Dental Age Estimation: A Machine Learning Perspective

Dental age estimation is important for determining the actual age of an individual. In this paper, for the purpose of improving the accuracy of dental age estimation, we present several machine learning algorithms. We apply Demirjian’s method, Willem’s method, and our methods to a dataset with 1636 cases; 787 males and 849 females. The Multi-layer Perceptron algorithm is used to predict dental age in our experiments. In order to avoid overfitting, we use Leave-one-out cross-validation when training the model. Meanwhile, we employ root-mean-square error, mean-square-error and mean-absolute-error to measure the error of the results. Through experiments, we verify that this algorithm is more accurate than traditional dental methods. In addition, we try to use a new set of features that are converted by traditional dental methods. Specifically, we find that using Demirjian’s method converted data for males and using Willem’s method converted data for females can improve the accuracy of the dental age predictions.

[1]  Maria Gabriela Haye Biazevic,et al.  Estimating ages by third molars: stages of development in Brazilian young adults. , 2013, Journal of forensic and legal medicine.

[2]  S. Kvaal,et al.  Collection of post mortem data: DVI protocols and quality assurance. , 2006, Forensic science international.

[3]  James M. Tanner,et al.  Growth at Adolescence , 1956 .

[4]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[5]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[6]  Ramesh Kumaresan,et al.  Reliability and validity of five radiographic dental-age estimation methods in a population of Malaysian children. , 2016, Journal of investigative and clinical dentistry.

[7]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[8]  Jaroslav Bruzek,et al.  Dental Age Assessment in Children: A Comparison of Four Methods in a Recent French Population , 2013, Journal of forensic sciences.

[9]  Arthur L. Samuel,et al.  Some studies in machine learning using the game of checkers , 2000, IBM J. Res. Dev..

[10]  J. Ata-Ali,et al.  Accuracy of the estimation of dental age in comparison with chronological age in a Spanish sample of 2641 living subjects using the Demirjian and Nolla methods. , 2017, Forensic science international.

[11]  Michael J. Panik.  Advanced Statistics from an Elementary Point of View , 2005 .

[12]  Nenad Nedeljkovic,et al.  Dental age assessment validity of radiographic methods on Serbian children population. , 2013, Forensic science international.

[13]  S. Garn,et al.  Genetic, Nutritional, and Maturational Correlates of Dental Development , 1965, Journal of dental research.

[14]  O. Nelles,et al.  An Introduction to Optimization , 1996, IEEE Antennas and Propagation Magazine.

[15]  J M Tanner,et al.  A new system of dental age assessment. , 1973, Human biology.

[16]  G Willems,et al.  Dental age estimation in Belgian children: Demirjian's technique revisited. , 2001, Journal of forensic sciences.

[17]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[18]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[19]  C. M. Nolla.  The development of the permanent teeth , 1960 .

[20]  Jian Wang,et al.  Dental Age Estimation in East Asian Population with Least Squares Regression , 2018, AMLTA.

[21]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[22]  E. L. Lehmann,et al.  Theory of point estimation , 1950 .

[23]  Frank Rosenblatt,et al.  PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS , 1963 .

[24]  G Geserick,et al.  Age estimation of unidentified corpses by measurement of root translucency. , 2004, The Journal of forensic odonto-stomatology.

[25]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[26]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[27]  G Willems,et al.  A review of the most commonly used dental age estimation techniques. , 2001, The Journal of forensic odonto-stomatology.

[28]  Peter Mack,et al.  Dental age estimation standards for a Western Australian population. , 2015, Forensic science international.

[29]  Fan Jiang,et al.  Dental age assessment in 7-14-year-old Chinese children: comparison of Demirjian and Willems methods. , 2014, Forensic science international.

[30]  M. J. Collins,et al.  Age estimation: The state of the art in relation to the specific demands of forensic practise , 2000, International Journal of Legal Medicine.