Abstract
The accuracy of cephalometric landmark identification for malocclusion classification is essential for diagnosis and treatment planning. Identifying these landmarks is often complex and time-consuming for orthodontists. An AI model for classification was recently developed. This model was investigated based on current regulatory considerations as a result of the strict regulations on software systems and the lack of information on artificial intelligence (AI) requirements in this publication. The platform developed by the ITU/WHO for AI is used to assess the models of the application. The auditing procedure assessed the development process concerning medical device regulations, data protection regulations, and ethical considerations. Upon that, the major tasks during the development were evaluated, such as qualification, annotation procedure, and data set attributes. The AI models were investigated under consideration of technical, clinical, regulatory, and ethical considerations. The risk to the patient and user’s health can be considered low according to the International Medical Device Regulators Forum (IMDRF) definition. This application facilitates the decision and planning of malocclusion treatment based on lateral cephalograms without cephalometric landmarks. It is comparable with common standards in orthodontic diagnosis.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
For the audit, the data collection was placed on a GitHub repository https://github.com/aiaudit-org/trial-audits-team-itgdental/tree/main/data. Data collection can be found in section 2.1.
References
HJ Yu, SR Cho, MJ Kim, WH Kim, JW Kim, and Choi J. Automated skeletal classification with lateral cephalometry based on artificial intelligence. J Dent Res., 99(3):249–56, 2020.
S Yim, S Kim, I Kim, JW Park, JH Cho, and Hong M. Accuracy of one-step automated orthodontic diagnosis model using a convolutional neural network and lateral cephalogram images with different qualities obtained from nationwide multi-hospitals. Korean J Orthod., 52(1):3–19, 2022.
H-J Kim, KD Kim, and D-H. Kim. Deep convolutional neural network-based skeletal classification of cephalometric image compared with automated-tracing software. Scientific Reports., 12(1)(11659), 2022.
MA Giannopoulou, AC Kondylidou-Sidira, MA Papadopoulos, and AE Athanasiou. Are orthodontic landmarks and variables in digital cephalometric radiography taken in fixed and natural head positions reliable? International Orthodontics, 18(1):54–68, 2020.
HL da Silveira and HE. Silveira. Reproducibility of cephalometric measurements made by three radiology clinics.
H Kim, E Shim, J Park, YJ Kim, U Lee, and Y. Kim. Web-based fully automated cephalometric analysis by deep learning. Comput Methods Programs Biomed., 194(105513), 2020.
L. Oala, J. Fehr, L. Gilli, Balachandran, A. W. P., Leite, S. CalderonRamirez, G. Li, D. X.and Nobis, E. A. M. n. Alvarado, G. Jaramillo-Gutierrez, C. Matek, A. Shroff, F. Kherif, B. Sanguinetti, , and T. Wiegand. Ml4h auditing: From paper to practice. In Proceedings of the Machine Learning for Health NeurIPS Workshop., 136:280–317, 2020.
Funding
This publication was not financially supported.
Author information
Authors and Affiliations
Contributions
Behnaz Mohammad, Saeed Reza Motamedian conceived of the presented medical background and developed the performed the computations. Akhilanand Chaurasia performed the clinical evaluation. Shankeeth Vinayahalingam and Joachim Krois evaluated the technical aspects of the model. Anahita Haiat also contributed to the technical evaluation and supported in the configuration. Johannes Tanne did the regulatory assessment, supported in the configuration. Hossein Mohammad-Rahimi did the ethical assessment, shared the data and did the supervision of the publication. All authors discussed the results and contributed to the final manuscript.
Corresponding author
Ethics declarations
Ethics approval
No ethical approval was necessary for this kind of investigation. Ethics commitee of the Shahid Beheshti Univerity of Medical Sciences approved the initial study (IRB number: IR.SBMU.DRC.REC.1400.007).
Conflicts of interest
The authors declare not conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Github repository: https://github.com/aiaudit-org/trial-audits-team-i-tg-dental/tree/main/ Eval AI Overview TG-Dental Challenge https://health.aiaudit.org/web/challenges/challenge-page/383/overview.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Johannes, T., Akhilanand, C., Joachim, K. et al. Evaluation of AI Model for Cephalometric Landmark Classification (TG Dental). J Med Syst 47, 92 (2023). https://doi.org/10.1007/s10916-023-01977-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-023-01977-6