دورية أكاديمية
Impact of data synthesis strategies for the classification of craniosynostosis.
العنوان: | Impact of data synthesis strategies for the classification of craniosynostosis. |
---|---|
المؤلفون: | Schaufelberger M; Institute of Biomedical Engineering (IBT), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany., Kühle RP; Department of Oral, Dental and Maxillofacial Diseases, Heidelberg University Hospital, Heidelberg, Germany., Wachter A; Institute of Biomedical Engineering (IBT), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany., Weichel F; Department of Oral, Dental and Maxillofacial Diseases, Heidelberg University Hospital, Heidelberg, Germany., Hagen N; Institute of Medical Informatics, Heidelberg University Hospital, Heidelberg, Germany., Ringwald F; Institute of Medical Informatics, Heidelberg University Hospital, Heidelberg, Germany., Eisenmann U; Institute of Medical Informatics, Heidelberg University Hospital, Heidelberg, Germany., Hoffmann J; Department of Oral, Dental and Maxillofacial Diseases, Heidelberg University Hospital, Heidelberg, Germany., Engel M; Department of Oral, Dental and Maxillofacial Diseases, Heidelberg University Hospital, Heidelberg, Germany., Freudlsperger C; Department of Oral, Dental and Maxillofacial Diseases, Heidelberg University Hospital, Heidelberg, Germany., Nahm W; Institute of Biomedical Engineering (IBT), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany. |
المصدر: | Frontiers in medical technology [Front Med Technol] 2023 Dec 13; Vol. 5, pp. 1254690. Date of Electronic Publication: 2023 Dec 13 (Print Publication: 2023). |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: Frontiers Country of Publication: Switzerland NLM ID: 101772626 Publication Model: eCollection Cited Medium: Internet ISSN: 2673-3129 (Electronic) Linking ISSN: 26733129 NLM ISO Abbreviation: Front Med Technol Subsets: PubMed not MEDLINE |
أسماء مطبوعة: | Original Publication: Lausanne, Switzerland : Frontiers, [2019]- |
مستخلص: | Introduction: 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. Methods: 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)-based classification of craniosynostosis. The CNN is trained only on synthetic data but is validated and tested on clinical data. Results: 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. Conclusions: 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. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (© 2023 Schaufelberger, Kühle, Wachter, Weichel, Hagen, Ringwald, Eisenmann, Hoffmann, Engel, Freudlsperger and Nahm.) |
References: | J Plast Reconstr Aesthet Surg. 2020 Apr;73(4):723-731. (PMID: 31917189) Med Image Anal. 2014 May;18(4):635-46. (PMID: 24713202) Plast Reconstr Surg. 2009 Feb;123(2):635-642. (PMID: 19182624) J Craniomaxillofac Surg. 2021 Jun;49(6):449-455. (PMID: 33712336) J Neurosurg. 1982 Sep;57(3):370-7. (PMID: 7097333) Childs Nerv Syst. 2007 Mar;23(3):269-81. (PMID: 17186250) Int J Oral Maxillofac Surg. 2017 Jul;46(7):819-826. (PMID: 28392059) Sci Rep. 2020 Sep 18;10(1):15346. (PMID: 32948813) IEEE Trans Vis Comput Graph. 2010 Jul-Aug;16(4):621-35. (PMID: 20467060) Plast Reconstr Surg. 1989 Apr;83(4):738-42. (PMID: 2648432) BMC Genomics. 2007 Dec 12;8:458. (PMID: 18076769) Am J Med Genet A. 2008 Apr 15;146A(8):984-91. (PMID: 18344207) Int J Comput Assist Radiol Surg. 2017 Oct;12(10):1739-1749. (PMID: 28550406) IEEE Trans Image Process. 2004 Apr;13(4):600-12. (PMID: 15376593) Sci Rep. 2021 Sep 9;11(1):17970. (PMID: 34504140) J Clin Epidemiol. 1990;43(1):69-73. (PMID: 2319283) Diagnostics (Basel). 2022 Jun 21;12(7):. (PMID: 35885422) IEEE Trans Biomed Eng. 2023 Nov;70(11):3156-3165. (PMID: 37204949) Front Physiol. 2021 Jul 05;12:699291. (PMID: 34290623) |
فهرسة مساهمة: | Keywords: CNN; GAN; PCA; classification; craniosynostosis; generative adversarial network; photogrammetric surface scan; statistical shape model |
تواريخ الأحداث: | Date Created: 20240109 Latest Revision: 20240110 |
رمز التحديث: | 20240110 |
مُعرف محوري في PubMed: | PMC10773901 |
DOI: | 10.3389/fmedt.2023.1254690 |
PMID: | 38192519 |
قاعدة البيانات: | MEDLINE |
تدمد: | 2673-3129 |
---|---|
DOI: | 10.3389/fmedt.2023.1254690 |