artificial intelligence system for dental occlusion classification using intraoral photographs: a comparative analysis between artificial intelligence-based and clinical diagnoses. Am J Orthod Dentofac Orthop Elsevier. 2024;166:125\u201337.","journal-title":"Am J Orthod Dentofac Orthop Elsevier"},{"key":"1400_CR9","doi-asserted-by":"publisher","first-page":"100918","DOI":"10.1016\/j.imu.2022.100918","volume":"30","author":"M Aljabri","year":"2022","unstructured":"Aljabri M, Aljameel SS, Min-Allah N, Alhuthayfi J, Alghamdi L, Alduhailan N, et al. Canine impaction classification from panoramic dental radiographic images using deep learning models. Inf Med Unlocked [Internet]. 2022;30:100918. https:\/\/doi.org\/10.1016\/j.imu.2022.100918.","journal-title":"Inf Med Unlocked [Internet]"},{"key":"1400_CR10","first-page":"1642","volume":"17","author":"R Alsubhi","year":"2024","unstructured":"Alsubhi R, Alsharif H, Barashi M, Kadi H. Classification of Dental Crowding Severity Using Hybrid Deep Learning Model. J Int Dent Med Res Ectodermal Dysplasia Group-Turkey. 2024;17:1642\u20139.","journal-title":"J Int Dent Med Res Ectodermal Dysplasia Group-Turkey"},{"key":"1400_CR11","doi-asserted-by":"publisher","DOI":"10.3290\/j.ijcd.b5290567","author":"Z Chai","year":"2025","unstructured":"Chai Z, Wu Z, Zhang C, Song J. Automated detection of anterior crossbite on intraoral images and videos utilizing deep learning. Int J Comput Dent. 2025. https:\/\/doi.org\/10.3290\/j.ijcd.b5290567.","journal-title":"Int J Comput Dent"},{"key":"1400_CR12","doi-asserted-by":"publisher","DOI":"10.1186\/s13005-024-00448-8","volume":"20","author":"B Noeldeke","year":"2024","unstructured":"Noeldeke B, Vassis S, Sefidroodi M, Pauwels R, Stoustrup P, Springer. Comparison of deep learning models to detect crossbites on 2D intraoral photographs. Head Face Med. 2024;20:45.","journal-title":"Head Face Med"},{"key":"1400_CR13","doi-asserted-by":"crossref","unstructured":"Borghi L, Lumetti L, Cremonini F, Rizzo F, Grana C, Lombardo L, et al. Bits2Bites: Intra-oral Scans Occlusal Classification. Oral Dent Image Anal Work; 2025;1:1-10.","DOI":"10.1007\/978-3-032-20711-1_5"},{"key":"1400_CR14","doi-asserted-by":"publisher","first-page":"61","DOI":"10.5933\/JKAPD.2025.52.1.61","volume":"52","author":"S Kim","year":"2025","unstructured":"Kim S, Lee E, Park S, Jeong T, Shin J. Maxillo-mandibular transverse relationship of primary second molar and permanent first molar of children in mixed dentition: a cone-beam computed tomography analysis. J Korean Acad Pediatr Dent Korean Acad Pediatr Dentistry. 2025;52:61\u201375.","journal-title":"J Korean Acad Pediatr Dent Korean Acad Pediatr Dentistry"},{"key":"1400_CR15","doi-asserted-by":"publisher","DOI":"10.1186\/s40510-025-00586-y","volume":"26","author":"OA Rasol","year":"2025","unstructured":"Rasol OA, Hajeer MY, Alam MK, Jaber ST, Kara-Boulad JM, Jaber S, et al. Evaluation of different methods of correcting deep bite in adult and adolescent patients: a systematic review and meta-analysis. Prog Orthod. 2025;26:37. https:\/\/doi.org\/10.1186\/s40510-025-00586-y.","journal-title":"Prog Orthod"},{"key":"1400_CR16","doi-asserted-by":"crossref","unstructured":"Alsubhi R, Alsharif H, Kadi H, Barashi M. Dental crowding prediction from occlusal view images using deep learning. 2024 IEEE Int Conf Autom Control Intell Syst. IEEE; 2024. pp. 95\u2013100.","DOI":"10.1109\/I2CACIS61270.2024.10649861"},{"key":"1400_CR17","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-025-01345-0","volume":"24","author":"Q Chang","year":"2025","unstructured":"Chang Q, Bai Y, Wang S, Wang F, Liang S, Xie X, et al. Automated orthodontic diagnosis via self-supervised learning and multi-attribute classification using lateral cephalograms. Biomed Eng Online. 2025;24:9.","journal-title":"Biomed Eng Online"},{"key":"1400_CR18","doi-asserted-by":"publisher","DOI":"10.1186\/s13005-023-00397-8","volume":"19","author":"R Guo","year":"2023","unstructured":"Guo R, Tian Y, Li X, Li W, He D, Sun Y, et al. Facial profile evaluation and prediction of skeletal class II patients during camouflage extraction treatment: a pilot study. Head Face Med. 2023;19:51.","journal-title":"Head Face Med"},{"key":"1400_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ortho.2024.100926","volume":"22","author":"K O\u2019Friel","year":"2024","unstructured":"O\u2019Friel K, Chapple A, Ballard R, Armbruster P, Elsevier. Assessing AudaxCeph\u00ae\u2019s cephalometric tracing technology versus a semi-automated approach for analyzing severe Class II and Class III skeletons. Int Orthod. 2024;22:100926.","journal-title":"Int Orthod"},{"key":"1400_CR20","doi-asserted-by":"publisher","first-page":"1749","DOI":"10.1007\/s11277-024-11358-y","volume":"136","author":"M Juneja","year":"2024","unstructured":"Juneja M, Saini SK, Kaur H, Jindal P. Application of convolutional neural networks for dentistry occlusion classification. Wirel Pers Commun. 2024;136:1749\u201367. https:\/\/doi.org\/10.1007\/s11277-024-11358-y.","journal-title":"Wirel Pers Commun"},{"key":"1400_CR21","doi-asserted-by":"publisher","first-page":"102460","DOI":"10.1109\/ACCESS.2023.3317512","volume":"11","author":"P Xu","year":"2023","unstructured":"Xu P, Gholamalizadeh T, Moshfeghifar F, Darkner S, Erleben K. Deep-learning-based segmentation of individual tooth and bone with periodontal ligament interface details for simulation purposes. IEEE Access IEEE. 2023;11:102460\u201370.","journal-title":"IEEE Access IEEE"}],"container-title":["Odontology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10266-026-01400-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10266-026-01400-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10266-026-01400-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T21:15:35Z","timestamp":1790889335000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10266-026-01400-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,13]]},"references-count":21,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["1400"],"URL":"https:\/\/doi.org\/10.1007\/s10266-026-01400-9","relation":{},"ISSN":["1618-1247","1618-1255"],"issn-type":[{"value":"1618-1247","type":"print"},{"value":"1618-1255","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,13]]},"assertion":[{"value":"24 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"None.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"During the preparation of this manuscript, the authors used ChatGPT as a language editing and style improvement tool. After using this service, the authors carefully reviewed and edited the content as needed and took full responsibility for the final version of the manuscript.","order":2,"name":"Ethics","label":"Declaration of generative AI in scientific writing","group":{"name":"EthicsHeading","label":"Declarations"}}]}}