Accelerating computer vision-based human identification through the integration of deep learning-based age estimation from 2 to 89 years

Introduction: Forensic dentistry is essential for human identification, but traditional manual techniques are often time-intensive and prone to subjectivity. The integration of artificial intelligence (AI) presents a transformative opportunity to enhance accuracy and efficiency across various forensic odontology applications. This systematic review consolidates and analyzes the existing literature on AI applications in forensic dentistry. Materials and Methods: A comprehensive literature search was conducted in the PubMed and Scopus databases following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies published up to August 2025 were considered for inclusion. Results: A total of 116 studies were analyzed. The primary applications included age estimation (54 studies), gender estimation (33 studies), and human/dental identification (26 studies). Bite mark analysis (1 study) and facial reconstruction (2 studies) were identified as underexplored areas. Convolutional neural networks (CNNs) were the most frequently employed AI algorithm, utilized in 64% (74/116) of studies, while orthopantomograms (OPGs) were the predominant imaging modality in 72% (84/116) of investigations. Quantitative results demonstrated significant promise: age estimation models achieved a mean absolute error (MAE) as low as 0.0079 years and a peak classification accuracy of 99.98%; gender estimation models attained accuracies between 68% and 98%; and human identification models reached up to 100% accuracy in optimal conditions, though sensitivity dropped to 69% in complex postmortem cases. Emerging techniques, such as microbiome analysis and generative adversarial networks (GANs), were noted as innovative future directions. Conclusion: AI demonstrates significant potential to improve accuracy and reduce processing time in core forensic dentistry tasks, particularly age and gender estimation. However, challenges related to data privacy, algorithmic bias, and legal admissibility persist. Future research should prioritize the development of explainable AI models, standardized and diverse datasets, and robust regulatory frameworks to ensure ethical and trustworthy integration into forensic practice.

ObjectivesForensic age estimation from orthopantomograms (OPGs) can be performed more quickly and accurately using convolutional neural networks (CNNs), making them an ideal extension to standard forensic age estimation methods. This study evaluates improvements in forensic age prediction for children, adolescents, and young adults by training a custom CNN from a previous study, using a larger, diverse dataset with a focus on dental growth features.Methods21,814 OPGs from 13,766 individuals aged 1 to under 25 years were utilized. The custom CNN underwent 1000 epochs of training and validation using 16,000 and 4000 OPGs, respectively. The best model was chosen by the least mean absolute error (MAE) and evaluated with an additional test dataset of 1814 independent OPGs. Furthermore, the CNN was applied to OPGs from 15 available forensic age estimations conducted by experts certified by the Study Group on Forensic Age Diagnostics (AGFAD), and the results were compared.ResultsA MAE of 0.93 ± 0.81 years and a mean-signed error (MSE) of −0.06 ± 1.23 years were achieved in the test dataset. 63% of predictions were accurate within 1 year, and 95% within 2.5 years. Results of the CNN were comparable to those obtained by experts, effectively highlighting discrepancies in the reported ages of individuals.ConclusionUsing a large and diverse dataset along with custom deep learning techniques, forensic age estimation can be significantly improved, often providing predictions accurate to within 1 year. This approach offers a reliable, robust, and objective complement to standard forensic age estimation methods.Key PointsQuestionThe potential of custom convolutional neural networks for forensic age estimation, along with a large, diverse dataset, warrants further investigation, offering valuable support to experts.FindingsFor 1814 test-orthopantomograms, 63% of predictions were accurate within 1 year and 95% within 2.5 years, similar to expert estimates in 15 forensic cases.Clinical relevanceMany individuals’ fates depend on accurate age estimation. Forensic age estimation can benefit from applying CNN-based methods to further enhance reliability and accuracy.

We applied deep convolutional neural networks (CNNs) to detect periodontal bone loss (PBL) on panoramic dental radiographs. We synthesized a set of 2001 image segments from panoramic radiographs. Our reference test was the measured % of PBL. A deep feed-forward CNN was trained and validated via 10-times repeated group shuffling. Model architectures and hyperparameters were tuned using grid search. The final model was a seven-layer deep neural network, parameterized by a total number of 4,299,651 weights. For comparison, six dentists assessed the image segments for PBL. Averaged over 10 validation folds the mean (SD) classification accuracy of the CNN was 0.81 (0.02). Mean (SD) sensitivity and specificity were 0.81 (0.04), 0.81 (0.05), respectively. The mean (SD) accuracy of the dentists was 0.76 (0.06), but the CNN was not statistically significant superior compared to the examiners (p = 0.067/t-test). Mean sensitivity and specificity of the dentists was 0.92 (0.02) and 0.63 (0.14), respectively. A CNN trained on a limited amount of radiographic image segments showed at least similar discrimination ability as dentists for assessing PBL on panoramic radiographs. Dentists’ diagnostic efforts when using radiographs may be reduced by applying machine-learning based technologies.

Background/Objectives: Dental age estimation is a vital component of forensic science, helping to determine the identity and actual age of an individual. However, its effectiveness is challenged by methodological variability and biological differences between individuals. Therefore, to overcome the drawbacks such as the dependence on manual measurements, requiring a lot of time and effort, and the difficulty of routine clinical application due to large sample sizes, we aimed to automatically estimate tooth age from panoramic radiographs (OPGs) using artificial intelligence (AI) algorithms. Methods: Two-Dimensional Deep Convolutional Neural Network (2D-DCNN) and One-Dimensional Deep Convolutional Neural Network (1D-DCNN) techniques were used to extract features from panoramic radiographs and patient records. To perform age estimation using feature information, Genetic algorithm (GA) and Random Forest algorithm (RF) were modified, combined, and defined as Modified Genetic-Random Forest Algorithm (MG-RF). The performance of the system used in our study was analyzed based on the MSE, MAE, RMSE, and R2 values calculated during the implementation of the code. Results: As a result of the applied algorithms, the MSE value was 0.00027, MAE value was 0.0079, RMSE was 0.0888, and R2 score was 0.999. Conclusions: The findings of our study indicate that the AI-based system employed herein is an effective tool for age detection. Consequently, we propose that this technology could be utilized in forensic sciences in the future.

Objective To evaluate the accuracy of different convolutional neural networks (CNN),representative deep learning models,in the differential diagnosis of ameloblastoma and odontogenic keratocyst,and subsequently compare the diagnosis results between models and oral radiologists. Methods A total of 1000 digital panoramic radiographs were retrospectively collected from the patients with ameloblastoma (500 radiographs) or odontogenic keratocyst (500 radiographs) in the Department of Oral and Maxillofacial Radiology,Peking University School of Stomatology.Eight CNN including ResNet (18,50,101),VGG (16,19),and EfficientNet (b1,b3,b5) were selected to distinguish ameloblastoma from odontogenic keratocyst.Transfer learning was employed to train 800 panoramic radiographs in the training set through 5-fold cross validation,and 200 panoramic radiographs in the test set were used for differential diagnosis.Chi square test was performed for comparing the performance among different CNN.Furthermore,7 oral radiologists (including 2 seniors and 5 juniors) made a diagnosis on the 200 panoramic radiographs in the test set,and the diagnosis results were compared between CNN and oral radiologists. Results The eight neural network models showed the diagnostic accuracy ranging from 82.50% to 87.50%,of which EfficientNet b1 had the highest accuracy of 87.50%.There was no significant difference in the diagnostic accuracy among the CNN models (P=0.998,P=0.905).The average diagnostic accuracy of oral radiologists was (70.30±5.48)%,and there was no statistical difference in the accuracy between senior and junior oral radiologists (P=0.883).The diagnostic accuracy of CNN models was higher than that of oral radiologists (P<0.001). Conclusion Deep learning CNN can realize accurate differential diagnosis between ameloblastoma and odontogenic keratocyst with panoramic radiographs,with higher diagnostic accuracy than oral radiologists.

Although many studies in various fields employ deep learning models, only few such studies exist in dental imaging. This paper aims to evaluate the effectiveness of Convolutional Neural Network (CNN) algorithms for the detection and diagnosis of the quantitative level of dental restorations using panoramic radiographs by preparing a novel dataset. 20,973 panoramic X-ray radiographs, all labeled into five distinct categories by three dental experts, were used. AlexNet, VGG-16 and variants of ResNet models were trained with the dataset and evaluated for the classification task. Additionally, 10-fold cross-validation (i.e. nine-folds were separated for training and one-fold for validation) and data augmentation were carried out for all experiments. The most successful result came from ResNet-101 with 92.7% accuracy. Its macro-average AUC was also the highest with 0.989. Other accuracy results obtained for the dataset were 75.5% for AlexNet, 85.0% for VGG-16, 92.1% for ResNet-18, 91.7% for ResNet-50 and 92.1% for Inception ResNet V2. Accuracy of 92.7% is a very promising result for a computer-aided diagnosis system. This result proved that the system could assist dentists in providing supportive preliminary information the moment they first take a panoramic X-ray radiograph of a patient. Furthermore, as the introduced dataset is powerful enough, it can be re-labeled for different problems and used in different studies.

DNA methylation markers in combination with skeletal and dental ages to improve age estimation in children

To develop and evaluate a deep learning (DL)-based artificial intelligence (AI) framework for the comprehensive assessment of impacted maxillary canines, including positional classification, buccal-palatal localization, and detection of adjacent tooth root resorption, using panoramic radiographs (PRs) validated against cone beam computed tomography (CBCT) reference standards. This retrospective study included PRs and CBCT scans of 458 patients (581 impacted maxillary canines) acquired between 2020 and 2024. CBCT images served as the reference standard for buccal-palatal localization and root resorption, while canine position was determined based on beta angle measurements on PRs. Regions of interest (ROIs) were manually annotated on PRs, and cropped PR images were used as model inputs. CBCT images were used exclusively as the reference standard for labeling. A total of twelve pretrained convolutional neural network (CNN) architectures were evaluated across three diagnostic tasks. For each specific task, the top six performing architectures were selected to form a majority voting-based fusion model to enhance diagnostic accuracy. Model performance was assessed using accuracy, precision, recall, and F1-score derived from confusion matrix analyses. For three-class positional classification (horizontal, mesioangular, vertical), the best individual CNN achieved an accuracy of 88.61%, while the fusion model improved accuracy to 90.90%. In buccal-palatal localization, individual model accuracy reached 74.85%, increasing to 80.40% with fusion. For detection of adjacent tooth root resorption, the highest individual accuracy was 83.02%, and the fusion model achieved an accuracy of 88.59%. DL models can accurately evaluate the position, buccal-palatal localization, and root resorption associated with impacted maxillary canines when trained on ROIs extracted from PRs using CBCT-based annotations. The use of multiple CNN architectures combined with a fusion strategy significantly enhances diagnostic performance. These findings suggest that AI-based automated analysis may serve as a reliable complementary tool for improving diagnostic consistency and treatment planning in patients with impacted maxillary canines.

Staging third molar development is commonly used for age assessment in sub-adults. Current staging techniques are, at most, semi-automated and rely on manual interactions prone to operator variability. The aim of this study was to fully automate the staging process by employing the full potential of deep learning, using convolutional neural networks (CNNs) in every step of the procedure. The dataset used to train the CNNs consisted of 400 panoramic radiographs (OPGs), with 20 OPGs per developmental stage per sex, staged in consensus between three observers. The concepts of transfer learning, using pre-trained CNNs, and data augmentation were used to mitigate the issues when dealing with a limited dataset. In this work, a three-step procedure was proposed and the results were validated using fivefold cross-validation. First, a CNN localized the geometrical center of the lower left third molar, around which a square region of interest (ROI) was extracted. Second, another CNN segmented the third molar within the ROI. Third, a final CNN used both the ROI and the segmentation to classify the third molar into its developmental stage. The geometrical center of the third molar was found with an average Euclidean distance of 63 pixels. Third molars were segmented with an average Dice score of 93%. Finally, the developmental stages were classified with an accuracy of 54%, a mean absolute error of 0.69 stages, and a linear weighted Cohen's kappa coefficient of 0.79. The entire automated workflow on average took 2.72 s to compute, which is substantially faster than manual staging starting from the OPG. Taking into account the limited dataset size, this pilot study shows that the proposed fully automated approach shows promising results compared with manual staging.

There are plenty of difficulties surrounding the radiographs for the comparative techniques on human identification. The lack of soft tissue, the skull's and films positioning are a few of the obstacles faced in anthropological studies. With the objectives to standardize, producing high quality images and reducing adaptations, different exposure times, barriers and other aspects involving radiographs were tested in order to establish a protocol involving periapical and panoramic radiographs of dry skulls. With the help of an acrylic stand, specially designed to position the cranium, panoramic radiographs were primarily taken using different preset configurations, then four materials were tested to compensate for lack of soft tissue: a ice pack, a block of dental wax, a metal plate and finally a film exposed to light and processed that was left between the blank film and the intensifying screen. For the periapical radiographs, "Kodak E-speed films" were exposed to times from 0.06 to 0.8 second at the upper and lower molars and anterior regions. Clinical film holders were used and kept in position by a metal wire device. The processing times were 45 seconds of development and 10 minutes of fixation. The radiographs were presented to a group of fifteen dentists, of several specialties, who selected the best results and concluding that the panoramic radiographs were best taken with the 63 Kv and 06 mA configurations and two films inside the cassette. For the periapical the exposure times of 0.64 sec for the upper arch and 0.8 sec for the lower achieved the best acceptance. The presented results, allied with the data found in the literature a protocol was also prepared and attached to this research.

Age estimation based on the change in the size of the pulp due to secondary dentin deposition can be conducted non-invasively using radiographic photographs. Among these methods, age estimation using the pulp/tooth area ratio is highly accurate. The present study was conducted to apply this method using the panoramic radiographs of a Korean sample population and to evaluate its applicability in the Korean population. The study was conducted using panoramic radiographic images of 349 Koreans aged 20-79 years. The pulp/ tooth area ratio was calculated by measuring the area of the pulp and tooth. Teeth with a single canal, such as maxillary central incisor, lateral incisor, canine, and mandibular canine, were selected. Correlations between this ratio and age were calculated and regression formulas were derived. Age and pulp/tooth area ratio showed relatively low correlations compared with other studies. In particular, men showed lower correlations than women, and upper teeth showed a higher correlation than lower teeth. The regression formulas derived in this study also showed higher errors than those reported in other studies. Age estimation using pulp/tooth area ratio in a Korean using digital panoramic radiographs showed larger errors when compared with previous studies. Morphological diversity of tooth and pulp, indistinct anatomical details in panoramic radiograph, reduction in crown size due to attrition, and ethnic differences are believed to have affected the results.

Age estimation from facial images is one of the most popular fields of research concerning deep learning and convolutional neural networks. However, there are several factors influencing the final accuracy that require special consideration, and in this research, we examine how gender classification affects age estimation. We use a predefined version of the MobileNetV2 convolutional neural network and train it on the CASIAWebFace dataset which we augmented with our private dataset called AgeCFBP. For the purpose of testing the network performance, we used the FG-NET dataset. The results of our experiments showed that gender pre-classification has a measurable impact on age estimation in both male and female population by decreasing Mean Absolute Error (MAE) metric, which might lead to enhanced applications in real-world scenarios, such as biometric authentication, security systems, human-computer interaction, and age-restricted content access control.

BackgroundAge estimation from panoramic radiographs is a fundamental task in forensic sciences. Previous age assessment studies mainly focused on juvenile rather than elderly populations (> 25 years old). Most proposed studies were statistical or scoring-based, requiring wet-lab experiments and professional skills, and suffering from low reliability.ResultBased on Soft Stagewise Regression Network (SSR-Net), we developed DENSEN to estimate the chronological age for both juvenile and older adults, based on their orthopantomograms (OPTs, also known as orthopantomographs, pantomograms, or panoramic radiographs). We collected 1903 clinical panoramic radiographs of individuals between 3 and 85 years old to train and validate the model. We evaluated the model by the mean absolute error (MAE) between the estimated age and ground truth. For different age groups, 3–11 (children), 12–18 (teens), 19–25 (young adults), and 25+ (adults), DENSEN produced MAEs as 0.6885, 0.7615, 1.3502, and 2.8770, respectively. Our results imply that the model works in situations where genders are unknown. Moreover, DENSEN has lower errors for the adult group (> 25 years) than other methods. The proposed model is memory compact, consuming about 1.0 MB of memory overhead.ConclusionsWe introduced a novel deep learning approach DENSEN to estimate a subject’s age from a panoramic radiograph for the first time. Our approach required less laboratory work compared with existing methods. The package we developed is an open-source tool and applies to all different age groups.

Age estimation from facial images is a challenging computer vision task with diverse real-world applications. This paper proposes a novel hybrid architecture that integrates ConvNeXt, a state-of-the-art convolutional neural network (CNN), with a Vision Transformer (ViT) to leverage the complementary strengths of localized feature extraction and global attention. The proposed ConvNeXt-ViT hybrid is evaluated on benchmark age estimation datasets (MORPH II, CACD, AFAD, and IMDB-Clean) and achieves superior performance in terms of mean absolute error (MAE) compared to existing approaches. We explore various architectural configurations, use pre-trained models to address data limitations, and apply advanced training strategies and regularization techniques. Comprehensive ablation studies highlight the impact of each component and training strategy, particularly the importance of adapted attention mechanisms within the CNN backbone to focus on age-relevant facial features. The results demonstrate that the ConvNeXt-ViT hybrid not only outperforms traditional approaches but also provides a robust foundation for future research in age estimation and related visual tasks.

Automatic detection and classification of nasopalatine duct cyst and periapical cyst on panoramic radiographs using deep convolutional neural networks