{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T23:20:58Z","timestamp":1792797658776,"version":"4.5.0"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100009133","name":"KIT-Publication Fund of the Karlsruhe Institute of Technology","doi-asserted-by":"publisher","award":["\u00a0"],"award-info":[{"award-number":["\u00a0"]}],"id":[{"id":"10.13039\/100009133","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med. Technol."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Photogrammetric surface scans provide a radiation-free option to assess and classify craniosynostosis. Due to the low prevalence of craniosynostosis and high patient restrictions, clinical data are rare. Synthetic data could support or even replace clinical data for the classification of craniosynostosis, but this has never been studied systematically.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We tested the combinations of three different synthetic data sources: a statistical shape model (SSM), a generative adversarial network (GAN), and image-based principal component analysis for a convolutional neural network (CNN)\u2013based classification of craniosynostosis. The CNN is trained only on synthetic data but is validated and tested on clinical data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The combination of an SSM and a GAN achieved an accuracy of 0.960 and an F1 score of 0.928 on the unseen test set. The difference to training on clinical data was smaller than 0.01. Including a second image modality improved classification performance for all data sources.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Without a single clinical training sample, a CNN was able to classify head deformities with similar accuracy as if it was trained on clinical data. Using multiple data sources was key for a good classification based on synthetic data alone. Synthetic data might play an important future role in the assessment of craniosynostosis.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmedt.2023.1254690","type":"journal-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T05:04:31Z","timestamp":1702443871000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Impact of data synthesis strategies for the classification of craniosynostosis"],"prefix":"10.3389","volume":"5","author":[{"given":"Matthias","family":"Schaufelberger","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reinald Peter","family":"K\u00fchle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Wachter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederic","family":"Weichel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niclas","family":"Hagen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Friedemann","family":"Ringwald","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Urs","family":"Eisenmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Hoffmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Engel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Freudlsperger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Werner","family":"Nahm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,12,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/0895-4356(90)90058-W","article-title":"A population-based study of craniosynostosis","volume":"43","author":"French","year":"1990","journal-title":"J Clin Epidemiol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"738","DOI":"10.1097\/00006534-198904000-00025","article-title":"Virchow, the pathogenesis of craniosynostosis: a translation of his original work","volume":"83","author":"Persing","year":"1989","journal-title":"Plast Reconstr Surg"},{"key":"B3","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1186\/1471-2164-8-458","article-title":"Unravelling the molecular control of calvarial suture fusion in children with craniosynostosis","volume":"8","author":"Coussens","year":"2007","journal-title":"BMC Genomics"},{"key":"B4","doi-asserted-by":"publisher","first-page":"984","DOI":"10.1002\/ajmg.a.32208","article-title":"A population-based study of craniosynostosis in metropolitan Atlanta, 1989\u20132003","volume":"146","author":"Boulet","year":"2008","journal-title":"Am J Med Genet A"},{"key":"B5","doi-asserted-by":"publisher","first-page":"370","DOI":"10.3171\/jns.1982.57.3.0370","article-title":"Intracranial pressure in craniostenosis","volume":"57","author":"Renier","year":"1982","journal-title":"J Neurosurg"},{"key":"B6","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s00381-006-0251-z","article-title":"Neurodevelopment of children with single suture craniosynostosis: a review","volume":"23","author":"Kapp-Simon","year":"2007","journal-title":"Childs Nerv Syst"},{"key":"B7","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1097\/PRS.0b013e318195661a","article-title":"Single sutural craniosynostoses: surgical outcomes and long-term growth","volume":"123","author":"Fearon","year":"2009","journal-title":"Plast Reconstr Surg"},{"key":"B8","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1016\/j.bjps.2019.11.006","article-title":"Comparison of black bone MRI and 3D-CT in the preoperative evaluation of patients with craniosynostosis","volume":"73","author":"Saarikko","year":"2020","journal-title":"J Plast Reconstr Aesthet Surg"},{"key":"B9","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1016\/j.isprsjprs.2020.06.013","article-title":"Fully automatic smartphone-based photogrammetric 3D modelling of infant\u2019s heads for cranial deformation analysis","volume":"166","author":"Barbero-Garc\u00eda","year":"2020","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"B10","article-title":"A statistical shape model of craniosynostosis patients and 100 model instances of each pathology","volume-title":"Zenodo","author":"Schaufelberger","year":"2021"},{"key":"B11","author":"Nagel","year":""},{"key":"B12","doi-asserted-by":"publisher","first-page":"699291","DOI":"10.3389\/fphys.2021.699291","article-title":"Using machine learning to characterize atrial fibrotic substrate from intracardiac signals with a hybrid in silico and in vivo dataset","volume":"12","author":"S\u00e1nchez","year":"2021","journal-title":"Front Physiol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1016\/j.media.2014.02.008","article-title":"Personalized assessment of craniosynostosis via statistical shape modeling","volume":"18","author":"Mendoza","year":"2014","journal-title":"Med Image Anal"},{"key":"B14","doi-asserted-by":"publisher","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":"B15","doi-asserted-by":"publisher","first-page":"15346","DOI":"10.1038\/s41598-020-72143-y","article-title":"Combining deep learning with 3D stereophotogrammetry for craniosynostosis diagnosis","volume":"10","author":"de Jong","year":"2020","journal-title":"Sci Rep"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1516","DOI":"10.3390\/diagnostics12071516","article-title":"A radiation-free classification pipeline for craniosynostosis using statistical shape modeling","volume":"12","author":"Schaufelberger","year":"2022","journal-title":"Diagnostics"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TBME.2023.3278030","article-title":"3D-2D distance maps conversion enhances classification of craniosynostosis","volume":"70","author":"Schaufelberger","year":"2023","journal-title":"IEEE Trans Biomed Eng"},{"key":"B18","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1016\/j.ijom.2017.03.017","article-title":"A new method for three-dimensional evaluation of the cranial shape and the automatic identification of craniosynostosis using 3D stereophotogrammetry","volume":"46","author":"Meulstee","year":"2017","journal-title":"Int J Oral Maxillofac Surg"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1739","DOI":"10.1007\/s11548-017-1614-5","article-title":"Statistical shape modelling to aid surgical planning: associations between surgical parameters and head shapes following spring-assisted cranioplasty","volume":"12","author":"Rodriguez-Florez","year":"2017","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"B20","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1016\/j.jcms.2021.02.020","article-title":"Statistical shape modelling for the analysis of head shape variations","volume":"49","author":"Heutinck","year":"2021","journal-title":"J Cranio-Maxillofac Surg"},{"key":"B21","first-page":"139","article-title":"Generative adversarial networks. Commun","volume-title":"ACM","author":"Goodfellow","year":"2020"},{"key":"B22","author":"Pinetz","year":""},{"key":"B23","author":"Cignoni","year":""},{"key":"B24","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1109\/TVCG.2009.96","article-title":"Almost isometric mesh parameterization through abstract domains","volume":"16","author":"Pietroni","year":"2010","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"B25","author":"Dai","year":""},{"key":"B26","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1016\/j.patrec.2019.09.026","article-title":"Augmenting a 3D morphable model of the human head with high resolution ears","volume":"128","author":"Dai","year":"2019","journal-title":"Pattern Recognit Lett"},{"key":"B27","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1007\/s11263-019-01260-7","article-title":"Statistical modeling of craniofacial shape and texture","volume":"128","author":"Dai","year":"2020","journal-title":"Int J Comput Vis"},{"key":"B28","article-title":"Conditional generative adversarial nets","volume-title":"arXiv Preprint","author":"Mirza","year":"2014"},{"key":"B29","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","volume-title":"arXiv Preprint","author":"Radford","year":""},{"key":"B30","article-title":"Wasserstein GAN","volume-title":"arXiv Preprint","author":"Arjovsky","year":"2017"},{"key":"B31","first-page":"arXiv:1704.00028","article-title":"Improved training of wasserstein gans","volume-title":"arXiv Preprint","author":"Gulrajani","year":"2017"},{"key":"B32","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1515\/cdbme-2022-1005","article-title":"Generative-adversarial-network-based data augmentation for the classification of craniosynostosis","volume":"8","author":"Kaiser","year":"2022","journal-title":"Curr Dir Biomed Eng"},{"key":"B33","article-title":"Towards principled methods for training generative adversarial networks","volume-title":"arXiv Preprint","author":"Arjovsky","year":"2017"},{"key":"B34","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans Image Process"},{"key":"B35","author":"Paszke","year":""},{"key":"B36","volume-title":"Zenodo","author":"Schaufelberger","year":"2023"},{"key":"B37","author":"Agarwal","year":""}],"container-title":["Frontiers in Medical Technology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmedt.2023.1254690\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T05:04:35Z","timestamp":1702443875000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmedt.2023.1254690\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":37,"alternative-id":["10.3389\/fmedt.2023.1254690"],"URL":"https:\/\/doi.org\/10.3389\/fmedt.2023.1254690","relation":{},"ISSN":["2673-3129"],"issn-type":[{"value":"2673-3129","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,13]]},"article-number":"1254690"}}