{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T19:17:28Z","timestamp":1787167048138,"version":"build-2736575974"},"reference-count":39,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T00:00:00Z","timestamp":1699920000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"University of Heidelberg and Karlsruhe","award":["HEiKA_19-17"],"award-info":[{"award-number":["HEiKA_19-17"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Positional cranial deformities are a common finding in toddlers, yet differentiation from craniosynostosis can be challenging. The aim of this study was to train convolutional neural networks (CNNs) to classify craniofacial deformities based on 2D images generated using photogrammetry as a radiation-free imaging technique. A total of 487 patients with photogrammetry scans were included in this retrospective cohort study: children with craniosynostosis (n = 227), positional deformities (n = 206), and healthy children (n = 54). Three two-dimensional images were extracted from each photogrammetry scan. The datasets were divided into training, validation, and test sets. During the training, fine-tuned ResNet-152s were utilized. The performance was quantified using tenfold cross-validation. For the detection of craniosynostosis, sensitivity was at 0.94 with a specificity of 0.85. Regarding the differentiation of the five existing classes (trigonocephaly, scaphocephaly, positional plagiocephaly left, positional plagiocephaly right, and healthy), sensitivity ranged from 0.45 (positional plagiocephaly left) to 0.95 (scaphocephaly) and specificity ranged from 0.87 (positional plagiocephaly right) to 0.97 (scaphocephaly). We present a CNN-based approach to classify craniofacial deformities on two-dimensional images with promising results. A larger dataset would be required to identify rarer forms of craniosynostosis as well. The chosen 2D approach enables future applications for digital cameras or smartphones.<\/jats:p>","DOI":"10.3390\/jcm12227082","type":"journal-article","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T11:04:32Z","timestamp":1699959872000},"page":"7082","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["The Use of Artificial Intelligence for the Classification of Craniofacial Deformities"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9941-6772","authenticated-orcid":false,"given":"Reinald","family":"Kuehle","sequence":"first","affiliation":[{"name":"Department of Oral and Maxillofacial Surgery, University of Heidelberg, 69120 Heidelberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0572-4820","authenticated-orcid":false,"given":"Friedemann","family":"Ringwald","sequence":"additional","affiliation":[{"name":"Institute of Medical Informatics, University of Heidelberg, 69120 Heidelberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederic","family":"Bouffleur","sequence":"additional","affiliation":[{"name":"Department of Oral and Maxillofacial Surgery, University of Heidelberg, 69120 Heidelberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8578-8703","authenticated-orcid":false,"given":"Niclas","family":"Hagen","sequence":"additional","affiliation":[{"name":"Institute of Medical Informatics, University of Heidelberg, 69120 Heidelberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7501-9222","authenticated-orcid":false,"given":"Matthias","family":"Schaufelberger","sequence":"additional","affiliation":[{"name":"Institute of Biomedical Engineering, Karlsruhe Institute for Technology, 76131 Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8095-5090","authenticated-orcid":false,"given":"Werner","family":"Nahm","sequence":"additional","affiliation":[{"name":"Institute of Biomedical Engineering, Karlsruhe Institute for Technology, 76131 Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1322-755X","authenticated-orcid":false,"given":"J\u00fcrgen","family":"Hoffmann","sequence":"additional","affiliation":[{"name":"Department of Oral and Maxillofacial Surgery, University of Heidelberg, 69120 Heidelberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Freudlsperger","sequence":"additional","affiliation":[{"name":"Department of Oral and Maxillofacial Surgery, University of Heidelberg, 69120 Heidelberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Engel","sequence":"additional","affiliation":[{"name":"Department of Oral and Maxillofacial Surgery, University of Heidelberg, 69120 Heidelberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8770-3822","authenticated-orcid":false,"given":"Urs","family":"Eisenmann","sequence":"additional","affiliation":[{"name":"Institute of Medical Informatics, University of Heidelberg, 69120 Heidelberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1016\/j.jcms.2016.07.007","article-title":"Increase of prevalence of craniosynostosis","volume":"44","author":"Cornelissen","year":"2016","journal-title":"J. Craniomaxillofac. Surg."},{"key":"ref_2","first-page":"85","article-title":"The incidence of isolated craniosynostosis in the newborn infant","volume":"139","author":"Shuper","year":"1985","journal-title":"Am. J. Dis. Child."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1097\/00006534-198904000-00025","article-title":"Virchow and the pathogenesis of craniosynostosis: A translation of his original work","volume":"83","author":"Persing","year":"1989","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_4","first-page":"230","article-title":"On dwarfism, particularly in Franconia, and on pathological skull shapes","volume":"2","author":"Virchow","year":"1851","journal-title":"Verh. Phys. Med. Ges."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.cps.2018.11.009","article-title":"Syndromic Craniosynostosis","volume":"46","author":"Steinbacher","year":"2019","journal-title":"Clin. Plast. Surg."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/s00381-006-0251-z","article-title":"Neurodevelopment of children with single suture craniosynostosis: A review","volume":"23","author":"Speltz","year":"2007","journal-title":"Childs Nerv. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1093\/jpepsy\/jsh068","article-title":"Single-suture craniosynostosis: A review of neurobehavioral research and theory","volume":"29","author":"Speltz","year":"2004","journal-title":"J. Pediatr. Psychol."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Cacciaguerra, G., and Palermo, M. (2021). The Evolution of the Role of Imaging in the Diagnosis of Craniosynostosis: A Narrative Review. Children, 8.","DOI":"10.3390\/children8090727"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1097\/PRS.0000000000007830","article-title":"Weighing in on the Controversy: Preoperative Imaging in Unicoronal Craniosynostosis Leads to Strategic Changes in Surgical Care","volume":"147","author":"Ulma","year":"2021","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1667\/RR1393.1","article-title":"Radiation dose to the brain and subsequent risk of developing brain tumors in pediatric patients undergoing interventional neuroradiology procedures","volume":"170","author":"Simon","year":"2008","journal-title":"Radiat. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1056\/NEJM198810203191601","article-title":"Tumors of the brain and nervous system after radiotherapy in childhood","volume":"319","author":"Ron","year":"1988","journal-title":"N. Engl. J. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.1097\/SCS.0b013e3181ebe92a","article-title":"Measuring cranial vault volume with three-dimensional photography: A method of measurement comparable to the gold standard","volume":"21","author":"McKay","year":"2010","journal-title":"J. Craniofac. Surg."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1016\/j.jcms.2017.01.002","article-title":"Quantifying the effect of corrective surgery for trigonocephaly: A non-invasive, non-ionizing method using three-dimensional handheld scanning and statistical shape modelling","volume":"45","author":"Goktekin","year":"2017","journal-title":"J. Craniomaxillofac. Surg."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"726","DOI":"10.1016\/j.jcms.2012.01.007","article-title":"Objectification of cranial vault correction for craniosynostosis by three-dimensional photography","volume":"40","author":"Wilbrand","year":"2012","journal-title":"J. Craniomaxillofac. Surg."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1016\/j.bjps.2014.03.009","article-title":"Three-dimensional orbital dysmorphology in metopic synostosis","volume":"67","author":"Ezaldein","year":"2014","journal-title":"J. Plast. Reconstr. Aesthet. Surg."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1428","DOI":"10.1016\/j.jcms.2015.07.018","article-title":"A 3D morphometric follow-up analysis after frontoorbital advancement in non-syndromic craniosynostosis","volume":"43","author":"Martini","year":"2015","journal-title":"J. Craniomaxillofac. Surg."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s10006-013-0399-0","article-title":"Assessing aesthetic outcomes after trigonocephaly correction","volume":"18","author":"Metzler","year":"2014","journal-title":"J. Oral Maxillofac. Surg."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1097\/SCS.0b013e318272dacb","article-title":"Analysis of cosmetic results of metopic synostosis: Concordance and interobserver variability","volume":"24","author":"Anand","year":"2013","journal-title":"J. Craniofac. Surg."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1097\/PRS.0000000000002052","article-title":"Objective Assessment of the Interfrontal Angle for Severity Grading and Operative Decision-Making in Metopic Synostosis","volume":"137","author":"Anolik","year":"2016","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1007\/s00381-012-1721-0","article-title":"Avoiding CT scans in children with single-suture craniosynostosis","volume":"28","author":"Schweitzer","year":"2012","journal-title":"Childs Nerv. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1080\/0268869021000007560","article-title":"Are routine preoperative CT scans necessary in the management of single suture craniosynostosis?","volume":"16","author":"Cerovac","year":"2002","journal-title":"Br. J. Neurosurg."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1246","DOI":"10.1016\/j.bjps.2012.03.038","article-title":"Value of preoperative imaging in the diagnostics of isolated metopic suture synostosis: A risk-benefit analysis","volume":"65","author":"Engel","year":"2012","journal-title":"J. Plast. Reconstr. Aesthet. Surg."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1097\/00006534-199401000-00003","article-title":"Metopic synostosis: Quantitative assessment of presenting deformity and surgical results based on CT scans","volume":"93","author":"Posnick","year":"1994","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.ijom.2021.06.003","article-title":"Photogrammetric evaluation of corrective surgery for trigonocephaly","volume":"51","author":"Kuehle","year":"2021","journal-title":"Int. J. Oral Maxillofac. Surg."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1007\/s00247-013-2673-6","article-title":"Craniosynostosis: Imaging review and primer on computed tomography","volume":"43","author":"Badve","year":"2013","journal-title":"Pediatr. Radiol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1159\/000489175","article-title":"CT Imaging Findings after Craniosynostosis Reconstructive Surgery","volume":"53","author":"Ginat","year":"2018","journal-title":"Pediatr. Neurosurg."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1097\/RTI.0000000000000385","article-title":"Machine Learning and Deep Neural Networks in Thoracic and Cardiovascular Imaging","volume":"34","author":"Retson","year":"2019","journal-title":"J. Thorac. Imaging"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1148\/radiol.2019182465","article-title":"Deep Convolutional Neural Network-based Software Improves Radiologist Detection of Malignant Lung Nodules on Chest Radiographs","volume":"294","author":"Sim","year":"2020","journal-title":"Radiology"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Goyal, M., and Knackstedt, T. (2020). Artificial intelligence-based image classification methods for diagnosis of skin cancer: Challenges and opportunities. Comput. Biol. Med., 127.","DOI":"10.1016\/j.compbiomed.2020.104065"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Singh, S.P., and Wang, L. (2020). 3D Deep Learning on Medical Images: A Review. Sensors, 20.","DOI":"10.3390\/s20185097"},{"key":"ref_31","first-page":"iv35","article-title":"Deep learning for medical image analysis: A brief introduction","volume":"2","author":"Wiestler","year":"2020","journal-title":"Neurooncol. Adv."},{"key":"ref_32","first-page":"5","article-title":"Genetics of craniosynostosis: Review of the literature","volume":"2","author":"Ciurea","year":"2009","journal-title":"J. Med. Life"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"967","DOI":"10.1097\/SCS.0000000000007369","article-title":"A Role for Artificial Intelligence in the Classification of Craniofacial Anomalies","volume":"32","author":"Geisler","year":"2021","journal-title":"J. Craniofac. Surg."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"15346","DOI":"10.1038\/s41598-020-72143-y","article-title":"Combining deep learning with 3D stereophotogrammetry for craniosynostosis diagnosis","volume":"10","author":"Bijlsma","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1051e","DOI":"10.1097\/PRS.0000000000006260","article-title":"Quantification of Head Shape from Three-Dimensional Photography for Presurgical and Postsurgical Evaluation of Craniosynostosis","volume":"144","author":"Porras","year":"2019","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"495","DOI":"10.3390\/diagnostics10070495","article-title":"Dimensional Image-Based Screening Tool for Infants with Positional Cranial Deformities: A Machine Learning Approach","volume":"10","author":"Jung","year":"2020","journal-title":"Diagnostics"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"17970","DOI":"10.1038\/s41598-021-96821-7","article-title":"Automatic detection and monitoring of abnormal skull shape in children with deformational plagiocephaly using deep learning","volume":"11","author":"Tabatabaei","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_39","first-page":"2746","article-title":"Automated Sagittal Craniosynostosis Classification from CT Images Using Transfer Learning","volume":"5","author":"You","year":"2020","journal-title":"Clin. Surg."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/12\/22\/7082\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:22:41Z","timestamp":1760131361000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/12\/22\/7082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,14]]},"references-count":39,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["jcm12227082"],"URL":"https:\/\/doi.org\/10.3390\/jcm12227082","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,14]]}}}