COMPARATIVE ANALYSIS OF THREE MACHINE LEARNING MODELS FOR EARLY PREDICTION OF SKELETAL CLASS-III MALOCCLUSION FROM PROFILE PHOTOS

Öz

The pre-adolescent growth period is the best time for the skeletal Class-III malocclusion treatment. Diagnosis and treatment during this period continue to be a complex orthodontic problem. Class-III malocclusion is complicated to treat with braces frequently requiring surgical intervention after a pubertal growth spurt. In addition, delayed recognition of the problem will yield significant functional, aesthetic, and psychological concerns. This study presents the first fully automated machine learning method to accurately diagnose Class-III malocclusion applied across mobile images, to the best of our knowledge. For this purpose, we comparatively evaluated three machine learning approaches: a deep learning algorithm, a machine learning algorithm, and a rule-based algorithm. We collected a novel profile image data set for this analysis along with their formal diagnosis from 435 orthodontics patients. The most successful method among the three was the machine learning method, with an accuracy of %76.

Anahtar Kelimeler

• Class III Malocclusion
• Machine Learning
• Medical Informatics

Kaynakça

1. Staudt CB, Kiliaridis S. “Different skeletal types underlying Class-III malocclusion in a random population.” Am J Orthod Dentofacial Orthop, 136(5), 715-721, 2009.
2. Oltramari-Navarro PV, de Almeida RR, Conti AC, Navarro Rde L, de Almeida MR, Fernandes LS. “Early treatment protocol for skeletal Class-III malocclusion.” Braz Dent J. ,24(2), 167-173, 2013.
3. Al-Khalifa, Hussein. (2014). “Orthopedic Correction of Class-III Malocclusions during Mixed Dentition.” Open Journal of Stomatology. 04(07), 372-380,2014
4. Mandall N, Cousley R, DiBiase A, Dyer F, Littlewood S, Mattick R, Nute SJ, Doherty B, Stivaros N, McDowall R, Shargill I, Worthington HV. “Early Class-III protraction facemask treatment reduces the need for orthognathic surgery: a multi-centre, two-arm parallel randomized, controlled trial.” J Orthod., 43(3), 164-175, 2016.
5. Sharma JN. “Epidemiology of malocclusions and assessment of orthodontic treatment need for the population of eastern Nepal.” World J Orthod., 10(4), 311- 316, 2009.
6. X. Xu et al., "Advances in Smartphone-Based Point-of-Care Diagnostics," in Proceedings of the IEEE, vol. 103, no. 2, pp. 236-247, Feb. 2015, doi: 10.1109/JPROC.2014.2378776.
7. Digital around the world - datareportal – global digital insights. DataReportal. (n.d.). Retrieved July 25, 2022, from https://datareportal.com/global-digital-overview
8. Mobile Health Industry Trends and forecast 2021. Artezio. (n.d.). Retrieved July 24, 2022, from https://www.artezio.com/pressroom/blog/mobile-industry-forecast/

9. Gupta G, Vaid NR. “The World of Orthodontic apps.” APOS Trends Orthod, 7(2), 73, 2017.
10. Development, C. S. (n.d.). Dental4Windows. Download.com. Retrieved July 24, 2022, from https://download.cnet.com/Dental4Windows/3000-2129_4-76472046.html
11. Baheti, M.J., Toshniwal, N. “Orthodontic apps at fingertips.”, Progress in Orthodontic, 15(1), 36, 2014.
12. Phimentum. (n.d.). Retrieved July 23, 2022, from https://www.phimentum.com/
13. Demircan, G.S., Kılıç, B., Önal-Süzek, T. (2021). “Early Diagnosis and Prediction of Skeletal Class-III Malocclusion from Profile Photos Using Artificial Intelligence.” In: Jarm, T., Cvetkoska, A., Mahnič-Kalamiza, S., Miklavcic, D. (eds) 8th European Medical and Biological Engineering Conference. EMBEC 2020. IFMBE Proceedings, 80, 434-448, 2020.
14. Basciftci,F.A.,Uysal,T.,Buyukerkmen,A.“Determinati on of Holdaway soft tissue norms in Anatolian Turkish adults” Am J Orthod Dentofacial Orthop, 123(4),395-400, 2003.
15. 1adrianb. (n.d.). 1adrianb/face-alignment: 2D and 3D face alignment library build using pytorch. GitHub. Retrieved July 24, 2022, from https://github.com/1adrianb/face-alignment.