Machine learning assisted Cameriere method for dental age estimation

Shihui Shen, Zihao Liu, Jian Wang, Linfeng Fan, Fang Ji, Jiang Tao, Shihui Shen, Zihao Liu, Jian Wang, Linfeng Fan, Fang Ji, Jiang Tao

Abstract

Background: Recently, the dental age estimation method developed by Cameriere has been widely recognized and accepted. Although machine learning (ML) methods can improve the accuracy of dental age estimation, no machine learning research exists on the use of the Cameriere dental age estimation method, making this research innovative and meaningful.

Aim: The purpose of this research is to use 7 lower left permanent teeth and three models [random forest (RF), support vector machine (SVM), and linear regression (LR)] based on the Cameriere method to predict children's dental age, and compare with the Cameriere age estimation.

Subjects and methods: This was a retrospective study that collected and analyzed orthopantomograms of 748 children (356 females and 392 males) aged 5-13 years. Data were randomly divided into training and test datasets in an 80-20% proportion for the ML algorithms. The procedure, starting with randomly creating new training and test datasets, was repeated 20 times. 7 permanent developing teeth on the left mandible (except wisdom teeth) were recorded using the Cameriere method. Then, the traditional Cameriere formula and three models (RF, SVM, and LR) were used to estimate the dental age. The age prediction accuracy was measured by five indicators: the coefficient of determination (R2), mean error (ME), root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE).

Results: The research showed that the ML models have better accuracy than the traditional Cameriere formula. The ME, MAE, MSE, and RMSE values of the SVM model (0.004, 0.489, 0.392, and 0.625, respectively) and the RF model (- 0.004, 0.495, 0.389, and 0.623, respectively) were lower with the highest accuracy. In contrast, the ME, MAE, MSE and RMSE of the European Cameriere formula were 0.592, 0.846, 0.755, and 0.869, respectively, and those of the Chinese Cameriere formula were 0.748, 0.812, 0.890 and 0.943, respectively.

Conclusions: Compared to the Cameriere formula, ML methods based on the Cameriere's maturation stages were more accurate in estimating dental age. These results support the use of ML algorithms instead of the traditional Cameriere formula.

Keywords: Cameriere; Dental age; Machine learning; Tooth development.

Conflict of interest statement

We hereby confirm that no competing interest exits in the submission of this manuscript, and manuscript is approved by all authors for publication.

© 2021. The Author(s).

Figures

Fig. 1
Fig. 1
Left: An example of single root tooth measurement. Ai, i = 1, …,5 (teeth with one root), is the distance between the inner sides of the open apex; Right: An example of multiple root tooth measurement. Ai, i = 6,7 (teeth with two open apices) is the sum of the distances between the inner sides of the two open apices; and Li, i = 1,…,7, is the length of the seventh teeth
Fig. 2
Fig. 2
A schematic outline of the operational procedures and analytical steps
Fig. 3
Fig. 3
Age and sex distribution for each category of age per year
Fig. 4
Fig. 4
Heat map showing the mean of the mean absolute errors (MAE) calculated from the 20 replicates for each pair of dental age estimation methods
Fig. 5
Fig. 5
ME, MAE, MSE and RMSE of machine learning methods (LR, SVM & RF) and Cameriere formula (European, Chinese formula)

References

    1. Bagherian A, Sadeghi M. Assessment of dental maturity of children aged 3.5 to 13.5 years using the Demirjian method in an Iranian population. J Oral Sci. 2011;53:37–42. doi: 10.2334/josnusd.53.37.
    1. Kumaresan R, Cugati N, Chandrasekaran B, Karthikeyan P. Reliability and validity of five radiographic dental-age estimation methods in a population of Malaysian children. J Investig Clin Dent [Internet] 2016;7(1):102–109. doi: 10.1111/jicd.12116.
    1. Franklin D. Forensic age estimation in human skeletal remains: current concepts and future directions. Leg Med [Internet] 2010;12(1):1–7. doi: 10.1016/j.legalmed.2009.09.001.
    1. Hashim HA, Mansoor H, Mohamed MHH. Assessment of skeletal age using hand-wrist radiographs following Bjork system. J Int Soc Prev Community Dent [Internet] 2018;8(6):482–427.
    1. Cardoso HF. Environmental effects on skeletal versus dental development: using a documented subadult skeletal sample to test a basic assumption in human osteological research. Am J Phys Anthr [Internet] 2007;132(2):223–233. doi: 10.1002/ajpa.20482.
    1. Conceicao EL, Cardoso HF. Environmental effects on skeletal versus dental development II: further testing of a basic assumption in human osteological research. Am J Phys Anthr [Internet] 2011;144(3):463–470. doi: 10.1002/ajpa.21433.
    1. Laurencin D, Wong A, Chrzanowski W, Knowles JC, Qiu D, Pickup DM, et al. Probing the calcium and sodium local environment in bones and teeth using multinuclear solid state NMR and X-ray absorption spectroscopy. Phys Chem Chem Phys [Internet] 2010;12(5):1081–91. doi: 10.1039/B915708E.
    1. Jelliffe EF, Jelliffe DB. Deciduous dental eruption, nutrition and age assessment. J Trop Pediatr Environ Child Health [Internet] 1973;19(2):193–248.
    1. Willems G, Van Olmen A, Spiessens B, Carels C. Dental Age Estimation in Belgian Children: Demirjian’s Technique Revisited. J Forensic Sci. 2001;46:893–895. doi: 10.1520/JFS15064J.
    1. Ye X, Jiang F, Sheng X, Huang H, Shen X. Dental age assessment in 7–14-year-old Chinese children: comparison of Demirjian and Willems methods. Forensic Sci Int [Internet] 2014;244:36–41. doi: 10.1016/j.forsciint.2014.07.027.
    1. Cameriere R, De Angelis D, Ferrante L, Scarpino F, Cingolani M. Age estimation in children by measurement of open apices in teeth: a European formula. Int J Leg Med [Internet] 2007;121(6):449–453. doi: 10.1007/s00414-007-0179-1.
    1. Rai B, Cameriere R, Ferrante L. Accuracy of Cameriere et al regression equation in Haryana population. Rom J Leg Med. 2009;17:147–150. doi: 10.4323/rjlm.2009.147.
    1. Bagh T, Chatra L, Shenai P, Km V, Rao PK, Prabhu RV, et al. Age estimation using Cameriere ’ s seven teeth method with indian specific formula in South Indian children. Int J Adv Health Sci. 2014;1(2):2–10.
    1. Mazzilli LEN, Melani RFH, Lascala CA, Palacio LAV, Cameriere R. Age estimation: Cameriere’s open apices methodology accuracy on a southeast Brazilian sample. J Forensic Leg Med [Internet] 2018;58:164–168. doi: 10.1016/j.jflm.2018.06.006.
    1. Gulsahi A, Tirali RE, Cehreli SB, De Luca S, Ferrante L, Cameriere R. The reliability of Cameriere’s method in Turkish children: a preliminary report. Forensic Sci Int [Internet] 2015;249:319–319.
    1. Galić I, Vodanović M, Cameriere R, Nakaš E, Galić E, Selimović E, et al. Accuracy of Cameriere, Haavikko, and Willems radiographic methods on age estimation on Bosnian-Herzegovian children age groups 6–13. Int J Legal Med. 2011;125(2):315–321. doi: 10.1007/s00414-010-0515-8.
    1. Alghali R, Kamaruddin AF, Mokhtar N. Dental age estimation: comparison of reliability between Malay formula of Demirjian method and Malay formula of Cameriere method. In: AIP conference proceedings. 2016.
    1. Wolf TG, Briseño-Marroquín B, Callaway A, Patyna M, Müller VT, Willershausen I, et al. Dental age assessment in 6- to 14-year old German children: comparison of Cameriere and Demirjian methods. BMC Oral Health [Internet] 2016;16(1):1–8. doi: 10.1186/s12903-015-0139-y.
    1. Rai B, Kaur J, Cingolani M, Ferrante L, Cameriere R. Age estimation in children by measurement of open apices in teeth: an Indian formula. Int J Leg Med [Internet] 2010;124(3):237–41. doi: 10.1007/s00414-010-0427-7.
    1. De Luca S, De Giorgio S, Butti AC, Biagi R, Cingolani M, Cameriere R. Age estimation in children by measurement of open apices in tooth roots: study of a Mexican sample. Forensic Sci Int [Internet] 2012;221(1–3):155.e1–155.e7.
    1. Guo YC, Yan CX, Lin XW, Zhou H, Li JP, Pan F, et al. Age estimation in northern Chinese children by measurement of open apices in tooth roots. Int J Leg Med [Internet] 2015;129(1):179–86. doi: 10.1007/s00414-014-1035-8.
    1. Halabi SS, Prevedello LM, Kalpathy-cramer J, Mamonov AB. The RSNA pediatric bone age machine learning challenge. Radiology. 2018;290:498–503. doi: 10.1148/radiol.2018180736.
    1. Dallora AL, Anderberg P, Kvist O, Mendes E, Ruiz SD, Berglund JS. Bone age assessment with various machine learning techniques: a systematic literature review and meta-analysis. PLoS ONE. 2019;14(7):1–22. doi: 10.1371/journal.pone.0220242.
    1. Galibourg A, Cussat-Blanc S, Dumoncel J, Telmon N, Monsarrat P, Maret D. Comparison of different machine learning approaches to predict dental age using Demirjian’s staging approach. Int J Legal Med. 2021;135(2):665–675. doi: 10.1007/s00414-020-02489-5.
    1. Tao J, Wang J, Wang A, Xie Z, Wang Z, Wu S, et al. Dental age estimation: a machine learning perspective. In: Hassanien AE, Azar AT, Gaber T, Bhatnagar R, F. Tolba M, editors. The international conference on advanced machine learning technologies and applications (AMLTA2019). Cham: Springer; 2020. p. 722–33.
    1. Vila-Blanco N, Carreira MJ, Varas-Quintana P, Balsa-Castro C, Tomás I. Deep neural networks for chronological age estimation from OPG images. IEEE Trans Med Imaging. 2020;39(7):2374–2384. doi: 10.1109/TMI.2020.2968765.
    1. Schmeling A, Geserick G, Reisinger W, Olze A. Age estimation. Forensic Sci Int. 2007;165(2–3):178–181. doi: 10.1016/j.forsciint.2006.05.016.
    1. Mosteller F, Tukey JW. Data analysis, including statistics. Handb Soc Psychol. 1968;2:80–203.
    1. Mileman PA. A study of cross-validation and bootstrap for accuracy estimation and model selection. Int Jt Conf Artif Intell. 2001;30(2):133–133.
    1. Maslove DM, Podchiyska T, Lowe HJ. Discretization of continuous features in clinical datasets. J Am Med Inform Assoc. 2013;20(3):544–553. doi: 10.1136/amiajnl-2012-000929.
    1. Sturges HA. The choice of a class interval. J Am Stat Assoc. 1926;21(153):65–66. doi: 10.1080/01621459.1926.10502161.
    1. Yucheng G, Lai W, Teng C, Chunxia Y, Xi F, Ministry H, et al. Recent progresses on dental age. Chin J Forensic Med. 2013;28:478–480.
    1. Lehmann EL, Casella G. Theory of point estimation. Berlin: Springer; 2006.
    1. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2012;12:2825–2830.
    1. Zingg MA, Knechtle B, Rust CA, Rosemann T, Lepers R. Analysis of participation and performance in athletes by age group in ultramarathons of more than 200 km in length. Int J Gen Med [Internet] 2013;6:209–220.
    1. Fahradyan A, Tsuha M, Wolfswinkel EM, Mitchell KAS, Hammoudeh JA, Magee W. Optimal timing of secondary alveolar bone grafting: a literature review. J Oral Maxillofac Surg. 2019;77:843–849. doi: 10.1016/j.joms.2018.11.019.
    1. Burges CJC. A tutorial on support vector machine for pattern recognition. Data Min Knowl Discov. 1998;2(2):955–974. doi: 10.1023/A:1009715923555.
    1. Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20(3):273–297.
    1. Štepanovský M, Ibrová A, Buk Z, Velemínská J. Novel age estimation model based on development of permanent teeth compared with classical approach and other modern data mining methods. Forensic Sci Int [Internet] 2017;279:72–82. doi: 10.1016/j.forsciint.2017.08.005.

Source: PubMed

Sponsorit ja yhteistyökumppanit

Sairaudet

Huumeiden interventiot

3
Tilaa