Personal identification with orthopantomography using simple convolutional neural networks: a preliminary study

Abstract

Forensic dental examination has played an important role in personal identification (PI). However, PI has essentially been based on traditional visual comparisons of ante-and postmortem dental records and radiographs, and there is no globally accepted PI method based on digital technology. Although many effective image recognition models have been developed, they have been underutilized in forensic odontology. The aim of this study was to verify the usefulness of PI with paired orthopantomographs obtained in a relatively short period using convolutional neural network (CNN) technologies. Thirty pairs of orthopantomographs obtained on different days were analyzed in terms of the accuracy of dental PI based on six well-known CNN architectures: VGG16, ResNet50, Inception-v3, InceptionResNet-v2, Xception, and MobileNet-v2. Each model was trained and tested using paired orthopantomographs, and pretraining and fine-tuning transfer learning methods were validated. Higher validation accuracy was achieved with fine-tuning than with pretraining, and each architecture showed a detection accuracy of 80.0% or more. The VGG16 model achieved the highest accuracy (100.0%) with pretraining and with fine-tuning. This study demonstrated the usefulness of CNN for PI using small numbers of orthopantomographic images, and it also showed that VGG16 was the most useful of the six tested CNN architectures.

A pilot study of an automated personal identification process: Applying machine learning to panoramic radiographs

“…The findings of this study are consistent with the accuracy levels reported by those authors, which ranged from 80% to 100%. 25 Similarly, Heinrich et al (2018) observed a high rate of successful identification (85%) in an automated comparison of AM and PM-simulated panoramic radiographs from a large database. 10 …”

Lingual bone thickness in the apical region of the horizontal mandibular third molar: A cross-sectional study in young Japanese

“…Yoo et al reported on the application of artificial intelligence to predict the difficulty of surgery for third molar extraction [ 16 ]. The authors reported on an artificial intelligence-based analysis method for orthopantomography [ 17 ]. Artificial intelligence is increasingly being applied to the dental field [ 18 ].…”

Current applications and development of artificial intelligence for digital dental radiography

“…AI application in forensic odontology can also be used for automatic age estimation, sex determination, skeletal morphology identification and personal identification. [99][100][101][102][103][104][105] Deep CNN was used for age estimation through staging of third molar development corresponding to the Demirjian classification in panoramic radiographs. [100][101][102] The best stage allocation accuracy obtained was 61% in a fully manual segmentation process of the third molar.…”

“…103 Patil et al (2020) also demonstrated the potential use of ANN for gender determination using mandibular morphometric parameters in panoramic radiographs. 104 Matsuda et al (2020) conducted a preliminary study to investigate the potential use of simple CNN architectures for personal identification by comparing 30 pairs of panoramic radiographs. 105 Despite the various promising results in the field of forensic odontology, further improvement of AI models is still needed.…”