Skip to main content
Download PDF

Application of entire dental panorama image data in artificial intelligence model for age estimation

BMC Oral Health volume 23, Article number: 1007 (2023) Cite this article

Abstract

Background

Accurate age estimation is vital for clinical and forensic purposes. With the rapid advancement of artificial intelligence(AI) technologies, traditional methods relying on tooth development, while reliable, can be enhanced by leveraging deep learning, particularly neural networks. This study evaluated the efficiency of an AI model by applying the entire panoramic image for age estimation. The outcome performances were analyzed through supervised learning (SL) models.

Methods

Total of 27,877 dental panorama images from 5 to 90 years of age were classified by 2 types of grouping. In type 1 they were classified by each age and in type 2, applying heuristic grouping, the age over 20 years were classified by every 5 years. Wide ResNet (WRN) and DenseNet (DN) were used for supervised learning. In addition, the analysis with ± 3 years of deviation in both types were performed.

Results

For the DN model, while the type 1 grouping achieved an accuracy of 0.1016 and F1 score of 0.058, the type 2 achieved an accuracy of 0.3146 and F1 score of 0.2027. Incorporating ± 3years of deviation, the accuracy of type 1 and 2 were 0.281, 0.7323 respectively; and the F1 score were 0.1768, 0.6583 respectively. For the WRN model, while the type 1 grouping achieved an accuracy of 0.1041 and F1 score of 0.0599, the type 2 achieved an accuracy of 0.3182 and F1 score of 0.2071. Incorporating ± 3years of deviation, the accuracy of type 1 and 2 were 0.2716, 0.7323 respectively; and the F1 score were 0.1709, 0.6437 respectively.

Conclusions

The application of entire panorama image data for supervised with classification by heuristics grouping with ± 3years of deviation for supervised learning models and demonstrated satisfactory outcome for the age estimation.

Peer Review reports

Background

Age estimation is extremely important in radiographical, clinical and forensic practice. Accurate age estimation is essential for multiple purposes, as it can be applied to determine the precise time and treatment strategy based on clinical findings [1, 2] and it can serve as important forensic evidence. In children and adolescents, despite several limitations, the development of dentition is one of the most stable and important markers for age estimation [3, 4]. Compared to other skeletal age evaluations, tooth growth and development are less affected by environmental circumstances [5, 6]. This may be related to the precise genetic control of tooth development and eruption [7].

There are many methods for estimating age based on tooth development, eruption, and mineralization stages [8,9,10]. However, theses usually provide slightly less accurate estimations. Many researchers have created modified methods to improve the accuracy of age estimations, adjusting the numbers for particular races and populations or constructing more complex methods of analysis [11, 12]. Even if there have been various improvements, learning the complicated methods that differ depending on the observer and require the intensive efforts of professionals for estimation analysis can still be challenging. However, with the recent advancements in deep learning technology, such as neural networks, multiple layers of interconnected nodes can process vast amounts of data. These networks adjust the weights and biases of the nodes to minimize the error between the predicted output and the actual output [13,14,15,16].

However, most previous machine learning studies have been based on the simple application of existing age estimation methods that are limited to using specific teeth or parts of dental panoramic images for analysis. This study evaluated the application of entire panoramic image data in the deep learning for the age estimation. The outcome performance of age estimation of two supervised learning models, WideResNet,(WRN) and DenseNet (DS) was analyzed.

Materials and methods

Ethical approval

This study was conducted in accordance with the guidelines of the World Medical Association Helsinki Declaration for biomedical research involving human subjects. This study was approved by the Institutional Review Board (IRB) and Clinical Data Warehouse (CDW) data review board of The Catholic University of Korea, Catholic Medical Center (XC21WADI0064). Needs for informed consent were waived by the IRB. Data were collected and administered by CDW and the images were exported under the supervision of Enterprise Data Platform (EDP) of The Catholic University of Korea Information Convergence Institute.

Data collection and classification

After IRB and Data review board’s approval, the CDW system searched for a list of subjects who visited Eunpyeong St. Mary’s Hospital, St. Vincent Hospital, or Seoul St. Mary’s Hospital of the College of Medicine of The Catholic University of Korea from 2016 to 2020 and underwent panoramic imaging obtained using a ProMax (Planmeca, Helsingki, Finland) or Kodak 8000 Digital Panoramic System (Carestream Health Inc., NY, USA) according to the user manual. The patient data list was undergone to an automatic de-identification process by the CDW system. The panoramic images of listed patients were provided by EDP system after the information had been de-identified and the privacy was ensured. From the collected list, a total of 121,469 qualified panoramic images were downloaded by the EDP system in JPEG format. (Fig. 1) The panorama radiographs with low resolution or pathologic lesion such as cyst and tumors were excluded. Of these radiographs, 27,877 images were randomly selected and labeled from 5 to 90 years of age and gender by two experienced dentists. Each image was resized to 256 × 256 pixels. Since the numbers of instances among classes were unbalanced, a re-sampling technique was utilized to uniformly match the amount of data (Tables 1 and 2).

Fig. 1
figure 1

Image data acquisition process through CDW & EDP system

Full size image
Table 1 Type 1 classification: Numbers of data classified by each age
Full size table
Table 2 Type 2 classification Number of images by age and gender in heuristics grouping where the age over 20 years were classified by every 5 years
Full size table

Modeling and learning

Total of 27,877 dental panorama images labeled from 5 to 90 years of age were classified by 2 types of grouping. In type 1, they were classified by each age and in type 2, using heuristic grouping, the age over 20 years was classified by every 5 years. In addition, the application of ± 3 years of deviation in both types was also analyzed. Dataset was split into three disjoint sets, including a training set, a validation set and a test set consisting of 13,220, 1,653 and 1,653 images, respectively. (Tables 1 and 2)

DN and WRN models were applied for supervised learning. Stochastic gradient descent was used as an optimizer with a learning rate of 0.005, a mini-batch size of 8, a resize of 256 and a momentum of 0.9.

Performance analysis

The accuracy, sensitivity, precision, and f1 scores were calculated to evaluate the performance of each model. Python programming language (v. 3.7.11), Pytorch (v.1.8.2) and a graphics card (Nvidia Quadro 6000 8GB *2) were used for analysis.

Results

Tables 3 and 4 show the model performances of DN and WRN. After a total of 13,220 classified panorama images were trained, 1,653 images were used for validation in each model. The same number of images used for validation was utilized for the test. The best performance was obtained using 40 epochs.

Table 3 Performance of DenseNet model
Full size table
Table 4 Performance of WideResNet model
Full size table

In DN model, the accuracy and F1 score for type 1 grouping were 0.1016 and 0.058, respectively, with a ± 3years of deviation, 0.2813 and 0.1768. For the type 2 grouping, the accuracy and F1 score were 0.3146 and 0.2027, respectively, with a ± 3years of deviation, 0.7641 and 0.6583. The precision and recall score of type 1 grouping were 0.0579 and 0.0583, respectively, with a ± 3years of deviation, 0.1776 and 0.1768. For the type 2 grouping, precision and recall score were 0.2115 and 0.2117, respectively, with a ± 3years of deviation, 0.6632 and 0.6658 respectively.

In WRN model, the accuracy and F1 score of type 1 grouping were 0.1041 and 0.0599, respectively, with a ± 3years of deviation, 0.2716 and 0.1709. For the type 2 grouping, the accuracy and F1 score were 0.3182 and 0.2071, respectively, with a ± 3years of deviation. 0.7323 and 0.6437 respectively. The precision and recall score of type 1 grouping were 0.0598 and 0.0608, respectively, with a ± 3years of deviation, 0.1707 and 0.1718. For the type 2 grouping, precision and recall score were 0.2098 and 0.2147, respectively, with a ± 3years of deviation, 0.7623 and 0.6476 respectively.

Figures 2 and 3 show the results of both DN and WRN models as a confusion matrix. Considering that a higher the diagonal value of the confusion matrix indicates a more accurate predictive model, the figure present a significant accurate diagnosis in type 2 grouping with a ± 3years of deviation in both DN and WRN models.

Figs. 2
figure 2

a and b. Confusion matrix of the results by DenseNet. 2a results before heuristic grouping (type1gourping). 2b, results after heuristic grouping (type 2 grouping)

Full size image
Figs. 3
figure 3

a and b. Confusion matrix of the results by WideResNet. 3a results before heuristic grouping (type1gourping). 3b, results after heuristic grouping (type 2 grouping)

Full size image

Discussion

Over the years age estimation through imaging has been a well-established method within the field of forensic dentistry, garnering widespread recognition for its inherent utility. Panchbhai discussed various radiological methods used for human age identification. The literature survey identified 46 relevant articles that highlighted the significance of radiography in assessing the extent of dental tissue calcification, crown and root formation, eruption stages, and their correlation with age [17]. Radiographic and tomographic techniques are cost-effective and important tools in forensic dentistry for human identification, especially when combined with information technology resources. Imaging, clinical, and forensic dentists should consider the available methods and legal requirements to ensure accurate age estimation.

Most available age estimation methods are statistical methods that require effort and time during preprocessing measurement. For example, age can be predicted using a regression formula with tooth-coronal index (TCI) [18,19,20]. In comparison, the present study estimated age based on the overall appearance of a panoramic image rather than the tooth shape, such as measuring the TCI of a specific tooth. The method used in this study differed from previous papers. Simply classifying the images by age reduced the effort of preprocessing step that traditionally required labelling of specific structure of tooth by professionals. And the application of deep learning allowed the process of the data from full panorama images for the analysis of the age estimation not limiting in only from specific teeth data. However, Due to their complexity, AI systems have been often regarded as black boxes, which do not provide any feedback on why and how they arrive at their predictions. In future, efficient application of “explainable AI” is expected to visualize, interpret, and explain the logic behind AI solutions and provide clear prediction strategies [21].

Several other methods for age estimation have been devised. In a machine learning study using Cone beam computed tomography (CBCT) images, the buccal alveolar bone levels of 150 images were utilized by dividing ages of 20–69 years old into 5-year units. In Saric’s CBCT based study, the Random Forest classifier achieved a correlation coefficient of 0.803 and a mean absolute error of 6.022 [22]. However, since the CBCT study used a small number of samples, additional research is needed to determine whether it can be widely applied. In addition, it is more difficult to obtain a CBCT image than a dental panorama for age estimation, and there is a risk of radiation exposure. The present method achieved relatively precise age estimations through heuristic grouping with of supervised classification learning models with 13,220 whole panoramic images.

An AI-based age estimation study using 1,922 panoramic images of patients 15–23 years old was conducted in Malaysia [23]. The study used a hybrid model of convolutional neural networks (CNN) and K nearest neighbors (KNN). Although the method age range was narrow, it successfully estimated age in one-year, six-month, three-months and one-month range with accuracies of 99.98%, 99.96%, 99.87% and 98.78%, respectively. The hybrid (HCNN-KNN) model made good predictions but is based on relatively certain eruption and developmental stages in adolescents and young adults except for those receiving orthodontic treatment, those with dysplasia or those who experienced trauma. The present study was analyzed not only young age patient, but also adult and older patients were included. The machine learning covered the images of the living patient of the age from 5 to 90.

In a CNN study using panoramic photos of 4,035 patients aged 19–85 years in Croatia, age estimation studies were conducted in four groups: 0–15 years old, 16–30 years old, 31–60 years old and over 61 years old with the VGG16 AI learning method [24] through whole orthopantomographic images of archaeological skull. The study demonstrated 73% accuracy. In Korea, a study was conducted on artificial intelligence learning using CNN on 1,586 dental panoramic X-rays [25]. The image of the first molar was exported and the age was estimated by CNN learning. Based on the data from the 10-year-old group, the patients were reclassified into three groups of 0–19 years old, 20–49 years old and 50 years old or older with an estimated accuracy ranging from 89.05 to 90.27%. In both studies, the use of CNN with graphics was attempted rather than simple AI learning and the Korean study also presented the results of heatmap and Grad-CAM. In the present study, grouping was conducted through artificial intelligence learning and the accuracy and f1 score were improved after heuristic grouping. While previous studies have focused on improving accuracy using a wide age range of patients, In the present study, heuristics grouping for over 20 years of age dividing by every 5 years with ± 3 years of deviation for the analysis was applied for provide improve accuracy of age estimation in narrower age range.

It is a known fact that, the external validation using panoramic radiograph datasets from other institutions is necessary to obtain reliable results [26]. However, since each medical imaging data contains private personal information, such data are primarily protected and locked. and not easily accessible and shareable between different institutions due to medical ethical issue [27]. Nevertheless, this study is characterized by the utilization of data from three hospitals of our university located in different districts and with different panorama equipment system. The collection and de-identification of the data were performed using CDW system. And the panorama image files were downloaded and protected by the EDP system of our institution. It would contributed to diminish the overfitting.

The supervised machine learning model used in this study, were WRN and DN. The WRN model is a type of SL using a novel network with decreased depth and increased width of residual networks compared to the previous ResNet model [28]. In addition to the effect of dropout in the residual block, WRN provides better performance and faster training compared to previous deep learning networks, achieving new state-of-the-art and significant improvements compared to ImageNet [28]. While WRN focused on the width of the network, DN focused on the shortcut connections of ResNet [29]. In previous SL involving ResNet, the Highway network, and ResDrop, only the output of the previous layer was sent to the next layer. In comparison, DN receives the output of many previous layers at once and combines the inputs by concatenation rather than addition [29]. Compared with WRN showing the same performance and similar error rates, DN reported an improvement with approximately two times fewer parameters, suggesting deep supervision as the reason for the improved performance [29]. Both SL models exhibited significantly improved results compared to the previous generation, with similar results between them. Based on this performance, both models are being applied in a wide range of medical research fields, with the possibility of more extensive use in the future [30, 31]. Another study compared age estimation on panoramic radiography using the Kvaal method and machine learning. The study found that machine learning techniques, specifically the XG Boosting Reg classifier, showed higher precision in age estimation (MAE: 4.77) compared to the Kvaal method (MAE: 5.68), indicating that ML can enhance age estimation on panoramic radiographs [32]. The reason for the superiority of various machine learning age estimation methods is that the range/quantity of features or patterns that a human can find in a panoramic image is smaller than the features/patterns that a deep neural network can find. It is also difficult to explain the results of age estimation because it is difficult to know which part of the image the deep neural network looked at to identify the features or patterns. However, if advances in this field continue in the future, more convenient and faster age estimation will provide an opportunity to better understand the principles of analysis using deep neural networks.

Artificial intelligence learning could be a useful solution in forensics fields such as age estimation because it can perform complex tasks that were previously difficult to complete in a faster and more accurate manner. In order to achieve this goal, research should continue to utilize and develop various machine learning methods. In the future, it is essential to conduct research on the application and evaluation of various new methods, including semi-supervised learning or SL using artificial intelligence.

Conclusion

This preliminary study attempts to utilize entire dental panoramic image data in a deep learning model for age estimation. Instead of traditionally requiring professionals to label specific tooth structures, simply classifying the images by age reduced the effort of the preprocessing step. The application of deep learning enabled the analysis of age estimation using data from full panoramic images, rather than being limited to specific teeth data. The performances of both DN and WRN models, with heuristics grouping (where ages over 20 years were classified in 5-year intervals) and a deviation of ± 3 years, yielded satisfactory results in accuracy, recall, precision, and F1 scores. These results are comparable to previous studies on age estimation using traditional methods that require intensive professional effort for analysis and utilize partial data from images, such as teeth. Further clinical and transdisciplinary studies in the medical and advanced technological fields are needed to enhance the quality and simplify the process of age estimation through AI. In the future, the application of AI is expected to assist humans in clinical and dentomaxillofacial radiology fields.

Data availability

The datasets generated and/or analyzed during the present study are not publicly available as ethics approval was granted on the basis that only the researchers involved in the study could access the identified data but are available and accessible from the corresponding author on reasonable request.

Abbreviations

AI:

Artificial Intelligence

SL:

Supervised Learning

WRN:

WideResNet

DS:

DenseNet

IRB:

Institutional Review Board

CDW:

Clinical Data Warehouse

EDP:

Enterprise Data Platform

TCI:

tooth-coronal index

CBCT:

Cone beam computed tomography

CNN:

convolutional neural networks

KNN:

K nearest neighbors

VGG16:

Very Deep Convolutional Networks for Large-Scale Image Recognition

References

  1. Bagherian A, Sadeghi M. Assessment of dental maturity of children aged 3.5 to 13.5 years using the Demirjian method in an Iranian population. J Oral Sci. 2011;53:37–42. https://doi.org/10.2334/josnusd.53.37.

    Article  PubMed  Google Scholar 

  2. Kumaresan R, Cugati N, Chandrasekaran B, Karthikeyan P. Reliability and validity of five radiographic dental-age estimation methods in a population of Malaysian children. J Investig Clin Dent. 2016;7:102–9. https://doi.org/10.1111/jicd.12116.

    Article  PubMed  Google Scholar 

  3. Cunha E, Baccino E, Martrille L, Ramsthaler F, Prieto J, Schuliar Y, et al. The problem of aging human remains and living individuals: a review. Forensic Sci Int. 2009;193:1–13. https://doi.org/10.1016/j.forsciint.2009.09.008.

    Article  PubMed  Google Scholar 

  4. Franklin D. Forensic age estimation in human skeletal remains: current concepts and future directions. Leg Med (Tokyo). 2010;12:1–7. https://doi.org/10.1016/j.legalmed.2009.09.001.

    Article  PubMed  Google Scholar 

  5. Cardoso HF. Environmental effects on skeletal versus dental development: using a documented subadult skeletal sample to test a basic assumption in human osteological research. Am J Phys Anthropol. 2007;132:223–33. https://doi.org/10.1002/ajpa.20482.

    Article  PubMed  Google Scholar 

  6. Conceição EL, Cardoso HF. Environmental effects on skeletal versus dental development II: further testing of a basic assumption in human osteological research. Am J Phys Anthropol. 2011;144:463–70. https://doi.org/10.1002/ajpa.21433.

    Article  PubMed  Google Scholar 

  7. Laurencin D, Wong A, Chrzanowski W, Knowles JC, Qiu D, Pickup DM, et al. Probing the calcium and sodium local environment in bones and teeth using multinuclear solid state NMR and X-ray absorption spectroscopy. Phys Chem Chem Phys. 2010;12:1081–91. https://doi.org/10.1039/b915708e.

    Article  PubMed  Google Scholar 

  8. Buk Z, Kordik P, Bruzek J, Schmitt A, Snorek M. The age at death assessment in a multi-ethnic sample of pelvic bones using nature-inspired data mining methods. Forensic Sci Int. 2012;220:294e291–299. https://doi.org/10.1016/j.forsciint.2012.02.019.

    Article  Google Scholar 

  9. Corsini MM, Schmitt A, Bruzek J. Aging process variability on the human skeleton: artificial network as an appropriate tool for age at death assessment. Forensic Sci Int. 2005;148:163–7. https://doi.org/10.1016/j.forsciint.2004.05.008.

    Article  PubMed  Google Scholar 

  10. Harris EF. Dental age: effects of estimating different events during mineralization. Dent Anthropol. 2011;24:59–63. https://doi.org/10.26575/daj.v24i2-3.63.

    Article  Google Scholar 

  11. Blenkin MR, Evans W. Age estimation from the teeth using a modified Demirjian system. J Forensic Sci. 2010;55:1504–8. https://doi.org/10.1111/j.1556-4029.2010.01491.x.

    Article  PubMed  Google Scholar 

  12. Teivens A, Mörnstad H. A comparison between dental maturity rate in the Swedish and Korean populations using a modified Demirjian method. J Forensic Odontostomatol. 2001;19:31–5.

    PubMed  Google Scholar 

  13. Dallora AL, Anderberg P, Kvist O, Mendes E, Diaz Ruiz S, Sanmartin J, Berglund. Bone age assessment with various machine learning techniques: a systematic literature review and meta-analysis. PLoS ONE. 2019;14:e0220242. https://doi.org/10.1371/journal.pone.0220242.

    Article  PubMed  PubMed Central  Google Scholar 

  14. Galibourg A, Cussat-Blanc S, Dumoncel J, Telmon N, Monsarrat P, Maret D. Comparison of different machine learning approaches to predict dental age using Demirjian’s staging approach. Int J Legal Med. 2021;135:665–75. https://doi.org/10.1007/s00414-020-02489-5.

    Article  PubMed  Google Scholar 

  15. Tao J, Wang J, Wang A, Xie Z, Wang Z, Wu S et al. Dental age estimation: a machine learning perspective, in: Hassanien A, Azar A, Gaber T, Bhatnagar RF, Tolba M, Eds., The International Conference on Advanced Machine Learning Technologies and Applications (AMLTA2019), Springer, Cham, 2020, pp. 722–733. https://doi.org/10.1007/978-3-030-14118-9_71.

  16. Vila-Blanco N, Carreira MJ, Varas-Quintana P, Balsa-Castro C, Tomas I. Deep neural networks for chronological age estimation from OPG images. IEEE Trans Med Imaging. 2020;39:2374–84. https://doi.org/10.1109/tmi.2020.2968765.

    Article  PubMed  Google Scholar 

  17. Panchbhai AS. Dental radiographic indicators, a key to age estimation. Dentomaxillofac Radiol. 2011;40(4):199–212. https://doi.org/10.1259/dmfr/19478385. PMID: 21493876; PMCID: PMC3520308.

    Article  PubMed  PubMed Central  Google Scholar 

  18. Jeon HS, Tea IH, Ko MY, Ahn YW. [Age estimation by dental radiographs in Korean adults]. J Oral Med Pain. 2009;34:179–88.

    Google Scholar 

  19. Shen S, Liu Z, Wang J, Fan L, Ji F, Tao J. Machine learning assisted Cameriere method for dental age estimation. BMC Oral Health. 2021;21:641. https://doi.org/10.1186/s12903-021-01996-0.

    Article  PubMed  PubMed Central  Google Scholar 

  20. Štepanovský M, Ibrová A, Buk Z, Velemínská J. Novel age estimation model based on development of permanent teeth compared with classical approach and other modern data mining methods. Forensic Sci Int. 2017;279:72–82. https://doi.org/10.1016/j.forsciint.2017.08.005.

    Article  PubMed  Google Scholar 

  21. Schwendicke F, Samek W, Krois J. Artificial Intelligence in Dentistry: chances and challenges. J Dent Res. 2020;99(7):769–74. https://doi.org/10.1177/0022034520915714. Epub 2020 Apr 21. PMID: 32315260; PMCID: PMC7309354.

    Article  PubMed  Google Scholar 

  22. Saric R, Kevric J, Hadziabdic N, Osmanovic A, Kadic M, Saracevic M, et al. Dental age assessment based on CBCT images using machine learning algorithms. Forensic Sci Int. 2022;334:111245. https://doi.org/10.1016/j.forsciint.2022.111245.

    Article  PubMed  Google Scholar 

  23. Sharifonnasabi F, Jhanjhi NZ, John J, Obeidy P, Band SS, Alinejad-Rokny H, et al. Hybrid HCNN-KNN model enhances age estimation accuracy in orthopantomography. Front Public Health. 2022;10:879418. https://doi.org/10.3389/fpubh.2022.879418.

    Article  PubMed  PubMed Central  Google Scholar 

  24. Banjšak L, Milošević D, Subašić M. Implementation of artificial intelligence in chronological age estimation from orthopantomographic X-ray images of archaeological skull remains. Bull Int Association Paleodontology. 2020;14:122–9.

    Google Scholar 

  25. Kim S, Lee YH, Noh YK, Park FC, Auh QS. Age-group determination of living individuals using first molar images based on artificial intelligence. Sci Rep. 2021;11:1073. https://doi.org/10.1038/s41598-020-80182-8.

    Article  PubMed  PubMed Central  Google Scholar 

  26. Bleeker SE, Moll HA, Steyerberg EW, Donders AR, Derksen-Lubsen G, Grobbee DE, et al. External validation is necessary in prediction research: a clinical example. J Clin Epidemiol. 2003;56(9):826–32. https://doi.org/10.1016/s0895-4356(03)00207-5.

    Article  PubMed  Google Scholar 

  27. Schwendicke F, Samek W, Krois J. Artificial Intelligence in Dentistry: chances and challenges. J Dent Res. 2020;99(7):769–74. https://doi.org/10.1177/0022034520915714.

    Article  PubMed  Google Scholar 

  28. Zagoruyko S, Komodakis N. Wide residual networks, arXiv preprint. (2016) arXiv:1605.07146. https://doi.org/10.48550/arXiv.1605.07146.

  29. Huang G, Liu Z, van der Maaten L, Weinberger KQ, Densely connected convolutional networks, in: O’Conner L, Vision, Recognition P. (CVPR), IEEE, Honolulu (HI), USA, 2017, pp. 2261–2269. https://doi.org/10.1109/CVPR.2017.243.

  30. Zhong Z, Wei F, Lin Z, Zhang C. ADA-Tucker: compressing deep neural networks via adaptive dimension adjustment tucker decomposition. Neural Netw. 2019;110:104–15. https://doi.org/10.1016/j.neunet.2018.10.016.

    Article  PubMed  Google Scholar 

  31. Kim YJ, Kim KG. [Development of an optimized deep learning model for medical imaging]. Taehan Yongsang Uihakhoe Chi. 2020;81:1274–89. https://doi.org/10.3348/jksr.2020.0171.

    Article  PubMed  Google Scholar 

  32. Pereira de Sousa D, Diniz Lima E, Souza Paulino JA, Dos Anjos Pontual ML, Meira Bento P, Melo DP. Age determination on panoramic radiographs using the Kvaal method with the aid of artificial intelligence. Dentomaxillofac Radiol. 2023;52(4):20220363. https://doi.org/10.1259/dmfr.20220363. Epub 2023 Mar 29. PMID: 36988148; PMCID: PMC10170175.

    Article  PubMed  Google Scholar 

Download references

Funding

This study was funded by a 2021 research grant from the Research Institute of Medical Science, The Catholic University of Korea, Eunpyeong St. Mary’s Hospital (EPSMH-B-2021-09). The funding only provided support of research materials to SL and did not play an additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Author information

Authors and Affiliations

  1. Department of Dentistry, Eunpyeong St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, 1021, Tongil-ro, Eunpyeong-gu, Seoul, 03312, Republic of Korea

    Se Hoon Kahm & Sang Hwa Lee

  2. Division of Oral & Maxillofacial Surgery, Department of Dentistry, St. Vincent’s Hospital, College of Medicine, The Catholic University of Korea, 93 Jungbu-daero, Paldal-gu, Suwon-si, Gyeonggi-do, Republic of Korea

    Ji-Youn Kim

  3. Unidocs Inc, 272 Digital-ro, Guro-gu, Seoul, Republic of Korea

    Seok Yoo

  4. Department of Artificial Intelligence, Graduate School, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul, Republic of Korea

    Soo-Mi Bae

  5. JINHAKapply Corp, 34 Gyeonghuigung-gil, Jongno-gu, Seoul, Republic of Korea

    Ji-Eun Kang

Authors
  1. Se Hoon Kahm
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ji-Youn Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Seok Yoo
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Soo-Mi Bae
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ji-Eun Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Sang Hwa Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

SH Kahm: The acquisition, analysis, and interpretation of data for the work; AND Drafting the work and revising it critically for important intellectual content; Agreement to be accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved. Final approval of the version to be published. JY Kim: Revising it critically for important intellectual content Agreement to be accountable for all aspects of the work in ensuring thatquestions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved. S Yoo: Substantial contributions to the conception or design of the work; or the acquisition, analysis, or interpretation of data for the work; Drafting the work or revising it critically for important intellectual content. SM Bae: the acquisition, analysis, or interpretation of data for the work; revising it critically for important intellectual contentJE Kang: the acquisition, analysis, or interpretation of data for the work; revising it critically for important intellectual content. SH Lee: Substantial contributions to the conception or design of the work, the acquisition, analysis, and interpretation of data for the work; AND Drafting the work and revising it critically for important intellectual content; AND Final approval of the version to be published; AND Agreement to be accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Corresponding author

Correspondence to Sang Hwa Lee.

Ethics declarations

Ethics approval and consent to participate

The study was conducted according to the guidelines of the Declaration of Helsinki. And this study was approved by the Institutional Review Board (IRB) and Clinical Data Warehouse (CDW) data review board of the Catholic University of Korea, Catholic Medical Center (XC21WADI0064), and waived the need for informed consent.

Consent for publication

Not applicable.

Competing interests

The authors declare that they have no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kahm, S.H., Kim, JY., Yoo, S. et al. Application of entire dental panorama image data in artificial intelligence model for age estimation. BMC Oral Health 23, 1007 (2023). https://doi.org/10.1186/s12903-023-03745-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1186/s12903-023-03745-x

Keywords

BMC Oral Health

ISSN: 1472-6831

Contact us