Accuracy of the London Atlas, Haavikko's Method and Cameriere's European Formula of dental age estimation in Turkish children

Dental age estimation using a convolutional neural network algorithm on panoramic radiographs: A pilot study in Indonesia

Purpose

This study employed a convolutional neural network (CNN) algorithm to develop an automated dental age estimation method based on the London Atlas of Tooth Development and Eruption. The primary objectives were to create and validate CNN models trained on panoramic radiographs to achieve accurate dental age predictions using a standardized approach.

Material and Methods

A dataset of 801 panoramic radiographs from outpatients aged 5 to 15 years was used. A CNN model for dental age estimation was developed using a 16-layer CNN architecture implemented in Python with TensorFlow and Scikit-learn, guided by the London Atlas of Tooth Development. The model included 6 convolutional layers for feature extraction, each followed by a pooling layer to reduce the spatial dimensions of the feature maps. A confusion matrix was used to evaluate key performance metrics, including accuracy, precision, recall, and F1 score.

Results

The proposed model achieved an overall accuracy, precision, recall, and F1 score of 74% on the validation set. The highest F1 scores were observed in the 10-year and 12-year age groups, indicating superior performance in these categories. In contrast, the 6-year age group demonstrated the highest misclassification rate, highlighting potential challenges in accurately estimating age in younger individuals.

Conclusion

Integrating a CNN algorithm for dental age estimation represents a significant advancement in forensic odontology. The application of AI improves both the precision and efficiency of age estimation processes, providing results that are more reliable and objective than those obtained via traditional methods.

Comparison of different dental age estimation methods with deep learning: Willems, Cameriere-European, London Atlas

This study aimed to compare dental age estimates using Willems, Cameriere-Europe, London Atlas, and deep learning methods on panoramic radiographs of Turkish children. The dental ages of 1169 children (613 girls, 556 boys) who agreed to participate in the study were determined by 4 different methods. The Convolutional Neural Network models examined were implemented in the TensorFlow library. Simple correlations and intraclass correlations between children's chronological ages and dental age estimates were calculated. Goodness-of-fit criteria were calculated based on the errors in dental age estimates and the smallest possible values for the Akaike Information Criterion, the Bayesian-Schwarz Criterion, the Root Mean Squared Error, and the coefficient of determination value. Simple correlations were observed between dental age and chronological ages in all four methods (p < 0.001). However, there was a statistically significant difference between the average dental age estimates of methods other than the London Atlas for boys (p = 0.179) and the four methods for girls (p < 0.001). The intra-class correlation between chronological age and methods was examined, and almost perfect agreement was observed in all methods. Moreover, the predictions of all methods were similar to each other in each gender and overall (Intraclass correlation [ICCW] = 0.92, ICCCE=0.94, ICCLA=0.95, ICCDL=0.89 for all children). The London Atlas is only suitable for boys in predicting the age of Turkish children, Willems, Cameriere-Europe formulas, and deep learning methods need revision.

An investigation of the validity of the Bedek models and Cameriere-European formula used in dental age prediction in Turkish children

BACKGROUND

Dental age estimation is one of the most reliable methods for determining age, commonly used for forensic, criminal, and anthropological purposes. The purpose of this study was to assess and compare the precision of the Bedek models and the Cameriere-European Formula (CF) in determinating dental age in a sample of Turkish individuals.

METHODS

Retrospective panoramic radiographs of 1018 subjects (497 boys and 521 girls) aged 5-14 years were evaluated using the Bedek models and the CF. The differences between calculated dental age (DA) and chronological age (CA) for each sex and age group were analyzed using the paired sample t-test and the Wilcoxon signed-rank test. The accuracy of the methods used to estimate dental age was determined by calculating the mean absolute error (MAE) based on the proximity of the dental age to the chronological age.

RESULTS

The CF method overestimated CA by 0.1 year in the entire sample. Conversely, the Bedek models tended to overestimate CA, with the three-, four-, and seven-tooth models exhibiting the most significant difference. There was a statistically significant difference between boys and girls in the DA-CA calculation using the CF method in the entire sample. Among the Bedek models, the three- and four-tooth models had the lowest MAE in the entire sample, while the single-tooth model had the highest MAE.

CONCLUSION

The CF method showed higher accuracy in predicting the age of children living in eastern Turkey compared to the Bedek Models.

Accuracy of second and third molar maturity indices, Olze, Haavikko, and Demirjian methods for 14- and 16-year-old age thresholds assessment in Croatian children and adolescents

This study explores the reliability of four established legal age threshold estimation approaches in a Croatian sample. We applied Haavikko stages, Demirjian stages, Olze's third molar eruption stages, and second and third molar maturity indices measurement in 593 orthopantomograms of Croatian children and adolescents aged 11.00-20.99 years old. The left mandibular second and third molar were assessed. Logistic regression analysis was conducted to test the significance of predictive variables. Logistic Receiver operating characteristic (ROC) curves were performed to evaluate the classification ability of variables for estimating 14- and 16-year-old thresholds. The areas under the ROC curve (AUC), accuracy (Acc), sensitivity (Se), specificity (Sp), Positive Likelihood Ratio (LR +), Negative Likelihood Ratio (LR-), and Bayes post-test probability (Bayes PTP) were calculated to evaluate classification performance. Results suggest that the combination of I2M&I3M is the best classifier for the 14-year-old threshold (AUC = 0.879); for males alone, I2M is an even better classifier (AUC = 0.881). The highest Acc 80.1% (95%CI, 75.9%-83.9%), Bayes PTP 86.5% (95%CI, 82.8%-89.7%) and Sp 88.9% (95%CI, 83.0%-93.3%) were by I3M < 0.81 & I2M < 0.03 in total samples; the highest Acc 86.1% (80.6%- 90.6%), Bayes PTP 87.2% (95%CI, 81.7%- 91.4%) and Sp 87.8% (95%CI, 78.2%- 94.3%) were by I2M < 0.01 in males, Acc of Haavikko Ac and Demirjian H stage in second molar is very close with slightly lower Bayes PTP and Sp. I3M is a good classifier for 16-year-old threshold (AUC = 0.889). The cut-off value I3M < 0.34 can be used to classify the 16-year-old threshold with Acc of 80.6% (95%CI, 77.2%-83.7%), Sp of 83.4% (95%CI, 79.0%-87.3%), and 81.7% (95%CI, 78.4%-84.8%) Bayes PTP. In conclusion, to classify the 14-year-old threshold, a pair of cut-off values I3M < 0.81 & I2M < 0.03 can be used in Croatian females; I2M < 0.01, Demirjian H stage, Haavikko Ac stage in second molar, and the pair I3M < 0.81 & I2M < 0.03 can all be used in Croatian males. I3M < 0.34 can classify the 16-year-old threshold in Croatian populations.

Investigation of root apical closure of first permanent molars with cone-beam computed tomography: A retrospective study

Background/purpose

The objective of this study was to assess the root apical closure ages of first permanent molars retrospectively among a group of western Turkish children aged between 5 and 15 years using cone-beam computed tomography (CBCT).

Materials and methods

CBCT images of 202 patients were examined. The patients were divided into 7 groups according to age: ≤8 years, 8-8.99 years, 9-9.99 years, 10-10.99 years, 11-11.99 years, 12-12.99 years, and ≥13 years. Teeth with at least one open apex were considered as 'teeth with open apex' and teeth with all closed apices were considered as 'teeth with closed apex'. The data was evaluated by Pearson Chi-square test and Fisher's exact test. P value of <0.05 was considered statistically significant.

Results

Apical closure rate of the maxillary first molars was 4.1%, 32.2%, 55.4%, 76.2%, and 90.6% at 8-8.99 years, 9-9.99 years, 10-10.99 years, 11-11.99 years, and 12-12.99 years, respectively. Apical closure rate of the mandibular first molars was 4.4%, 41.2%, 70.7%, 80.0%, and 92.2% at 8-8.99 years, 9-9.99 years, 10-10.99 years, 11-11.99 years, and 12-12.99 years, respectively. At 12-12.99 years, females had a significantly higher rate of closed root apices of mandibular first molars than males (P < 0.05). At 9-9.99 and 12-12.99 years, females had a significantly higher rate of closed root apices of maxillary molars than males (P < 0.05).

Conclusion

CBCT is a useful tool for the evaluation of root development. The results of present study can provide valuable aids for clinicians during root canal treatment of permanent first molars.

Technical note: RP Atlas-an unprecedented proposal for a Brazilian population dental development chart based on the London atlas

Age estimation methods through developmental atlases are simplified by image comparison using radiographs. Atlas-based methods have been utilized to create population-specific charts addressing population diversity. To tackle the absence of a dedicated atlas for the Brazilian population, the objective of the present study was to create a new atlas for dental development in Brazil based on the London Atlas chart. The new atlas (RP Atlas) is based on the median of tooth development, eruption, and resorption in individuals aged 5 to 23. The sample (567 individuals) was divided between females (n = 290) and males (n = 277). The RP Atlas was handcrafted, scanned, colored, and clustered in two atlases divided by sex. The development of a specific atlas for the Brazilian population has the potential to enhance the accuracy of age estimation in forensic scenarios, notably in a mixed country like Brazil. Further research is needed to assess the suitability of the newly developed atlas for the Brazilian population.

A systematic overview of dental methods for age assessment in living individuals: from traditional to artificial intelligence-based approaches

Dental radiographies have been used for many decades for estimating the chronological age, with a view to forensic identification, migration flow control, or assessment of dental development, among others. This study aims to analyse the current application of chronological age estimation methods from dental X-ray images in the last 6 years, involving a search for works in the Scopus and PubMed databases. Exclusion criteria were applied to discard off-topic studies and experiments which are not compliant with a minimum quality standard. The studies were grouped according to the applied methodology, the estimation target, and the age cohort used to evaluate the estimation performance. A set of performance metrics was used to ensure good comparability between the different proposed methodologies. A total of 613 unique studies were retrieved, of which 286 were selected according to the inclusion criteria. Notable tendencies to overestimation and underestimation were observed in some manual approaches for numeric age estimation, being especially notable in the case of Demirjian (overestimation) and Cameriere (underestimation). On the other hand, the automatic approaches based on deep learning techniques are scarcer, with only 17 studies published in this regard, but they showed a more balanced behaviour, with no tendency to overestimation or underestimation. From the analysis of the results, it can be concluded that traditional methods have been evaluated in a wide variety of population samples, ensuring good applicability in different ethnicities. On the other hand, fully automated methods were a turning point in terms of performance, cost, and adaptability to new populations.

Age estimation using London Atlas methodology: A systematic review and meta-analysis

Age estimation is a fundamental competence of Forensic Anthropologists and Odontologists. The London Atlas is a dental development chart by AlQahtani et al. (2010) that gained recent notoriety due to its applicability in forensic scenarios. This study aimed to answer, by a systematic review of literature and meta-analysis, the following question: "on average, what is the deviation between real and estimated ages, when applying the London Atlas method in sub-adults?". This study was carried out according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and registered in the International Prospective Register of Systematic Reviews (PROSPERO). Five electronic databases were screened (PubMed, SciELO, Scopus, Web of Science, and LILACS), and active search was carried out. The quality assessment was performed by means of Joanna Briggs Institute Critical Appraisal Tools for Systematic Reviews. The initial search resulted in 1021 studies, from which 24 filled the inclusion criteria. For the meta-analysis, 17 studies provided sufficient data. Out of these, eleven studies enabled meta-analysis of mean absolute difference values. Standardized mean differences were 0.02 years for MD and 0.78 for MAD. Analysis of subgroups was also accomplished by sex, and did not indicated heterogeneity between males and females. The London Atlas is an accurate age estimation method, presenting acceptable error and bias values worldwide. Despite the high heterogeneity of the studies, majority of studies presented a low risk of bias. Meta-analysis showed a non-significant and slight tendency of overestimating age, in total. Sub-group analysis showed modestly better results for boys than girls.

The Cameriere, Haavikko, Demirjian, and Willems methods for the assessment of dental age in Croatian children

AIM

This study aimed to evaluate the accuracy and precision of the Cameriere European formula, Demirjian, Haavikko, and Willems methods for estimating dental age in a sample of children with permanent dentition in Croatia.

MATERIAL AND METHODS

The study consisted of a sample of 1576 panoramic radiographs; a sub-sample of 84 OPGs, in which all first seven mandibular teeth were maturated, was excluded from the study. A final sample of 1492 (704 males and 788 females) aged 6.0 to 13.9 years was evaluated. Seven mandibular teeth from the left side of the mandible were analyzed, and dental age (DA) was determined by the Cameriere European formula, Demirjian method from 1976, Haavikko, and Willems methods and compared to chronological age (CA). In addition, the mean age difference (DA-CA), the mean absolute error (MAE) between dental and chronological age, the percentage of the individuals of dental age within ± 0.25 to ± 2 years of chronological age, and intra-observer and inter-observer statistics were calculated.

RESULTS

The Cameriere European formula estimated the best dental age compared to the chronological age; the mean underestimation was - 0.4 years for both sexes, Haavikko underestimated by - 0.17 years, while Demirjian and Willems overestimated by 1.02 years and 0.48 years, respectively. The most significant difference showed the Demirjian method in 11-year-old and 12-year-old females. The MAE were 0.50 years, 1.01 years, 0.61 years, and 0.78 years in males and 0.51 years, 1.18 years, 0.61 years, and 0.70 years in females for the Cameriere European formula, Haavikko, Willems, and Demirjian methods, respectively. Furthermore, the Cameriere European formula showed the highest proportions of individuals with DA within ± 0.5 year difference of the CA, 61.5% in males and 59.6% in females. In addition, the Cameriere method showed the best intra-observer and inter-observer agreements.

CONCLUSIONS

Although the Demirjian method was used previously in Croatian children for legal, medical, and clinical purposes, the Cameriere European formula, Haavikko, and Willems were more accurate in the tested sample. According to our findings, the Cameriere European formula showed the best accuracy and precision in dental age assessment in Croatian children following Haavikko, and we recommend it as the method of the first choice in forensic and clinical analyses.

Employing the London Atlas in the Age Estimation of a Select South African Population

Dental age estimation in the living and deceased is a fundamental aspect of forensic sciences, civil cases, medico-legal proceedings and clinical dentistry. Accordingly, this study aimed to validate the accuracy and reproducibility of the London Atlas in a select South African sample of KwaZulu-Natal. In this cross-sectional study, 760 digital panoramic radiographs (n = 760) aged between 5.00 and 23.99 years were retrospectively reviewed through consecutive sampling. Each radiograph was assessed and assigned a dental age in accordance with the London Atlas of Human Tooth Development and Eruption by AlQahtani et al. (2010). The London Atlas overestimated age with a mean difference of −0.85 to −1.26 years in the selected South African sample of KwaZulu-Natal. A statistically significant difference between the chronological and estimated dental ages was recorded. Furthermore, the South African Black and Indian males had a higher overestimation of age than their female counterparts, with a mean difference of 0.13 and 0.07 years, respectively. This overestimation was less in the South African Indian population in comparison to the SA Black population. This outcome resulted in the creation of the KZN population- and sex-specific charts and atlases for the two selected cohorts of KwaZulu-Natal. The KZN Atlases were found to be more accurate in the selected sample, with a mean absolute error of 0.57 years and no statistically significant differences between the chronological and estimated dental ages.

Dental age estimation with fewer than mandibular seven teeth: An accuracy study of Bedek models in Turkish children

OBJECTIVES

One or more missing teeth, such as hypodontia, make it difficult to obtain accurate results in age estimation methods. This paper aims to test the accuracy of the models developed by Bedek et al. that can estimate age with fewer than seven teeth for Turkish children.

MATERIALS AND METHODS

Panoramic radiographs of 1118 children (540 girls and 578 boys) aged between 6 and 16 years were evaluated using the Willems method and Bedek models for the entire sample and for different ages and sexes. Differences between dental age (DA) and chronological age (CA) calculated for all methods for each sex and all age groups were analyzed the paired sample t-test and Wilcoxon signed rank test. The accuracy of the DA estimation methods was determined by the proximity of DA to CA by calculating mean absolute error (MAE).

RESULTS

While all Bedek models underestimated CA by 0.2 to 0.1 years, the Willems method overestimated CA by 0.3 years. DA-CA difference in the total sample and girls was statistically significant in all methods. In the total sample, the seven- and four-teeth models had the lowest MAE, while the one-tooth model had the highest MAE.

CONCLUSIONS

Seven- and four-teeth models were the most suitable for age estimation, and all models except the one-tooth model were found to be more accurate than the Willems method in northwestern Turkish children.

CLINICAL RELEVANCE

Especially in children with hypodontia, it may be possible to estimate DA with the use of Bedek models.