Efficacy of the methods of age determination using artificial intelligence in panoramic radiographs - a systematic review.

The aim of this systematic review is to analyze the literature to determine whether the methods of artificial intelligence are effective in determining age in panoramic radiographs. Searches without language and year limits were conducted in PubMed/Medline, Embase, Web of Science, and Scopus databases. Hand searches were also performed, and unpublished manuscripts were searched in specialized journals. Thirty-six articles were included in the analysis. Significant differences in terms of root mean square error and mean absolute error were found between manual methods and artificial intelligence techniques, favoring the use of artificial intelligence (p < 0.00001). Few articles compared deep learning methods with machine learning models or manual models. Although there are advantages of machine learning in data processing and deep learning in data collection and analysis, non-comparable data was a limitation of this study. More information is needed on the comparison of these techniques, with particular emphasis on time as a variable.

Automatic and robust estimation of sex and chronological age from panoramic radiographs using a multi-task deep learning network: a study on a South Korean population.

Sex and chronological age estimation are crucial in forensic investigations and research on individual identification. Although manual methods for sex and age estimation have been proposed, these processes are labor-intensive, time-consuming, and error-prone. The purpose of this study was to estimate sex and chronological age from panoramic radiographs automatically and robustly using a multi-task deep learning network (ForensicNet). ForensicNet consists of a backbone and both sex and age attention branches to learn anatomical context features of sex and chronological age from panoramic radiographs and enables the multi-task estimation of sex and chronological age in an end-to-end manner. To mitigate bias in the data distribution, our dataset was built using 13,200 images with 100 images for each sex and age range of 15-80 years. The ForensicNet with EfficientNet-B3 exhibited superior estimation performance with mean absolute errors of 2.93 ± 2.61 years and a coefficient of determination of 0.957 for chronological age, and achieved accuracy, specificity, and sensitivity values of 0.992, 0.993, and 0.990, respectively, for sex prediction. The network demonstrated that the proposed sex and age attention branches with a convolutional block attention module significantly improved the estimation performance for both sex and chronological age from panoramic radiographs of elderly patients. Consequently, we expect that ForensicNet will contribute to the automatic and accurate estimation of both sex and chronological age from panoramic radiographs.

Dental age assessment and dental scoring systems: combined different statistical methods.

INTRODUCTION: Age Estimation has been considered as a human basic right, carried out through the use of tables for dental age assessment based on the chronology of tooth eruption. As such, the final aim of this investigation is to create tables with applicability to the Portuguese population, for the different scoring systems used and combined different statistical approaches. MATERIALS AND METHODS: For this purpose, dental age assessment was achieved in all four third molars, using different scoring systems, in a total sample of 626 orthopantomograms (324 females, 302 males), aged between 12 and 25 years old, from the database population of Lisbon North University Hospital Center, approved by the Ethic Committee. RESULTS: The values of validation showed excellent results both on precision and on reproducibility. Mostly all methods showed statistically significant differences between the estimated age and the chronological age and, therefore, the presence of estimation errors. Kullman's and Mincer's methods are the ones with best applicability in the Portuguese population, in the lower third molars. The reliability measures (sensitivity, specificity and accuracy) values decrease as age increases. CONCLUSION: A combination of the scoring systems as a protocol for dental age assessment in Portuguese nationality was established. Tables, for all the scoring systems used, were made with applicability in the Portuguese population.

Studying eruption patterns of mandibular third molars for forensic age assessment: Introducing current reference data from a population of black South Africans.

INTRODUCTION: Evaluation of the eruption of mandibular third molars in orthopantomograms (OPGs) is a method of forensic age assessment. The objective of our study was to provide valid reference data for this trait within a population of black South Africans. The study was guided by the criteria for reference studies in age assessment. MATERIALS AND METHODS: A study population from Pretoria, South Africa comprising 670 OPGs obtained from 338 black females and 332 black males aged between 15.00 and 25.97 years was analysed. All OPGs were performed for medical indication during the period from 2011 to 2022 and were retrospectively evaluated. From the 670 OPGs, a total of 1021 mandibular third molars were evaluated. The assessment of mandibular third molars was conducted using the staging scale presented by Olze et al. in 2012. Two experienced dentists evaluated the OPGs independently of each other. If the two examiners diverged in their assessments, a consensus stage was assigned. RESULTS: As expected, the mean, median and minimal age increased with higher stages for both teeth and both sexes. The minimum age recorded for stage D, indicating complete tooth eruption, was 15.79 years in females and 16.62 years in males. CONCLUSION: As it is the case for previous reference studies in other countries, placing exclusive reliance on the evaluation of mandibular third molar eruption is inadequate for ascertaining the age of majority among Black South Africans. Future studies need to examine if our results are transferable to other countries in Sub-Saharan Africa.

Forensic age estimation at the University Center of Legal Medicine Lausanne-Geneva: a retrospective study over 12 years.

With the undeniable increase in asylum requests from unaccompanied alleged minors, age estimation of living individuals has become an essential part of the routine work in European forensic centers. This study aims to review the forensic age estimations performed in our center since 2010, to evaluate the state-of-the-art of this practice in Switzerland with the evolution of the methodology according to upcoming recommendations. Our institute's expert reports performed between 2010 and 2022 were retrospectively analyzed. We gathered the following parameters: demographic data, morphological characteristics, alleged age compared with the assessed minimum age, sexual maturation, dental and bone age. When available, we collected personal and family history, medical history, records of torture-related/self-inflicted injuries, and information about eating habits that might affect skeletal development. Data collection amounted to 656 cases. Forensic age estimations ordered by the Swiss Secretariat for Migration (SEM) represented 76.4% of cases, with 23.6% of them ordered by the Court/Public Prosecutor. Most alleged minors were male (94.5%) and came from Afghanistan (53.4%). Adjunction of CT scans of the sternoclavicular joints was necessary in 86.4% of cases. Only 25.2% of our reports concluded on most probable minority, with 55.6% of definite majors; in 19.2% of our cases, minority could not be excluded. This study aspires to further broaden our expertise regarding forensic age estimations. Given the increasing migratory flows, we can expect a notable increase in the frequency of these requests. Consequently, this study aims to promote a multidisciplinary approach and the international standardization of the methodology of these estimations.

Decision tree analysis for age estimation in living individuals: integrating cervical and dental radiographic evaluations within a South African population.

Age estimation in living individuals around the age of 18 years is medico-legally important in undocumented migrant cases and in countries like South Africa where many individuals are devoid of identification documents. Establishing whether an individual is younger than 18 years largely influences the legal procedure that should be followed in dealing with an undocumented individual. The aim of this study was to combine dental third molar and anterior inferior apophysis ossification data for purposes of age estimation, by applying a decision tree analysis. A sample comprising of 871 black South African individuals (n = 446 males, 425 = females) with ages ranging between 15 and 24 years was analyzed using panoramic and cephalometric radiographs. Variables related to the left upper and lower third molars and cervical vertebral ring apophysis ossification of C2, C3, and C4 vertebrae analyzed in previous studies were combined in a multifactorial approach. The data were analyzed using a pruned decision tree function for classification. Male and female groups were handled separately as a statistically significant difference was found between the sexes in the original studies. A test sample of 30 individuals was used to determine if this approach could be used with confidence in estimating age of living individuals. The outcomes obtained from the test sample indicated a close correlation between the actual ages (in years and months) and the predicted ages (in years only), demonstrating an average age difference of 0.47 years between the corresponding values. This method showed that the application of decision tree analysis using the combination of third molar and cervical vertebral development is usable and potentially valuable in this application.

Radiological assessment of periodontal ligament space visibility on third molars for forensic age assessment - a comparison study of three different staging scales.

Various staging scales have been proposed for the assessment of the visibility of the periodontal ligament space of mandibular third molars on dental panoramic radiographs (PANs) for forensic age assessment in living individuals. However, up to now, there has been no systematic comparison between these staging scales available. We directly compared the 2010 staging scale proposed by Olze et al. with the 2017 staging by Lucas et al. and the 2020 staging by Guo et al. in a German study population. We evaluated 233 PANs from 115 females and 118 males aged 20.0 to 40.9 years using three independent examiners, with one examiner conducting two assessments. We examined the correlation between age and stage, as well as the inter- and intra-rater reliabilities. While the point estimates for the correlation coefficient and the reliability measures were lowest for the Guo scale and highest for the Olze scale, confidence intervals showed a large overlap, particularly for the scales of Olze et al. and Lucas et al. The correlation coefficients between stage and age were consistently lower in females than in males across all methods. In summary, we showed that the staging scales of Olze et al. and Lucas et al. were very similar. The Olze method showed higher point estimates across all analyses, and because there are more reference data available for this method, we argue that it should be preferred as the method of choice for further studies in the field. However, Guo method could be considered for instances, in which the inter-radicular periodontal ligament is not evaluable.

Predicting chronological age of 14 or 18 in adolescents: integrating dental assessments with machine learning.

AIM: Age estimation plays a critical role in personal identification, especially when determining compliance with the age of consent for adolescents. The age of consent refers to the minimum age at which an individual is legally considered capable of providing informed consent for sexual activities. The purpose of this study is to determine whether adolescents meet the age of 14 or 18 by using dental development combined with machine learning. METHODS: This study combines dental assessment and machine learning techniques to predict whether adolescents have reached the consent age of 14 or 18. Factors such as the staging of the third molar, the third molar index, and the visibility of the periodontal ligament of the second molar are evaluated. RESULTS: Differences in performance metrics indicate that the posterior probabilities achieved by machine learning exceed 93% for the age of 14 and slightly lower for the age of 18. CONCLUSION: This study provides valuable insights for forensic identification for adolescents in personal identification, emphasizing the potential to improve the accuracy of age determination within this population by combining traditional methods with machine learning. It underscores the importance of protecting and respecting the dignity of all individuals involved.

The effect of birth weight on tooth development by Demirjian's method.

OBJECTIVES: The aim of this study was to investigate the impact of birth weight on tooth development in children aged 7-8 years. MATERIALS AND METHODS: This retrospective cohort study comprised 75 children born at Bint Al-Huda Hospital, Bojnurd, in 2013-2014. The children were categorized into three groups based on their birth weight: Normal Birth Weight (NBW), Low Birth Weight (LBW), and Very Low Birth Weight (VLBW). Panoramic radiographs were taken for orthodontic examination, and Demirjian's 8-teeth method was employed to determine dental age. The study compared dental and chronological age within each group. Data analysis utilized SPSS software version 26, employing One-way ANOVA and chi-square tests. Statistical significance was set at P ≤ 0.05. RESULTS: The mean difference in dental and chronological age for Very Low Birth Weight (VLBW) children was 0.22 ± 0.44 years, for Low Birth Weight (LBW) children it was 0.19 ± 0.45 years, and for Normal Birth Weight (NBW) children, it was 0.08 ± 0.46 years. Although the mean difference decreased with increasing birth weight, this trend did not achieve statistical significance (P = 0.55). Furthermore, no significant differences were observed between the weight groups (P = 0.529) or genders (P = 0.191).

Skeletal maturation evaluation: which is the reliability of dental calcification Demirjian method versus hand-wrist X-ray in growing subjects? A systematic review.

OBJECTIVES: This systematic review aimed at evaluating the reliability of dental maturation (DM) according to Demirjian method compared to hand and wrist maturation (HWM) to assess skeletal maturity (SM) in growing subjects, to identify the teeth and the corresponding mineralisation stages related to the pubertal growth spurt (PGS). MATERIALS AND METHODS: PubMed, Scopus, and Web of Science were systematically searched until January 5th, 2024, to identify observational cross-sectional studies that assessed the reliability of Demirjian method compared to the HWM methods (i.e., Grave and Brown and Fishman) in growing subjects. The quality assessment was evaluated using the Joanna Briggs Institute (JBI) Critical Appraisal Checklist. RESULTS: Out of 136 papers suitable for title/abstract screening, 19 included studies. Of them, 17 papers showed the reliability of Demirjian DM method compared to HWM Fishman and Grave and Brown methods to assess SM in growing subjects. According to JBI Critical Appraisal Checklist, 12 papers were high-quality studies and 7 papers were medium-quality studies.  Conclusions: The mandibular second molar might be considered as the best indicator compared to other teeth and that the peak of growth occurs no earlier than stage F in females and stage G in males according to Demirjian method. Also, the mandibular canine might be analysed as indicator of SM in males, and results suggest that the peak of growth occurs no earlier than maturation stage F according to Demirjian method, only in male subjects. Further studies are needed to confirm these findings.

Fully automated deep learning approach to dental development assessment in panoramic radiographs.

BACKGROUND: Dental development assessment is an important factor in dental age estimation and dental maturity evaluation. This study aimed to develop and evaluate the performance of an automated dental development staging system based on Demirjian's method using deep learning. METHODS: The study included 5133 anonymous panoramic radiographs obtained from the Department of Pediatric Dentistry database at Seoul National University Dental Hospital between 2020 and 2021. The proposed methodology involves a three-step procedure for dental staging: detection, segmentation, and classification. The panoramic data were randomly divided into training and validating sets (8:2), and YOLOv5, U-Net, and EfficientNet were trained and employed for each stage. The models' performance, along with the Grad-CAM analysis of EfficientNet, was evaluated. RESULTS: The mean average precision (mAP) was 0.995 for detection, and the segmentation achieved an accuracy of 0.978. The classification performance showed F1 scores of 69.23, 80.67, 84.97, and 90.81 for the Incisor, Canine, Premolar, and Molar models, respectively. In the Grad-CAM analysis, the classification model focused on the apical portion of the developing tooth, a crucial feature for staging according to Demirjian's method. CONCLUSIONS: These results indicate that the proposed deep learning approach for automated dental staging can serve as a supportive tool for dentists, facilitating rapid and objective dental age estimation and dental maturity evaluation.

Automatic dental age calculation from panoramic radiographs using deep learning: a two-stage approach with object detection and image classification.

BACKGROUND: Dental age is crucial for treatment planning in pediatric and orthodontic dentistry. Dental age calculation methods can be categorized into morphological, biochemical, and radiological methods. Radiological methods are commonly used because they are non-invasive and reproducible. When radiographs are available, dental age can be calculated by evaluating the developmental stage of permanent teeth and converting it into an estimated age using a table, or by measuring the length between some landmarks such as the tooth, root, or pulp, and substituting them into regression formulas. However, these methods heavily depend on manual time-consuming processes. In this study, we proposed a novel and completely automatic dental age calculation method using panoramic radiographs and deep learning techniques. METHODS: Overall, 8,023 panoramic radiographs were used as training data for Scaled-YOLOv4 to detect dental germs and mean average precision were evaluated. In total, 18,485 single-root and 16,313 multi-root dental germ images were used as training data for EfficientNetV2 M to classify the developmental stages of detected dental germs and Top-3 accuracy was evaluated since the adjacent stages of the dental germ looks similar and the many variations of the morphological structure can be observed between developmental stages. Scaled-YOLOv4 and EfficientNetV2 M were trained using cross-validation. We evaluated a single selection, a weighted average, and an expected value to convert the probability of developmental stage classification to dental age. One hundred and fifty-seven panoramic radiographs were used to compare automatic and manual human experts' dental age calculations. RESULTS: Dental germ detection was achieved with a mean average precision of 98.26% and dental germ classifiers for single and multi-root were achieved with a Top-3 accuracy of 98.46% and 98.36%, respectively. The mean absolute errors between the automatic and manual dental age calculations using single selection, weighted average, and expected value were 0.274, 0.261, and 0.396, respectively. The weighted average was better than the other methods and was accurate by less than one developmental stage error. CONCLUSION: Our study demonstrates the feasibility of automatic dental age calculation using panoramic radiographs and a two-stage deep learning approach with a clinically acceptable level of accuracy.

Correlation between dental and skeletal maturity in Korean children based on dental maturity percentile: a retrospective study.

BACKGROUND: The correlation between dental maturity and skeletal maturity has been proposed, but its clinical application remains challenging. Moreover, the varying correlations observed in different studies indicate the necessity for research tailored to specific populations. AIM: To compare skeletal maturity in Korean children with advanced and delayed dental maturity using dental maturity percentile. DESIGN: Dental panoramic radiographs and cephalometric radiographs were obtained from 5133 and 395 healthy Korean children aged between 4 and 16 years old. Dental maturity was assessed with Demirjian's method, while skeletal maturity was assessed with the cervical vertebral maturation method. Standard percentile curves were developed through quantile regression. Advanced (93 boys and 110 girls) and delayed (92 boys and 100 girls) dental maturity groups were defined by the 50th percentile. RESULTS: The advanced group showed earlier skeletal maturity in multiple cervical stages (CS) in both boys (CS 1, 2, 3, 4, and 6) and girls (CS 1, 3, 4, 5, and 6). Significant differences, as determined by Mann-Whitney U tests, were observed in CS 1 for boys (p = 0.004) and in CS 4 for girls (p = 0.037). High Spearman correlation coefficients between dental maturity and cervical vertebral maturity exceeded 0.826 (p = 0.000) in all groups. CONCLUSION: A correlation between dental and skeletal maturity, as well as advanced skeletal maturity in the advanced dental maturity group, was observed. Using percentile curves to determine dental maturity may aid in assessing skeletal maturity, with potential applications in orthodontic diagnosis and treatment planning.

Association between dental age and malocclusions: a systematic review.

BACKGROUND: The evidence in the literature suggests that some skeletal or dental malocclusions are involved with dental development, resulting in advanced or delayed dental age (DA). The purpose of this systematic review was to investigate the association between DA and different types of malocclusions. METHODS: The search was carried out on PubMed, Scopus, Web of Science, Virtual Health Library, and in the gray literature. Observational studies that evaluated the association between DA and sagittal, vertical, or transversal malocclusions were included. The quality assessment was performed using the Newcastle-Ottawa Scale (NOS). The data from primary studies were narratively synthesized. The certainty of evidence was evaluated using the GRADE approach. The study was conducted from August 2023 to October 2023. RESULTS: One Thousand Nine Hundred Ninety-One records were identified in the initial search. Twenty (n = 20) studies were included. Most of the studies (n=15) presented a moderate quality according to NOS. Twelve studies evaluated the association between DA and sagittal discrepancies; eight studies evaluated vertical discrepancies, and only one study analyzed a transversal discrepancy. Demirjian's method for DA assessment was the most used among the studies. The primary studies observed that patients of both sexes presenting a vertical growth pattern and males with skeletal Class III malocclusion tend to have advanced DA. The study that investigated transversal malocclusion found that unilateral posterior cross-bite is associated with delayed DA. The certainty of evidence was very low for all outcomes evaluated. CONCLUSION: DA may be associated with the type of malocclusion. It is suggested that DA can be used as an initial diagnostic tool in orthodontics. Future well-designed studies should be performed in order to investigate the association between DA and different types of malocclusions in more detail. TRIAL REGISTRATION: This study was registered in the PROSPERO database (CRD42023454207).

A comparison of estimated age based on pulp volume from cone beam computed tomography (CT) images and panoramic radiography data with chronological age.

This retrospective study was conducted to evaluate different methods for dental age estimation in children and to examine the feasibility of using cone beam computed tomography (CBCT) data for age estimation. A total of 200 radiographic records (both digital panoramic radiographs and CBCTs) were acquired from 100 children aged 9 to 16 years, all taken on the same dates. Radiographic data was acquired from archived records and included both panoramic radiography and CBCT data belonging to the same individual. CBCT was used when panoramic radiographic data was insufficient. The pulp volume and pulp/tooth volume ratio of the left first molar teeth in the mandible were calculated from the CBCT data using MIMICS software. In addition, age was estimated by the Demirjian and Willems methods from data obtained from panoramic radiography images. Statistical analyses and linear regression analysis were performed as necessary. There was a statistically significant difference between the mean difference between the Demirjian method and chronological age, and between the Willems method and chronological age (p < 0.001). Statistically significance was achieved in a linear regression model created from pulp volume (R2 = 0.098) and pulp/tooth volume ratio (R2 = 0.395) data for the estimated dental age analysis (p < 0.001) and a negative correlation was observed with chronological age. When compared estimated dental age from CBCT data with chronological age, the pulp/tooth volume ratio method yielded results closer to chronological age than using only pulp volume data. When considering both panoramic radiographic age estimation methods and age estimation methods using CBCT data, we found that the results obtained with the Willems method, a panoramic radiographic age estimation technique, provided the closest results to the chronological age. More contributions should be made to the literature regarding the feasibility of age estimation using pulp and tooth volume as an alternative method.

Dental age estimation methods applied to Indian children and adolescents: A systematic review and meta-analysis.

Country-specific systematic reviews and meta-analyses have been proposed to compile the available literature and rank methods based on their performance for a target population. India is a country with a vast scientific literature on dental age estimation. This systematic review aimed to provide evidence to help the decision of experts regarding the method of choice for dental age estimation in India. The research protocol was registered in Open Science Framework. Literature Search was performed in Embase, LILACS, MedLine (via PubMed), SciELO, Scopus and Web of Science. Grey Literature was searched in Google Scholar and ProQuest. Observational cross-sectional studies that compared chronological and estimated ages using Demirjian (original [DEM] and Chaillet's modification [modified-DEM]) and Acharya (ACH) methods were included. JBI tool was used to assess the risk of bias. The search detected 9799 studies, out of which 56 were eligible (n=13,107 panoramic radiographs of Indian individuals). Low risk of bias was registered for 48 studies, while 8 presented a moderate risk of bias. The meta-analysis showed a standardized mean difference between chronological and estimated ages of -0.11 (95%CI: -0.29; 0.07), 0.74 (95%CI: 0.39; 1.09), and -0.01 (95%CI: -0.23; 0.22) years for DEM, modified-DEM and ACH, respectively. High heterogeneity (I2=88-93%) was observed across studies for all the methods, including subgroup analyses based on sex. This study ranked ACH, DEM and modified-DEM (from the best to the worse) performances in the Indian population.

Application of Medical Statistical and Machine Learning Methods in the Age Estimation of Living Individuals.

In the study of age estimation in living individuals, a lot of data needs to be analyzed by mathematical statistics, and reasonable medical statistical methods play an important role in data design and analysis. The selection of accurate and appropriate statistical methods is one of the key factors affecting the quality of research results. This paper reviews the principles and applicable principles of the commonly used medical statistical methods such as descriptive statistics, difference analysis, consistency test and multivariate statistical analysis, as well as machine learning methods such as shallow learning and deep learning in the age estimation research of living individuals, and summarizes the relevance and application prospects between medical statistical methods and machine learning methods. This paper aims to provide technical guidance for the age estimation research of living individuals to obtain more scientific and accurate results.

Dental Age Estimation in Northern Chinese Han Children and Adolescents Using Demirjian's Method Combined with Machine Learning Algorithms.

OBJECTIVES: To investigate the application value of combining the Demirjian's method with machine learning algorithms for dental age estimation in northern Chinese Han children and adolescents. METHODS: Oral panoramic images of 10 256 Han individuals aged 5 to 24 years in northern China were collected. The development of eight permanent teeth in the left mandibular was classified into different stages using the Demirjian's method. Various machine learning algorithms, including support vector regression (SVR), gradient boosting regression (GBR), linear regression (LR), random forest regression (RFR), and decision tree regression (DTR) were employed. Age estimation models were constructed based on total, female, and male samples respectively using these algorithms. The fitting performance of different machine learning algorithms in these three groups was evaluated. RESULTS: SVR demonstrated superior estimation efficiency among all machine learning models in both total and female samples, while GBR showed the best performance in male samples. The mean absolute error (MAE) of the optimal age estimation model was 1.246 3, 1.281 8 and 1.153 8 years in the total, female and male samples, respectively. The optimal age estimation model exhibited varying levels of accuracy across different age ranges, which provided relatively accurate age estimations in individuals under 18 years old. CONCLUSIONS: The machine learning model developed in this study exhibits good age estimation efficiency in northern Chinese Han children and adolescents. However, its performance is not ideal when applied to adult population. To improve the accuracy in age estimation, the other variables can be considered.

Research Progress on Dental Age Estimation Based on MRI Technology.

Dental age estimation is a crucial aspect and one of the ways to accomplish forensic age estimation, and imaging technology is an important technique for dental age estimation. In recent years, some studies have preliminarily confirmed the feasibility of magnetic resonance imaging (MRI) in evaluating dental development, providing a new perspective and possibility for the evaluation of dental development, suggesting that MRI is expected to be a safer and more accurate tool for dental age estimation. However, further research is essential to verify its accuracy and feasibility. This article reviews the current state, challenges and limitations of MRI in dental development and age estimation, offering reference for the research of dental age assessment based on MRI technology.

Adolescents and Children Age Estimation Using Machine Learning Based on Pulp and Tooth Volumes on CBCT Images.

OBJECTIVES: To estimate adolescents and children age using stepwise regression and machine learning methods based on the pulp and tooth volumes of the left maxillary central incisor and cuspid on cone beam computed tomography (CBCT) images, and to compare and analyze the estimation results. METHODS: A total of 498 Shanghai Han adolescents and children CBCT images of the oral and maxillofacial regions were collected. The pulp and tooth volumes of the left maxillary central incisor and cuspid were measured and calculated. Three machine learning algorithms (K-nearest neighbor, ridge regression, and decision tree) and stepwise regression were used to establish four age estimation models. The coefficient of determination, mean error, root mean square error, mean square error and mean absolute error were computed and compared. A correlation heatmap was drawn to visualize and the monotonic relationship between parameters was visually analyzed. RESULTS: The K-nearest neighbor model (R2=0.779) and the ridge regression model (R2=0.729) outperformed stepwise regression (R2=0.617), while the decision tree model (R2=0.494) showed poor fitting. The correlation heatmap demonstrated a monotonically negative correlation between age and the parameters including pulp volume, the ratio of pulp volume to hard tissue volume, and the ratio of pulp volume to tooth volume. CONCLUSIONS: Pulp volume and pulp volume proportion are closely related to age. The application of CBCT-based machine learning methods can provide more accurate age estimation results, which lays a foundation for further CBCT-based deep learning dental age estimation research.