Adolescents and Children Age Estimation Using Machine Learning Based on Pulp and Tooth Volumes on CBCT Images.

OBJECTIVES: To estimate adolescents and children age using stepwise regression and machine learning methods based on the pulp and tooth volumes of the left maxillary central incisor and cuspid on cone beam computed tomography (CBCT) images, and to compare and analyze the estimation results. METHODS: A total of 498 Shanghai Han adolescents and children CBCT images of the oral and maxillofacial regions were collected. The pulp and tooth volumes of the left maxillary central incisor and cuspid were measured and calculated. Three machine learning algorithms (K-nearest neighbor, ridge regression, and decision tree) and stepwise regression were used to establish four age estimation models. The coefficient of determination, mean error, root mean square error, mean square error and mean absolute error were computed and compared. A correlation heatmap was drawn to visualize and the monotonic relationship between parameters was visually analyzed. RESULTS: The K-nearest neighbor model (R2=0.779) and the ridge regression model (R2=0.729) outperformed stepwise regression (R2=0.617), while the decision tree model (R2=0.494) showed poor fitting. The correlation heatmap demonstrated a monotonically negative correlation between age and the parameters including pulp volume, the ratio of pulp volume to hard tissue volume, and the ratio of pulp volume to tooth volume. CONCLUSIONS: Pulp volume and pulp volume proportion are closely related to age. The application of CBCT-based machine learning methods can provide more accurate age estimation results, which lays a foundation for further CBCT-based deep learning dental age estimation research.

[Comparison of the accuracy for evaluating cervical vertebral bone age and dental age of children in Shanghai].

PURPOSE: To compare the applicability and validity of dental age (DA) estimated by Willems method and cervical vertebral bone age (CVBA) evaluated by regression formula in estimating the chronological age of children in Shanghai. METHODS: Panoramic radiographs and lateral cephalograms were retrospectively collected from 320 subjects (160 males, 160 females), totaling 640 images. Discrepancies between chronological and estimated ages were statistically calculated by paired samples t test or Wilcoxon signed rank test using SPSS 25.0 software package. The accuracy of the two methods was comprehensively evaluated by comparing their standard deviation, mean absolute error (MAE) and the correct rate of acceptable range of estimated age error. RESULTS: The mean DA underestimated CA by 0.75±1.03 years for males and by 1.05±1.18 years for females; whereas the mean CVBA underestimated CA by 0.78±1.40 years for males and 0.53±1.31 years for females. MAE of Willems method was 1.15 years and the MAE of regression formula of CVBA was 1.20 years. The correct rate of clinically acceptable error of 0.5 years was 26.25% for Willems method and 27.19% for regression formula of CVBA. CONCLUSIONS: Willems method is more accurate than regression formula in indicating cervical vertebral skeletal age of adolescents in Shanghai children. Because of significant differences between CA and estimated ages, further modifications are urged to improve the accuracy of these two methods.