Orthodontics’ Digital Transformation (Literature Review)
DOI:
https://doi.org/10.5281/a10.5281/zenodo.21962937Ключевые слова:
AI, ML, neural networks, orthodontics, orthodontic therapy, automationАннотация
One of the most important technical developments in orthodontics nowadays is artificial intelligence (AI). The
comprehensive diagnostics, effective segmentation of bone structures, and prediction of treatment outcomes based on
individual patient characteristics are all successfully automated by neural network algorithms. AI not only predetermines
the indications for surgery in orthognathic surgery but also offers precise 3D surgical planning. A new paradigm for communication
between doctors and patients is being established by the visualisation of treatment results.
Subject. This study focuses on artificial intelligence systems for automating diagnostics, planning orthodontic treatments,
and forecasting outcomes.
Aim. In order to identify the primary vectors of the digital transformation in the field of dentistry, an analysis of the literature
devoted to the implementation of artificial intelligence technologies in orthodontic practice will be conducted.
Materials and Methods. Based on an examination of the eLIBRARY, Scopus, Google Scholar, PubMed/MEDLINE, and
MDPI databases, a study of the literature on the use of AI in orthodontics from 2019 to 2025 was carried out. Consequently,
110 scholarly articles were chosen and scrutinised thoroughly.
Outcomes. Thus far, the digital evolution of orthodontics has shown considerable advancement via the use of neural
network frameworks. AI is capable of identifying and classifying dentofacial anomalies from photographs, determining
skeletal maturity stages, and performing comprehensive diagnoses. This includes the identification of the causes of
anomalies, cephalometric analysis, 3D modelling, assessment of the temporomandibular joint (TMJ) condition, and facial
scanning. These systems enhance the efficiency of clinicians’ work by expediting data analysis, minimising diagnostic
errors, providing a “second opinion” in intricate cases, and generating clear visualisations of potential treatment outcomes.
Conclusions. Contemporary technologies provide novel opportunities for enhancing the standard of orthodontic treatment.
Nonetheless, to achieve effective AI integration, systemic obstacles need to be tackled: enhancing the quality of input
data, mitigating model overfitting, and performing thorough clinical validation of the algorithms.
At this juncture, the domain is shifting from experimental innovations to practical implementation, with clinicians retaining
the primary role while AI functions as a decision-support instrument.
Библиографические ссылки
1. Ahn, J. S., et al. (2021). Automated landmark detection on lateral cephalograms using deep convolutional neural networks.
Journal of Dentistry, 109, 103658.
2. Alauddin, M. S., et al. (2023). Applications of artificial intelligence in dentistry: A comprehensive review. Journal of
International Oral Health, 15(1), 1-10.
3. Alqahtani, H., et al. (2022). Accuracy and reliability of artificial intelligence in cephalometric landmark detection: A systematic
review. International Journal of Environmental Research and Public Health, 19(21), 14210.
4. Anas, M., et al. (2022). Deep learning applications in detection and diagnosis of dental caries: A systematic review.
Diagnostics, 12(8), 1874
5. Arik, S. O., et al. (2017). Fully automated landmark detection in cephalometric radiography using convolutional neural
networks. IEEE Transactions on Medical Imaging, 36(11), 2410–2422.
6. Bichu, Y. M., et al. (2021). Artificial intelligence in orthodontics: A scoping review. The Angle Orthodontist, 91(6), 841-
856.
7. Bozkur, M., & Kaya, B. (2023). Deep learning algorithms for cephalometric analysis: Performance evaluation and clinical
applicability. Turkish Journal of Orthodontics, 36(2), 112–119.
8. Buman, S., et al. (2022). Automated orthodontic treatment planning using machine learning frameworks. Progress in
Orthodontics, 23(1), 45.
9. Chen, H., et al. (2021). Deep learning for automatic landmark detection on 2D lateral cephalograms. BMC Oral Health,
21(1), 432.
10. Chen, Y., et al. (2022). Artificial intelligence in clear aligner therapy: Current application and future perspectives. BMC
Oral Health, 22(1), 312
11. Diagnocat AI Systems. (2023). Automated dental CBCT and radiographic interpretation platform. Available at: https://
diagnocat.com.
12. Dindaroğlu, F., et al. (2020). Deep learning applications in orthodontic diagnosis and treatment planning: A systematic
review. Journal of Orofacial Orthopedics, 81(5), 375–389.
13. Elnagar, M. H., et al. (2022). Robotics and artificial intelligence in contemporary orthodontics. Seminars in Orthodontics,
28(3), 180-191.
14. Gao, J., et al. (2021). Automated identification of anatomical landmarks on facial scans using deep neural networks.
Computers in Biology and Medicine, 135, 104589.
15. Gu, Y., et al. (2021). Development and validation of a deep learning model for automated cephalometric analysis.
Scientific Reports, 11(1), 16821.
16. Guo, Y., et al. (2020). Automated lateral and posteroanterior cephalometric tracing on web-based AI platforms: Reliability
and efficiency. Korean Journal of Orthodontics, 50(4), 265–274.
17. Gupta, A., et al. (2022). Artificial intelligence in dentistry: A state-of-the-art review. Journal of Dental Research, Dental
Clinics, Dental Prospects, 16(2), 75-83.
18. Han, X., et al. (2021). Evaluation of deep learning models for automatic segmentation of teeth in CBCT images. International
Journal of Computer Assisted Radiology and Surgery, 16(7), 1145-1155.
19. Hwang, J. J., et al. (2019). Development of an artificial intelligence model for automatic landmark detection on lateral
cephalograms. The Angle Orthodontist, 89(6), 882-888.
20. Ismail, M. A., et al. (2023). Machine learning models for predicting tooth extraction decisions in orthodontic treatment.
American Journal of Orthodontics and Dentofacial Orthopedics, 163(3), 380-391.
21. Jeon, S. H., et al. (2021). Deep learning-based automated diagnosis of malocclusion using facial and intraoral photos.
Journal of Clinical Medicine, 10(18), 4125.
22. Jiang, F., et al. (2022). Precision evaluation of artificial intelligence-based cephalometric analysis: A cross-sectional
comparative study. Journal of Dentistry, 124, 104230.
23. Jung, S. K., & Kim, T. W. (2021). New possibilities of artificial intelligence in orthodontics. Journal of the World Federation
of Orthodontists, 10(3), 95–101.
24. Kadioglu, O., et al. (2022). Digital transformation in orthodontic education and practice. Seminars in Orthodontics,
28(2), 110-118.
25. Kangas, J., et al. (2023). Reliability of AI-based landmark detection in lateral cephalometry: A multi-center validation.
European Journal of Orthodontics, 45(4), 410-418.
26. Katyal, V., et al. (2021). The accuracy of AI-driven remote monitoring systems in clear aligner therapy. Journal of
Aligner Orthodontics, 5(2), 115-123.
27. Kibar, C. D., et al. (2023). Topographic 3D facial analysis in patients with craniofacial anomalies using deep learning
models. Orthodontics & Craniofacial Research, 26(S2), 88–97.
28. Kim, H., et al. (2020). Deep learning for tooth segmentation and classification on 3D digital dental models. Medical
Image Analysis, 61, 101638.
29. Kim, I., et al. (2021). Automated prediction of facial growth in children using deep convolutional neural networks. American
Journal of Orthodontics and Dentofacial Orthopedics, 159(5), 620-629.
30. Kok, H., et al. (2021). Comparison of artificial intelligence and human experts in cephalometric landmark identification.
Dental Press Journal of Orthodontics, 26(4), e2119310.
31. Kunz, F., et al. (2020). Artificial intelligence in orthodontics: Evaluation of a fully automated cephalometric analysis
software. Journal of Orofacial Orthopedics, 81(1), 52-63.
32. Lau, B., et al. (2022). Accuracy and speed comparison between professional 3D facial scanners and mobile application-
based scanners. Journal of Cranio-Maxillofacial Surgery, 50(9), 712-719.
33. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.
34. Lee, C., et al. (2020). Artificial intelligence-based landmark detection for cephalometric analysis: A systematic review
and meta-analysis. Scientific Reports, 10(1), 22185.
35. Lee, J. H., et al. (2022). Cephalometric risk stratification of obstructive sleep apnea in pediatric orthodontic patients
using machine learning models. Sleep Medicine, 98, 142–150.
36. Lee, K. S., et al. (2021). Automated cephalometric landmark identification using multiscale convolutional neural networks.
Computers in Biology and Medicine, 131, 104273.
37. Li, P., et al. (2021). Deep learning applications in orthognathic surgical planning: A scoping review. International Journal
of Oral and Maxillofacial Surgery, 50(11), 1450–1458.
38. Li, Z., et al. (2023). Automated dental plaque and gingivitis detection using deep learning on intraoral images. Journal
of Periodontal Research, 58(2), 245-254.
39. Liu, Y., et al. (2021). Machine learning in dentistry: Fundamentals, applications, and future directions. Journal of Dental
Sciences, 16(3), 1015-1025.
40. Lo, Giudice A., et al. (2020). Accuracy of 3D facial digital models obtained with low-cost smartphone technology. International
Journal of Environmental Research and Public Health, 17(18), 6589.
Загрузки
Опубликован
Выпуск
Раздел
Лицензия
Copyright (c) 2026 MAKTABGACHA VA MAKTAB TA’LIMI JURNALI
Это произведение доступно по лицензии Creative Commons «Attribution» («Атрибуция») 4.0 Всемирная.
