Skip to main content
Erschienen in:

04.03.2021 | Original Article

Accurate age classification using manual method and deep convolutional neural network based on orthopantomogram images

verfasst von: Yu-cheng Guo, Mengqi Han, Yuting Chi, Hong Long, Dong Zhang, Jing Yang, Yang Yang, Teng Chen, Shaoyi Du

Erschienen in: International Journal of Legal Medicine | Ausgabe 4/2021

Einloggen, um Zugang zu erhalten

Abstract

Age estimation is an important challenge in many fields, including immigrant identification, legal requirements, and clinical treatments. Deep learning techniques have been applied for age estimation recently but lacking performance comparison between manual and machine learning methods based on a large sample of dental orthopantomograms (OPGs). In total, we collected 10,257 orthopantomograms for the study. We derived logistic regression linear models for each legal age threshold (14, 16, and 18 years old) for manual method and developed the end-to-end convolutional neural network (CNN) which classified the dental age directly to compare with the manual method. Both methods are based on left mandibular eight permanent teeth or the third molar separately. Our results show that compared with the manual methods (92.5%, 91.3%, and 91.8% for age thresholds of 14, 16, and 18, respectively), the end-to-end CNN models perform better (95.9%, 95.4%, and 92.3% for age thresholds of 14, 16, and 18, respectively). This work proves that CNN models can surpass humans in age classification, and the features extracted by machines may be different from that defined by human.
Literatur
3.
Zurück zum Zitat Thevissen PW, Kvaal SI, Willems G (2012) Ethics in age estimation of unaccompanied minors. J Forensic Odontostomatol 30(Suppl 1):84–102PubMed Thevissen PW, Kvaal SI, Willems G (2012) Ethics in age estimation of unaccompanied minors. J Forensic Odontostomatol 30(Suppl 1):84–102PubMed
8.
Zurück zum Zitat Lengfu Z (2006) On minors’ civil liability ability. J Shangluo Teach Coll 20:59–63 Lengfu Z (2006) On minors’ civil liability ability. J Shangluo Teach Coll 20:59–63
10.
Zurück zum Zitat Mincer HH, Harris EF, Berryman HE (1993) The A.B.F.O. study of third molar development and its use as an estimator of chronological age. J Forensic Sci 38:379–390CrossRefPubMed Mincer HH, Harris EF, Berryman HE (1993) The A.B.F.O. study of third molar development and its use as an estimator of chronological age. J Forensic Sci 38:379–390CrossRefPubMed
14.
Zurück zum Zitat Cameriere R, Velandia Palacio LA, Pinares J, Bestetti F, Paba R, Coccia E, Ferrante L (2018) Assessment of second (I2M) and third (I3M) molar indices for establishing 14 and 16 legal ages and validation of the Cameriere’s I3M cut-off for 18 years old in Chilean population. Forensic Sci Int 285(205):e1–e5. https://doi.org/10.1016/j.forsciint.2017.12.043CrossRef Cameriere R, Velandia Palacio LA, Pinares J, Bestetti F, Paba R, Coccia E, Ferrante L (2018) Assessment of second (I2M) and third (I3M) molar indices for establishing 14 and 16 legal ages and validation of the Cameriere’s I3M cut-off for 18 years old in Chilean population. Forensic Sci Int 285(205):e1–e5. https://​doi.​org/​10.​1016/​j.​forsciint.​2017.​12.​043CrossRef
24.
Zurück zum Zitat Demirjian A, Goldstein H, Tanner JM (1973) A new system of dental age assessment. Hum Biol 45:211–227PubMed Demirjian A, Goldstein H, Tanner JM (1973) A new system of dental age assessment. Hum Biol 45:211–227PubMed
25.
Zurück zum Zitat Tan M, Le QV (2019) Efficientnet: rethinking model scaling for convolutional neural networks. arXiv:1905.11946 Tan M, Le QV (2019) Efficientnet: rethinking model scaling for convolutional neural networks. arXiv:1905.11946
32.
Zurück zum Zitat Yin W , Kann K , Yu M, Schutze H (2017) Comparative study of CNN and RNN for natural language processing. arXiv:1702.01923 Yin W , Kann K , Yu M,  Schutze H (2017) Comparative study of CNN and RNN for natural language processing. arXiv:1702.01923
Metadaten
Titel
Accurate age classification using manual method and deep convolutional neural network based on orthopantomogram images
verfasst von
Yu-cheng Guo
Mengqi Han
Yuting Chi
Hong Long
Dong Zhang
Jing Yang
Yang Yang
Teng Chen
Shaoyi Du
Publikationsdatum
04.03.2021
Verlag
Springer Berlin Heidelberg
Erschienen in
International Journal of Legal Medicine / Ausgabe 4/2021
Print ISSN: 0937-9827
Elektronische ISSN: 1437-1596
DOI
https://doi.org/10.1007/s00414-021-02542-x

Neu im Fachgebiet Rechtsmedizin

Pathologie der Milz

Nach einer Beschreibung der Milzanatomie und Darstellung der diagnostisch wichtigsten immunhistochemischen Färbungen zur Identifizierung der normalen Milzkompartimente werden am Beispiel eines nordafrikanischen Patienten mit rezentem …

Molekular definierte Nierenzellkarzinome 2025

Im Zuge der Überarbeitung der WHO-Klassifikation im Jahr 2022 konnten für mehrere Nierenzellkarzinome (NZK), die sich zuvor nicht eindeutig den bis dahin definierten Tumortypen zuordnen ließen, jedoch gemeinsame morphologische und molekulare …

Wichtige Änderungen in der WHO-Klassifikation der Hodentumoren 2022

In der 5. Auflage der „WHO-Klassifikation der Tumoren der ableitenden Harnwege und des männlichen Genitaltrakts“ sind bedeutende Anpassungen an den bisherigen Klassifikationen vorgenommen worden. Diese betreffen bei den Keimzelltumoren des Hodens …

DNA mixture deconvolution using fully continuous models EuroForMix and EFMrep

  • Open Access
  • Originalien

Mixture deconvolution is a powerful tool for inferring individual DNA profiles from DNA mixtures for subsequent transmission to a database or database queries. To carry out deconvolution, a mixed trace can be interpreted either manually by an …