CoChat

Deep Neural Networks for Chronological Age Estimation From OPG Images

Open access
Vila-Blanco, Nicolas, Carreira, Maria J., Varas-Quintana, Paulina, Balsa-Castro, Carlos, Tomas, Inmaculada · 2020 · IEEE Transactions on Medical Imaging
Cited by 158

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

Abstract

Chronological age estimation is crucial labour in many clinical procedures, where the teeth have proven to be one of the best estimators. Although some methods to estimate the age from tooth measurements in orthopantomogram (OPG) images have been developed, they rely on time-consuming manual processes whose results are affected by the observer subjectivity. Furthermore, all those approaches have been tested only on OPG image sets of good radiological quality without any conditioning dental characteristic. In this work, two fully automatic methods to estimate the chronological age of a subject from the OPG image are proposed. The first (DANet) consists of a sequential Convolutional Neural Network (CNN) path to predict the age, while the second (DASNet) adds a second CNN path to predict the sex and uses sex-specific features with the aim of improving the age prediction performance. Both methods were tested on a set of 2289 OPG images of subjects from 4.5 to 89.2 years old, where both bad radiological quality images and images showing conditioning dental characteristics were not discarded. The results showed that the DASNet outperforms the DANet in every aspect, reducing the median Error (E) and the median Absolute Error (AE) by about 4 months in the entire database. When evaluating the DASNet in the reduced datasets, the AE values decrease as the real age of the subjects decreases, until reaching a median of about 8 months in the subjects younger than 15. The DASNet method was also compared to the state-of-the-art manual age estimation methods, showing significantly less over- or under-estimation problems. Consequently, we conclude that the DASNet can be used to automatically predict the chronological age of a subject accurately, especially in young subjects with developing dentitions.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tmi.2020.2968765

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 6 references

Research works printed but not linked: 61

  1. 10.1016/j.eswa.2018.04.001 · DOI · Paper page
  2. 10.1007/s00414-007-0179-1 · doi:10.1007/s00414-007-0179-1
  3. 10.1007/s00414-008-0279-6 · doi:10.1007/s00414-008-0279-6
  4. 10.1017/CBO9780511542565.004 · DOI · Paper page
  5. 10.1177/00220345590380010601 · DOI · Paper page
  6. 10.1080/00085030.2017.1281632 · doi:10.1080/00085030.2017.1281632
  7. 10.1016/j.forsciint.2016.10.001 · DOI
  8. 10.1016/j.jflm.2018.07.014 · doi:10.1016/j.jflm.2018.07.014
  9. 10.1016/j.forsciint.2017.08.032 · doi:10.1016/j.forsciint.2017.08.032
  10. 10.1259/dmfr.20170362 · DOI
  11. 10.1007/s00414-005-0530-3 · DOI · Paper page
  12. 10.1007/s00414-009-0380-5 · doi:10.1007/s00414-009-0380-5
  13. 10.1093/ejo/cjn081 · DOI
  14. 10.1111/j.1556-4029.2008.00778.x · DOI
  15. 10.1016/j.jflm.2015.11.011 · doi:10.1016/j.jflm.2015.11.011
  16. 10.1016/j.forsciint.2008.03.014 · DOI
  17. 10.1016/j.forsciint.2016.11.009 · doi:10.1016/j.forsciint.2016.11.009
  18. 10.1177/00220345730520030701 · DOI
  19. 10.1016/j.jflm.2015.09.001 · DOI
  20. 10.1016/j.jflm.2017.03.005 · doi:10.1016/j.jflm.2017.03.005
  21. capitaneanu, 2017, A systematic review of odontological sex estimation methods, J Forensic Odonto- Stomat, 35, 1
  22. tanner, 1975, Assessment of Skeletal Maturity and Prediction of Adult Height (TW2 Method), 16
  23. greulich, 1959, Radiographic Atlas of Skeletal Development of the Hand and Wrist, 2
  24. 10.1016/S1353-1131(99)90170-0 · DOI
  25. 10.1111/j.1834-7819.2002.tb00333.x · doi:10.1111/j.1834-7819.2002.tb00333.x
  26. 10.1016/S0379-0738(00)00154-7 · DOI
  27. 10.1016/j.forsciint.2006.02.019 · DOI · Paper page
  28. 10.1007/s00414-004-0489-5 · doi:10.1007/s00414-004-0489-5
  29. 10.1007/s00414-010-0515-8 · DOI · Paper page
  30. 10.1016/j.forsciint.2007.03.009 · doi:10.1016/j.forsciint.2007.03.009
  31. chollet, 2015, Keras
  32. 10.1016/j.forsciint.2007.09.001 · DOI · Paper page
  33. 10.1007/s11749-018-0611-5 · DOI
  34. 10.1142/9789812772558_0013 · DOI
  35. glorot, 2010, Understanding the difficulty of training deep feedforward neural networks, Proc 13th Int Conf Artif Intell Statist, 249
  36. ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv 1502 03167
  37. nair, 2010, Rectified linear units improve restricted Boltzmann machines, Proc 27th Int Conf Mach Learn (ICML), 807
  38. haavikko, 1970, The formation and the alveolar and clinical eruption of the permanent teeth. An orthopantomographic study, Suom Hammaslaak Toim, 66, 103
  39. 10.1002/ajpa.1330130206 · DOI · Paper page
  40. 10.1109/SIBGRAPI.2018.00058 · DOI · Paper page
  41. lewis, 1960, The relationship between tooth formation and other maturational factors, Angle Orthodontist, 30, 70
  42. demirjian, 1973, A new system of dental age assessment, Hum Biol, 45, 211
  43. 10.1080/03014467600001671 · DOI · Paper page
  44. gg, 1985, Dental maturity as an indicator of chronological age: The accuracy and precision of three methods, Eur J Orthodontics, 7, 25, 10.1093/ejo/7.1.25 · doi:10.1093/ejo/7.1.25
  45. 10.3109/00016358608997720 · DOI
  46. 10.1111/j.1600-0722.1991.tb01029.x · doi:10.1111/j.1600-0722.1991.tb01029.x
  47. 10.1016/S0379-0738(98)00034-6 · doi:10.1016/s0379-0738(98)00034-6
  48. 10.1080/00016359850142862 · DOI · Paper page
  49. 10.1016/j.media.2016.10.010 · DOI · Paper page
  50. roche, 1988, Assessing the Skeletal Maturity of the Hand-Wrist FELS Method
  51. nolla, 1960, The development of the human dentition, J Dent Child, 27, 66
  52. 10.1016/j.future.2019.01.057 · doi:10.1016/j.future.2019.01.057
  53. 10.1007/s00414-005-0047-9 · DOI
  54. haavikko, 1974, Tooth formation age estimated on a few selected teeth. A simple method for clinical use, Proc Finn Dent Soc, 70, 9
  55. 10.4258/hir.2018.24.3.236 · DOI · Paper page
  56. 10.1109/EMBC.2018.8512755 · DOI
  57. 10.1186/1472-6831-14-160 · doi:10.1186/1472-6831-14-160
  58. 10.1259/dmfr.20180051 · DOI · Paper page
  59. oktay, 2017, Tooth detection with convolutional neural networks, Proc Med Technol Nat Congr (TIPTEKNO), 1
  60. 10.1109/EMBC.2018.8512732 · DOI
  61. 10.1166/jmihi.2017.2257 · doi:10.1166/jmihi.2017.2257

Cited by

Metadata

Authors
Vila-Blanco, N., Carreira, M. J., Varas-Quintana, P., Balsa-Castro, C., & Tomas, I.
Venue
IEEE Transactions on Medical Imaging
Published
2020-07
Volume
39
Issue
7
Pages
2374-2384
ISSN
  • 0278-0062 (ISSN-L)
  • 1558-254X
OpenAlex
W3003562648
Cited by
158
References
6
FWCI
85.43
Type
journal article
Language
en
Open access
hybrid
Funders
  • Consellería de Cultura, Educación e Ordenación Universitaria (ED431G/08)
  • Potential (ED431B 2017/029)
  • Competitive Reference (ED431C 2017/69)
  • N Vila-Blanco (ED481A-2017)
  • European Regional Development Fund

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.