Age-group determination of living individuals using first molar images based on artificial intelligence

Abstract

Dental age estimation of living individuals is difficult and challenging, and there is no consensus method in adults with permanent dentition. Thus, we aimed to provide an accurate and robust artificial intelligence (AI)-based diagnostic system for age-group estimation by incorporating a convolutional neural network (CNN) using dental X-ray image patches of the first molars extracted via panoramic radiography. The data set consisted of four first molar images from the right and left sides of the maxilla and mandible of each of 1586 individuals across all age groups, which were extracted from their panoramic radiographs. The accuracy of the tooth-wise estimation was 89.05 to 90.27%. Performance accuracy was evaluated mainly using a majority voting system and area under curve (AUC) scores. The AUC scores ranged from 0.94 to 0.98 for all age groups, which indicates outstanding capacity. The learned features of CNNs were visualized as a heatmap, and revealed that CNNs focus on differentiated anatomical parameters, including tooth pulp, alveolar bone level, or interdental space, depending on the age and location of the tooth. With this, we provided a deeper understanding of the most informative regions distinguished by age groups. The prediction accuracy and heat map analyses support that this AI-based age-group determination model is plausible and useful.

Figure 1

Overall workflow.

Figure 2

Classification of a panoramic dental X-ray using learned networks to predict age-group of the patient.

Figure 3

Conversion of the age-group prediction result of the five age-groups to the three age-groups.

Figure 4

Example of correctly classified teeth patches and their Grad-CAM results. The figures show the original molar image (left), Grad-CAM for three age-group prediction (middle) and Grad-CAM for five age-group prediction (right). Note that the softmax score for every first molar image in the figure is above 0.99.

Figure 5

Confusion matrix of the age-group estimation results of the predictions for the three age-groups and five age-groups. In (a), the network trained for predicting three age-groups. In (b), the network trained for predicting five age-groups is used for three age-group prediction. Each element of the confusion matrix represents the average number of patients over five-fold cross validation.

Figure 6

A comparison of average ROC curves over five-fold cross validation between the networks to obtain predictions for three age-groups and five age-groups. Each curve is obtained by binary classification to discriminate one age-group from others. The network that learned to predict five age-groups is used to predict the three age-groups. The AUC of each age-group shows (a) ages 0–19: Three-age group = 0.98 ± 0.01 and five-age group = 0.98 ± 0.01 (p value = 0.97), (b) ages 20–49: three-age group = 0.95 ± 0.01 and five-age group = 0.94 ± 0.01 (p value = 0.12), (c) ages over 50: three-age group = 0.97 ± 0.01 and five-age group = 0.97 ± 0.01 (p value = 0.98).