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

Seunghyeon Kim,Yung-Kyun Noh,Frank C Park,Q.-Schick Auh,Yeon-Hee Lee

doi:10.1038/s41598-020-80182-8

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.

Highlights

Dental age estimation of living individuals is difficult and challenging, and there is no consensus method in adults with permanent dentition
As human-engineered procedures are not required with convolutional neural network (CNN), an artificial intelligence (AI) system significantly reduces the workload of human interpreters or observers in dental age p rediction[21]
For networks trained to predict five groups, #16 and #26 were determined to be more useful for our CNNs with accuracies of 87.76 ± 0.67% and 88.16 ± 0.71%, respectively, compared with accuracies of 87.04 ± 0.81% and 87.04 ± 0.71% for teeth #36 and #46, respectively

Summary

Introduction

Dental age estimation of living individuals is difficult and challenging, and there is no consensus method in adults with permanent dentition. 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. Other methods using the tooth-coronal index[9], the level of the alveolar bone[10,11,12], and the pulp/tooth area ratio[13,14] have been reported; the accuracy is lower than that for children and adolescents. Previous methods had a major drawback of focusing only on partial features of teeth with large error ranges in age estimation. The main difference between CNNs and conventional individual feature-based methods is that CNNs perform end-to-end learning and extract a set of relevant features directly from raw data, without human intervention. In addition because CNNs autonomously learn a holistic feature set from data, they exhibit robust performance with a large amount of data

Objectives

Methods

Results

Discussion

Conclusion