Abstract
Age estimation can aid in forensic medicine applications, diagnosis, and treatment planning for orthodontics and pediatrics. Existing dental age estimation methods rely heavily on specialized knowledge and are highly subjective, wasting time, and energy, which can be perfectly solved by machine learning techniques. As the key factor affecting the performance of machine learning models, there are usually two methods for feature extraction: human interference and autonomous extraction without human interference. However, previous studies have rarely applied these two methods for feature extraction in the same image analysis task. Herein, we present two types of convolutional neural networks (CNNs) for dental age estimation. One is an automated dental stage evaluation model (ADSE model) based on specified manually defined features, and the other is an automated end-to-end dental age estimation model (ADAE model), which autonomously extracts potential features for dental age estimation. Although the mean absolute error (MAE) of the ADSE model for stage classification is 0.17 stages, its accuracy in dental age estimation is unsatisfactory, with the MAE (1.63 years) being only 0.04 years lower than the manual dental age estimation method (MDAE model). However, the MAE of the ADAE model is 0.83 years, being reduced by half that of the MDAE model. The results show that fully automated feature extraction in a deep learning model without human interference performs better in dental age estimation, prominently increasing the accuracy and objectivity. This indicates that without human interference, machine learning may perform better in the application of medical imaging.
Similar content being viewed by others
Data availability
Not applicable.
Code availability
Not applicable.
References
Willems G, Moulin-Romsee C, Solheim T (2002) Non-destructive dental-age calculation methods in adults: intra- and inter-observer effects. Forensic Sci Int 126:221–226. https://doi.org/10.1016/s0379-0738(02)00081-6
Willems G (2001) A review of the most commonly used dental age estimation techniques. J Forensic Odontostomatol 19:9–17
Costa J, Montero J, Serrano S, Albaladejo A, Lopez-Valverde A, Bica I (2014) Accuracy in the legal age estimation according to the third molars mineralization among Mexicans and Columbians. Aten Primaria 46(Suppl 5):165–175. https://doi.org/10.1016/S0212-6567(14)70086-1
Shamim T (2018) Forensic pediatric dentistry. J Forensic Dent Sci 10:128–131. https://doi.org/10.4103/jfo.jfds_79_17
Markovic E, Marinkovic N, Zelic K, Milovanovic P, Djuric M, Nedeljkovic N (2021) Dental age estimation according to European formula and Willems method: comparison between children with and without cleft lip and palate. Cleft Palate Craniofac J: 1055665621990513https://doi.org/10.1177/1055665621990513
Pinchi V, Bianchi I, Pradella F et al (2021) Dental age estimation in children affected by juvenile rheumatoid arthritis. Int J Legal Med 135:619–629. https://doi.org/10.1007/s00414-020-02395-w
Schmeling A, Grundmann C, Fuhrmann A et al (2008) Criteria for age estimation in living individuals. Int J Legal Med 122:457–460. https://doi.org/10.1007/s00414-008-0254-2
Demirjian A, Goldstein H, Tanner JM (1973) A new system of dental age assessment. Hum Biol 45:211–227
Olze A, Bilang D, Schmidt S, Wernecke KD, Geserick G, Schmeling A (2005) Validation of common classification systems for assessing the mineralization of third molars. Int J Legal Med 119:22–26. https://doi.org/10.1007/s00414-004-0489-5
Guo YC, Lin XW, Zhang WT et al (2015) Chronology of third molar mineralization in a northern Chinese population. Rechtsmedizin 25:34–39. https://doi.org/10.1007/s00194-014-0998-6
Liversidge HM (2008) Timing of human mandibular third molar formation. Ann Hum Biol 35:294–321. https://doi.org/10.1080/03014460801971445
Guo YC, Yan CX, Lin XW et al (2014) The influence of impaction to the third molar mineralization in northwestern Chinese population. Int J Legal Med 128:659–665. https://doi.org/10.1007/s00414-014-0979-z
Chaillet N, Nystrom M, Kataja M, Demirjian A (2004) Dental maturity curves in Finnish children: Demirjian’s method revisited and polynomial functions for age estimation. J Forensic Sci 49:1324–1331
Dubina TL, Dyundikova VA, Zhuk EV (1983) Biological age and its estimation. II. Assessment of biological age of albino rats by multiple regression analysis. Exp Gerontol 18:5–18. https://doi.org/10.1016/0531-5565(83)90046-3
Hegde S, Patodia A, Shah K, Dixit U (2019) The applicability of the Demirjian, Willems and Chaillet standards to age estimation of 5–15 year old Indian children. J Forensic Odontostomatol 37:40–50
Yang J, Xie M, Hu C et al (2021) Deep learning for detecting cerebral aneurysms with CT angiography. Radiology 298:155–163. https://doi.org/10.1148/radiol.2020192154
Zhang J, Zhou Y, Vieira DN et al (2021) An efficient method for building a database of diatom populations for drowning site inference using a deep learning algorithm. Int J Legal Med. https://doi.org/10.1007/s00414-020-02497-5
Li Y, Wu W, Chen H, Cheng L, Wang S (2020) 3D tumor detection in automated breast ultrasound using deep convolutional neural network. Med Phys 47:5669–5680. https://doi.org/10.1002/mp.14477
Ahn Y, Lee SM, Noh HN et al (2021) Use of a commercially available deep learning algorithm to measure the solid portions of lung cancer manifesting as subsolid lesions at CT: comparisons with radiologists and invasive component size at pathologic examination. Radiology: 202803. https://doi.org/10.1148/radiol.2021202803
Zheng Q, Ge Z, Du H, Li G (2021) Age estimation based on 3D pulp chamber segmentation of first molars from cone-beam-computed tomography by integrated deep learning and level set. Int J Legal Med 135:365–373. https://doi.org/10.1007/s00414-020-02459-x
Toneva D, Nikolova S, Agre G, Zlatareva D, Hadjidekov V, Lazarov N (2020) Machine learning approaches for sex estimation using cranial measurements. Int J Legal Med. https://doi.org/10.1007/s00414-020-02460-4
Aghnia Farda N, Lai JY, Wang JC, Lee PY, Liu JW, Hsieh IH (2020) Sanders classification of calcaneal fractures in CT images with deep learning and differential data augmentation techniques. Injury. https://doi.org/10.1016/j.injury.2020.09.010
Naik A, Edla DR, Dharavath R (2021) Prediction of malignancy in lung nodules using combination of deep, fractal, and gray-level co-occurrence matrix features. Big Data. https://doi.org/10.1089/big.2020.0190
Stern D, Payer C, Urschler M (2019) Automated age estimation from MRI volumes of the hand. Med Image Anal 58:101538. https://doi.org/10.1016/j.media.2019.101538
Mohaiminul Islam M, Huang S, Ajwad R, Chi C, Wang Y, Hu P (2020) An integrative deep learning framework for classifying molecular subtypes of breast cancer. Comput Struct Biotechnol J 18:2185–2199. https://doi.org/10.1016/j.csbj.2020.08.005
Liang M, Tang W, Xu DM et al (2016) Low-dose CT screening for lung cancer: computer-aided detection of missed lung cancers. Radiology 281:279–288. https://doi.org/10.1148/radiol.2016150063
Merdietio Boedi R, Banar N, De Tobel J, Bertels J, Vandermeulen D, Thevissen PW (2020) Effect of lower third molar segmentations on automated tooth development staging using a convolutional neural network. J Forensic Sci 65:481–486. https://doi.org/10.1111/1556-4029.14182
De Tobel J, Radesh P, Vandermeulen D, Thevissen PW (2017) An automated technique to stage lower third molar development on panoramic radiographs for age estimation: a pilot study. J Forensic Odontostomatol 35:42–54
Banar N, Bertels J, Laurent F et al (2020) Towards fully automated third molar development staging in panoramic radiographs. Int J Legal Med 134:1831–1841. https://doi.org/10.1007/s00414-020-02283-3
Galibourg A, Cussat-Blanc S, Dumoncel J, Telmon N, Monsarrat P, Maret D (2021) Comparison of different machine learning approaches to predict dental age using Demirjian’s staging approach. Int J Legal Med 135:665–675. https://doi.org/10.1007/s00414-020-02489-5
Stern D, Payer C, Giuliani N, Urschler M (2019) Automatic age estimation and majority age classification from multi-factorial MRI data. IEEE J Biomed Health Inform 23:1392–1403. https://doi.org/10.1109/JBHI.2018.2869606
Vila-Blanco N, Carreira MJ, Varas-Quintana P, Balsa-Castro C, Tomas I (2020) Deep neural networks for chronological age estimation from OPG images. IEEE Trans Med Imaging 39:2374–2384. https://doi.org/10.1109/TMI.2020.2968765
Guo YC, Han M, Chi Y et al (2021) Accurate age classification using manual method and deep convolutional neural network based on orthopantomogram images. Int J Legal Med 135:1589–1597. https://doi.org/10.1007/s00414-021-02542-x
Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Tan MX, Le QV (2019) EfficientNet: rethinking model scaling for convolutional neural networks. In: 36th International Conference on Machine Learning (ICML) Long Beach, CA
Schmeling A, Olze A, Reisinger W, Konig M, Geserick G (2003) Statistical analysis and verification of forensic age estimation of living persons in the Institute of Legal Medicine of the Berlin University Hospital Charite. Legal Medicine (Tokyo) 5:S367–S371. https://doi.org/10.1016/s1344-6223(02)00134-7
Olze A, Solheim T, Schulz R, Kupfer M, Pfeiffer H, Schmeling A (2010) Assessment of the radiographic visibility of the periodontal ligament in the lower third molars for the purpose of forensic age estimation in living individuals. Int J Legal Med 124:445–448. https://doi.org/10.1007/s00414-010-0488-7
Kim DK, Cho BJ, Lee MJ, Kim JH (2021) Prediction of age and sex from paranasal sinus images using a deep learning network. Medicine (Baltimore) 100:e24756. https://doi.org/10.1097/MD.0000000000024756
Degermenci M, Ertekin T, Ulger H, Acer N, Coskun A (2016) The age-related development of maxillary sinus in children. J Craniofac Surg 27:e38-44. https://doi.org/10.1097/SCS.0000000000002304
Funding
This work was supported by the National Key Research and Development Program of China under Grant No. 2017YFA0700800; the National Natural Science Foundation of China under Grant Nos. 81701869, 61971343, and 61627811; the Key Research and Development Program of Shaanxi Province of China under Grant No. 2020GXLH-Y-008; and Young Science and Technology Star Program of Shaanxi Province of China No.2020KJXX-025.
Author information
Authors and Affiliations
Contributions
Conceiving the study and the design: S.Y.D., Y.C.G.; annotations, creating the datasets, training the models, validation tests, conducting the statistical analysis and data analysis: M.Q.H., Y.T.C., H.L., D.Z.; analyzing the results: all authors; drafting the manuscript: M.Q.H., Y.Y.G., D.Z.; critically revising for important intellectual content: S.Y.D., Y.C.G.
Corresponding authors
Ethics declarations
Ethics approval
For this type of study, formal consent is not required.
Consent to participate
For this type of study, formal consent is not required.
Consent for publication
Not applicable.
Conflict of interest
The authors declare 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
About this article
Cite this article
Han, M., Du, S., Ge, Y. et al. With or without human interference for precise age estimation based on machine learning?. Int J Legal Med 136, 821–831 (2022). https://doi.org/10.1007/s00414-022-02796-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00414-022-02796-z