ABSTRACT
Adult age estimation is one of the most challenging problems in forensic science and physical anthropology. In this study, we aimed to develop and evaluate machine learning (ML) methods based on the modified Gustafson's criteria for dental age estimation. In this retrospective study, a total of 851 orthopantomograms were collected from patients aged 15 to 40 years old. The secondary dentin formation (SE), periodontal recession (PE), and attrition (AT) of four mandibular premolars were analyzed according to the modified Gustafson's criteria. Ten ML models were generated and compared for age estimation. The partial least squares regressor outperformed other models in males with a mean absolute error (MAE) of 4.151 years. The support vector regressor (MAE = 3.806 years) showed good performance in females. The accuracy of ML models is better than the single-tooth model provided in the previous studies (MAE = 4.747 years in males and MAE = 4.957 years in females). The Shapley additive explanations method was used to reveal the importance of the 12 features in ML models and found that AT and PE are the most influential in age estimation. The findings suggest that the modified Gustafson method can be effectively employed for adult age estimation in the southwest Chinese population. Furthermore, this study highlights the potential of machine learning models to assist experts in achieving accurate and interpretable age estimation.
ABSTRACT
Teeth-based age and sex estimation is an important task in mass disasters, criminal scenes, and archeology. Although various methods have been proposed, most of them are subjective and influenced by observers' experiences. In this study, we aimed to develop a deep learning model for automatic dental age and sex estimation from orthopantomograms (OPGs) and compare to manual methods. A large dataset of 15,195 OPGs (age range, 16 ~ 50 years; mean age, 29.65 years ± 9.36 [SD]; 10,218 females) was used to train and test a hybrid deep learning model which is a combination of convolutional neural network and transformer model. The final performance of this model was evaluated on additional independent 100 OPGs and compared to the manual method for external validation. In the test of 1413 OPGs, the mean absolute error (MAE) of age estimation was 2.61 years by this model. The accuracy and the area under the receiver operating characteristic curve (AUC) of sex estimation were 95.54% and 0.984. The heatmap indicated that the crown and pulp chamber of premolars and molars contain the most age-related information. In the additional independent 100 OPGs, this model achieved an MAE of 3.28 years for males and 3.79 years for females. The accuracy of this model was much higher than that of the manual models. Therefore, this model has the potential to assist radiologists in automated age and sex estimation.
Subject(s)
Molar , Neural Networks, Computer , Male , Female , Humans , Adolescent , Adult , Child, Preschool , Bicuspid , Tooth Crown , Dental Pulp CavityABSTRACT
Forensic odontology is regarded as an important branch of forensics dealing with human identification based on dental identification. This paper proposes a novel method that uses deep convolution neural networks to assist in human identification by automatically and accurately matching 2-D panoramic dental X-ray images. Designed as a top-down architecture, the network incorporates an improved channel attention module and a learnable connected module to better extract features for matching. By integrating associated features among all channel maps, the channel attention module can selectively emphasize interdependent channel information, which contributes to more precise recognition results. The learnable connected module not only connects different layers in a feed-forward fashion but also searches the optimal connections for each connected layer, resulting in automatically and adaptively learning the connections among layers. Extensive experiments demonstrate that our method can achieve new state-of-the-art performance in human identification using dental images. Specifically, the method is tested on a dataset including 1,168 dental panoramic images of 503 different subjects, and its dental image recognition accuracy for human identification reaches 87.21% rank-1 accuracy and 95.34% rank-5 accuracy. Code has been released on Github. (https://github.com/cclaiyc/TIdentify).
Subject(s)
Forensic Anthropology , Neural Networks, Computer , HumansABSTRACT
Human identification is an important task in mass disaster and criminal investigations. Although several automatic dental identification systems have been proposed, accurate and fast identification from panoramic dental radiographs (PDRs) remains a challenging issue. In this study, an automatic human identification system (DENT-net) was developed using the customized convolutional neural network (CNN). The DENT-net was trained on 15,369 PDRs from 6300 individuals. The PDRs were preprocessed by affine transformation and histogram equalization. The DENT-net took 128 × 128 × 7 square patches as input, including the whole PDR and six details extracted from the PDR. Using the DENT-net, the feature extraction took around 10 milliseconds per image and the running time for retrieval was 33.03 milliseconds in a 2000-individual database, promising an application on larger databases. The visualization of CNN showed that the teeth, maxilla, and mandible all contributed to human identification. The DENT-net achieved Rank-1 accuracy of 85.16% and Rank-5 accuracy of 97.74% for human identification. The present results demonstrated that human identification can be achieved from PDRs by CNN with high accuracy and speed. The present system can be used without any special equipment or knowledge to generate the candidate images. While the final decision should be made by human specialists in practice. It is expected to aid human identification in mass disaster and criminal investigation.
