Skip to main content

Advertisement

SpringerLink
Log in

Age estimation based on 3D pulp chamber segmentation of first molars from cone-beam–computed tomography by integrated deep learning and level set

  • Original Article
  • Published:
International Journal of Legal Medicine Aims and scope Submit manuscript

Abstract

Objectives

To develop an automatic segmentation method to segment the pulp chamber of first molars from 3D cone-beam–computed tomography (CBCT) images, and to estimate ages by calculated pulp volumes.

Materials and methods

Patients with CBCT scans were retrospectively identified. The age estimation was formulated as CBCT image segmentation using a coarse-to-fine strategy by integrated deep learning (DL) and level set (LS), followed by establishing a linear regression model. On the training data, DL model was trained for coarse segmentation. The validation set was to determine the optimal DL model, and a LS method established on it was to refine the coarse segmentation. On the testing data, the integrated DL and LS method was applied for pulp chamber segmentation, followed by volume calculation and age estimation. Statistical analysis was performed by Wilcoxon rank sum test to demonstrate gender difference in pulp chamber volume, and volume difference between maxillary and mandibular molars. Wilcoxon signed-rank test was adopted to compare true and estimated ages.

Results

A total of 180 CBCT studies were randomly divided into 37/10/133 patients for training, validation, and testing data, respectively. In the training and validation sets, the results showed high spatial overlaps between manual and automatic segmentation (dice = 87.8%). For the testing set, the estimated human ages were not significantly different with true human age (p = 0.57), with a correlation coefficient r = 0.74.

Conclusions

An integrated DL and LS method was able to segment pulp chamber of first molars from 3D CBCT images, and the derived pulp chamber volumes could effectively estimate the human ages.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Abbreviations

CBCT:

Cone-beam–computed tomography

References

  1. Ge ZP, Ma RH, Li G, Zhang JZ, Ma XC (2015) Age estimation based on pulp chamber volume of first molars from cone-beam computed tomography images. Forensic Sci Int 253(133):e1–e7

    Google Scholar 

  2. Aboshi H, Takahashi T, Komuro T (2010) Age estimation using microfocus X-ray computed tomography of lower premolars. Forensic Sci Int 200(1):35–40

    Article  CAS  PubMed  Google Scholar 

  3. Griffin RC, Chamberiain AT, Hotz G, Penkman KE, Collins MJ (2009) Age estimation of archaeological remains using amino acid racemization in dental enamel: a comparison of morphological, biochemical, and known ages-at-death. Am J Phys Anthropol 140(2):244–252

    Article  CAS  PubMed  Google Scholar 

  4. Kim YK, Kho HS, Lee KH (2000) Age estimation by occlusal tooth wear. J Forensic Sci 45(2):303–309

    Article  CAS  PubMed  Google Scholar 

  5. Kazmi S, Manica S, Revie G, Shepherd S, Hector M (2019) Age estimation using canine pulp volumes in adults: a CBCT image analysis. Int J Legal Med 133(6):1967–1976

    Article  PubMed  PubMed Central  Google Scholar 

  6. Gok E, Fedakar R, Kafa IM (2020) Usability of dental pulp visibility and tooth coronal index in digital panoramic radiography in age estimation in the forensic medicine. J Int J Legal Med 134(1):381–392

    Article  Google Scholar 

  7. Nudel I, Pokhojaev A, Hausman BS, Bitterman Y, Shpack N, May H, Sarig R (2020) Age estimation of fragmented human dental remains by secondary dentin virtual analysis. Int J Legal Med 134(5):1853–1860

    Article  PubMed  Google Scholar 

  8. Suvarna M, Balla SB, Chinni SS, Reddy KSP, Gopalaiah H, Pujita C, Redhi RN (2020) Examination of the radiographic visibility of the root pulp of the mandibular second molars as an age marker. Int J Legal Med 134(5):1869–1873

    Article  Google Scholar 

  9. Balla SB, Ankisetti SA, Bushra A, Bolloju VB, Mujahed AM, Kanaparthi A, Buddhavarapu SS (2020) Preliminary analysis testing the accuracy of radiographic visibility of root pulp in the mandibular first molars as a maturity marker at age threshold of 18 years. Int J Legal Med 134(2):769–774

    Article  PubMed  Google Scholar 

  10. Panchbhai AS (2011) Dental radiographic indicators, a key to age estimation. Dentomaxillofac Radiol 40(4):199–212

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Cameriere R, Ferrante L, Cingolani M (2004) Variations in pulp/tooth area ratio as an indicator of age: a preliminary study. J Forensic Sci 49(2):317–319

    Article  PubMed  Google Scholar 

  12. Drusini AG, Toso O, Ranzato C (1997) The coronal pulp cavity index: a biomarker for age determination in human adults. Am J Phys Anthropol 103(3):353–363

    Article  CAS  PubMed  Google Scholar 

  13. Cameriere R, Cunha E, Wasterlain SN, Luca SD, Sassaroli E, Pagliara F, Nuzzolese E, Cingolani M, Ferrante L (2013) Age estimation by pulp/tooth ratio in lateral and central incisors by peri-apical X-ray. J Forensic Legal Med 20(5):530–536

    Article  CAS  Google Scholar 

  14. Pinchi V, Pradella F, Buti J, Baldinotti C, Focardi M, Norelli GA (2015) A new age estimation procedure based on the 3D CBCT study of the pulp cavity and hard tissues of the teeth for forensic purposes: a pilot study. J Forensic Legal Med 36:150–157

    Article  Google Scholar 

  15. Agematsu H, Someda H, Hashimoto M, Matsunaga S, Abe S, Kim HJ, Koyama T, Naito H, Ishida R, Ide Y (2010) Three-dimensional observation of decrease in pulp cavity volume using micro-CT: age-related change. Bull Tokyo Dent Coll 51(1):1–6

    Article  PubMed  Google Scholar 

  16. Star H, Thevissen P, Jacobs R, Fieuws S, Solheim T, Willems G (2011) Human dental age estimation by calculation of pulp-tooth volume ratios yielded on clinically acquired cone beam computed tomography images of monoradicular teeth. J Forensic Sci 56(Suppl 1):S77–S82

    Article  PubMed  Google Scholar 

  17. Angelis DD, Gaudio D, Guercini N, Cipriani F, Gibelli D, Caputi S, Cattaneo C (2015) Age estimation from canine volumes. Radiol Med 120(8):731–736

    Article  PubMed  Google Scholar 

  18. Cameriere R, Luca SD, Aleman I, Ferrante L, Cingolani M (2012) Age estimation by pulp/tooth ratio in lower premolars by orthopantomography. Forensic Sci Int 214:105–112

    Article  PubMed  Google Scholar 

  19. Hesamian MH, Jia W, He X, Kennedy P (2019) Deep learning techniques for medical image segmentation: achievements and challenges. J Digit Imaging 32(4):582–596

    Article  PubMed  PubMed Central  Google Scholar 

  20. Litjens G, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, Laak JAWM, Ginneken B, Sanchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88

    Article  PubMed  Google Scholar 

  21. Carin L, Pencina MJ (2018) On deep learning for medical image analysis. JAMA 320(11):1192–1193

    Article  PubMed  Google Scholar 

  22. Yu L, X. Yang, Chen H, Qin J, Heng PA (2017) Volumetric convNets with mixed residual connections for automated prostate segmentation from 3D MR images. The Thirty-First AAAI Conference on Artificial Intelligence (AAAI), San Francisco, California, USA:66–72

  23. Oktay O, Schlemper J, Folgoc LL, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla NY, Kainz B, Glocker B, Rueckert D (2018) Attention U-net: learning where to look for the pancreas. The First Conference on Medical Imaging with Deep Learning (MIDL), Amsterdam, The Netherlands:1–10

  24. Roy AG, Conjeti S, Navab N, Wachinger C (2019) QuickNAT: a fully covolutional network for quick and accurate segmentation of neuroanatomy. NeuroImage 186:713–727

    Article  Google Scholar 

  25. Chan TF, Vese LA (2001) Acitve contours without edges. IEEE Trans Image Process 10(2):266–277

    Article  CAS  PubMed  Google Scholar 

  26. Li CM, Xu CY, Gui CF, Fox MD (2005) Level set evolution without re-initialization: a new variational formulation. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA 1:430–436

  27. Mathew DG, Rajesh S, Koshi E, Priya LE, Nair AS, Mohan A (2013) Adult forensic age estimation using mandibular first molar radiographs: a novel technique. J Forensic Den Sci 5(1):56–59

    Article  Google Scholar 

  28. Penaloza TYM, Karkhanis S, Kvaal SI, Vasudavan S, Castelblanco E, Kruger E, Tennant M (2016) Reliability and repeatability of pulp volume reconstruction through three different volume calculations. J Forensic Odontostomatol 34(2):35–46

    Google Scholar 

  29. Wang L, Li JP, Ge ZP, Li G (2019) CBCT image based segmentation method for tooth pulp cavity region extraction. Dentomaxillofac Radiol 48(2):20180236

    Article  PubMed  Google Scholar 

Download references

Funding

This work was supported by the National Natural Science Foundation of China (61802330); National Key R&D Program of China (No. 2018YFC0807303).

Author information

Authors and Affiliations

  1. School of Computer and Control Engineering, Yantai University, Yantai, China

    Qiang Zheng

  2. Department of Oral and Maxillofacial Radiology, Peking University School and Hospital of Stomatology, Beijing, China

    Zhipu Ge, Han Du & Gang Li

  3. Qingdao Stomatological Hospital, Qingdao, China

    Zhipu Ge

Authors
  1. Qiang Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhipu Ge
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Han Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Gang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors have made substantial contributions to all of the following: (1) the conception and design of the study, or acquisition of data, or analysis and interpretation of data; (2) drafting the article or revising it critically for important intellectual content; (3) final approval of the version to be submitted.

Corresponding author

Correspondence to Gang Li.

Ethics declarations

Conflicts of interest/competing interests

The authors declare that they have no conflict of interest.

Ethics approval

The institutional review board approval of this retrospective study was obtained prior to initiating the study.

Consent to participate

A waiver of consent/parental permission, assent and the Health Insurance Portability and Accountability Act of 1996 (HIPAA) authorization has been approved by the institutional review board.

Additional information

Publisher’s note

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

Supplementary Information

ESM 1

(DOCX 29 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zheng, Q., Ge, Z., Du, H. et al. 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 (2021). https://doi.org/10.1007/s00414-020-02459-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00414-020-02459-x

Keywords

Search

Navigation