Age Estimation Based on 3D Pulp Segmentation of First Molars from CBCT Images Using U-Net

Overview

Journal Dentomaxillofac Radiol

Publisher Oxford University Press

Date 2023 Jul 10

PMID 37427595

Authors

Yangjing Song

Huifang Yang

Zhipu Ge

Han Du

Gang Li

Affiliations

Soon will be listed here.

Abstract

Objective: To train a U-Net model to segment the intact pulp cavity of first molars and establish a reliable mathematical model for age estimation.

Methods: We trained a U-Net model by 20 sets of cone-beam CT images and this model was able to segment the intact pulp cavity of first molars. Utilizing this model, 239 maxillary first molars and 234 mandibular first molars from 142 males and 135 females aged 15-69 years old were segmented and the intact pulp cavity volumes were calculated, followed by logarithmic regression analysis to establish the mathematical model with age as the dependent variable and pulp cavity volume as the independent variable. Another 256 first molars were collected to estimate ages with the established model. Mean absolute error and root mean square error between the actual and the estimated ages were used to assess the precision and accuracy of the model.

Results: The dice similarity coefficient of the U-Net model was 95.6%. The established age estimation model was [Formula: see text] ( is the intact pulp cavity volume of the first molars). The coefficient of determination (R), mean absolute error and root mean square error were 0.662, 6.72 years, and 8.26 years, respectively.

Conclusion: The trained U-Net model can accurately segment pulp cavity of the first molars from three-dimensional cone-beam CT images. The segmented pulp cavity volumes could be used to estimate the human ages with reasonable precision and accuracy.

Citing Articles

Unveiling the power of artificial intelligence for image-based diagnosis and treatment in endodontics: An ally or adversary?.

Fontenele R, Jacobs R Int Endod J. 2024; 58(2):155-170.

PMID: 39526945 PMC: 11715142. DOI: 10.1111/iej.14163.

Optimal Training Positive Sample Size Determination for Deep Learning with a Validation on CBCT Image Caries Recognition.

Wang Y, Li G, Zhang X, Wang Y, Zhang Z, Li J Diagnostics (Basel). 2024; 14(18).

PMID: 39335759 PMC: 11431354. DOI: 10.3390/diagnostics14182080.

A reliable deep-learning-based method for alveolar bone quantification using a murine model of periodontitis and micro-computed tomography imaging.

Xi R, Ali M, Zhou Y, Tizzano M J Dent. 2024; 146:105057.

PMID: 38729290 PMC: 11288397. DOI: 10.1016/j.jdent.2024.105057.

Machine learning assessment of dental age classification based on cone-beam CT images: a different approach.

Dogan O, Boyacioglu H, Goksuluk D Dentomaxillofac Radiol. 2024; 53(1):67-73.

PMID: 38214945 PMC: 11003658. DOI: 10.1093/dmfr/twad009.

Third Molar Eruption in Dental Panoramic Radiographs as a Feature for Forensic Age Assessment-Presentation of a New Non-Staging Method Based on Measurements.

Timme M, Bender J, Steffens L, Shay D, Schmeling A Biology (Basel). 2023; 12(11).

PMID: 37998002 PMC: 10669860. DOI: 10.3390/biology12111403.

References

Chung M, Lee M, Hong J, Park S, Lee J, Lee J . Pose-aware instance segmentation framework from cone beam CT images for tooth segmentation. Comput Biol Med. 2020; 120:103720. DOI: 10.1016/j.compbiomed.2020.103720. View

Ge Z, Ma R, Li G, Zhang J, Ma X . Age estimation based on pulp chamber volume of first molars from cone-beam computed tomography images. Forensic Sci Int. 2015; 253:133.e1-7. DOI: 10.1016/j.forsciint.2015.05.004. View

Lahoud P, EzEldeen M, Beznik T, Willems H, Leite A, Van Gerven A . Artificial Intelligence for Fast and Accurate 3-Dimensional Tooth Segmentation on Cone-beam Computed Tomography. J Endod. 2021; 47(5):827-835. DOI: 10.1016/j.joen.2020.12.020. View

Wang Y, Liu S, Wang G, Liu Y . Accurate tooth segmentation with improved hybrid active contour model. Phys Med Biol. 2018; 64(1):015012. DOI: 10.1088/1361-6560/aaf441. View

Nemoto T, Futakami N, Kunieda E, Yagi M, Takeda A, Akiba T . Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs. Radiol Phys Technol. 2021; 14(3):318-327. DOI: 10.1007/s12194-021-00630-6. View

Zhang J, Xia W, Dong J, Tang Z, Zhao Q . Root Canal Segmentation in CBCT Images by 3D U-Net with Global and Local Combination Loss. Annu Int Conf IEEE Eng Med Biol Soc. 2021; 2021:3097-3100. DOI: 10.1109/EMBC46164.2021.9629727. View

Yang F, Jacobs R, Willems G . Dental age estimation through volume matching of teeth imaged by cone-beam CT. Forensic Sci Int. 2006; 159 Suppl 1:S78-83. DOI: 10.1016/j.forsciint.2006.02.031. View

Helmy M, Osama M, Elhindawy M, Mowafey B . Volume analysis of second molar pulp chamber using cone beam computed tomography for age estimation in Egyptian adults. J Forensic Odontostomatol. 2021; 38(3):25-34. PMC: 8565657. View

Karkhanis S, Mack P, Franklin D . Age estimation standards for a Western Australian population using the coronal pulp cavity index. Forensic Sci Int. 2013; 231(1-3):412.e1-6. DOI: 10.1016/j.forsciint.2013.04.004. View

10.

Drusini A, Toso O, Ranzato C . The coronal pulp cavity index: a biomarker for age determination in human adults. Am J Phys Anthropol. 1997; 103(3):353-63. DOI: 10.1002/(SICI)1096-8644(199707)103:3<353::AID-AJPA5>3.0.CO;2-R. View

11.

Kazmi S, Manica S, Revie G, Shepherd S, Hector M . Age estimation using canine pulp volumes in adults: a CBCT image analysis. Int J Legal Med. 2019; 133(6):1967-1976. PMC: 6811669. DOI: 10.1007/s00414-019-02147-5. View

12.

Cameriere R, Ferrante L, Cingolani M . Variations in pulp/tooth area ratio as an indicator of age: a preliminary study. J Forensic Sci. 2004; 49(2):317-9. View

13.

Ikeda N, Umetsu K, Kashimura S, Suzuki T, Oumi M . [Estimation of age from teeth with their soft X-ray findings]. Nihon Hoigaku Zasshi. 1985; 39(3):244-50. View

14.

Asif M, Nambiar P, Mani S, Ibrahim N, Khan I, Lokman N . Dental age estimation in Malaysian adults based on volumetric analysis of pulp/tooth ratio using CBCT data. Leg Med (Tokyo). 2018; 36:50-58. DOI: 10.1016/j.legalmed.2018.10.005. View

15.

Yu G, Ye L, Huang D . [Clinical investigation of radix entomolaris in mandibular first molars]. Hua Xi Kou Qiang Yi Xue Za Zhi. 2012; 30(3):259-61. View

16.

Adserias-Garriga J, Thomas C, Ubelaker D, Zapico S . When forensic odontology met biochemistry: Multidisciplinary approach in forensic human identification. Arch Oral Biol. 2017; 87:7-14. DOI: 10.1016/j.archoralbio.2017.12.001. View

17.

Dan Y, Zhu Z, Jin W, Li Z . S-Swin Transformer: simplified Swin Transformer model for offline handwritten Chinese character recognition. PeerJ Comput Sci. 2022; 8:e1093. PMC: 9575930. DOI: 10.7717/peerj-cs.1093. View

18.

Koranne V, Mhapuskar A, Marathe S, Joshi S, Saddiwal R, Nisa S . Age estimation in Indian adults by the coronal pulp cavity index. J Forensic Dent Sci. 2018; 9(3):177. PMC: 5887645. DOI: 10.4103/jfo.jfds_60_16. View

19.

Haghanifar S, Ghobadi F, Vahdani N, Bijani A . Age estimation by pulp/tooth area ratio in anterior teeth using cone-beam computed tomography: comparison of four teeth. J Appl Oral Sci. 2019; 27:e20180722. PMC: 9648962. DOI: 10.1590/1678-7757-2018-0722. View

20.

Chu G, Zhang Z, Zhou H, Yan C, Chen T, Guo Y . [Research Progress of Age Estimation Based on Age-related Changes of Dentin-pulp Complex]. Fa Yi Xue Za Zhi. 2018; 34(3):280-285. DOI: 10.12116/j.issn.1004-5619.2018.03.013. View