How to categorize a panoramic images database for automatically detection of dental treatments

  1. María Prados Privado 12
  2. Javier García Villalón 2
  3. Rosa Rojo López 23
  4. Antonio Blázquez Torres 2
  5. Carlos Hugo Martínez Martínez 2
  6. Carlos Ivorra Server 2
  1. 1 Universidad de Alcalá

    Universidad de Alcalá

    Alcalá de Henares, España


  2. 2 Asisa Dental. Research Department, Madrid, Spain
  3. 3 Department of Dentistry, Faculty of Health Sciences, Alfonso X el Sabio University, Madrid, España
Academic Journal of Health Sciences: Medicina Balear

ISSN: 2255-0560

Year of publication: 2023

Volume: 38

Issue: 2

Pages: 73-77

Type: Article

DOI: 10.3306/AJHS.2023.38.02.73 DIALNET GOOGLE SCHOLAR lock_openIbdigital editor


Cited by

  • Web of Science Cited by: 0 (30-05-2023)


Objectives: The objective is to provide a methodology to obtain a categorized database without segmentation by sex or age that can be used in dental object detection applications and that may help in the diagnosis and usual clinical practice. Methods: A total of 10,677 panoramic images were analyzed by four examiners. In each tooth, the examiner indicated if the tooth exists or not and the position on FDI notation. After that, and for each tooth that exists, the examiner detailed whether or not there were the variables analyzed. Those variables were filled teeth, crown, implant, endodontic treatment, caries, and prosthetic. A descriptive study of inter-observer and intra-observer concordance-consistency was performed. Results: The results were statistically significant. Both teams obtained for all variables an almost perfect concordance k = 0.9 except in filled teeth where the kappa was k=0.8 and caries where a moderate agreement was obtained. The intra-examiner agreement was poor in caries variable and almost perfect in the rest of variables. Conclusions: A correctly categorized database is essential to obtain correct results in applications with artificial intelligence and neural networks. This study shows how to categorize a database of dental images for use in object detection applications in the field of dentistry.

Bibliographic References

  • Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019 Jan 7;25(1):44-56.
  • Hackbarth AD. Eliminating Waste in US Health Care. JAMA. 2012 Apr 11;307(14):1513.
  • Lin PL, Lai YH, Huang PW. An effective classification and numbering system for dental bitewing radiographs using teeth region and contour information. Pattern Recognit. 2010 Apr;43(4):1380-92.
  • Miki Y, Muramatsu C, Hayashi T, Zhou X, Hara T, Katsumata A, et al. Classification of teeth in cone-beam CT using deep convolutional neural network. Comput Biol Med. 2017 Jan;80:24-9.
  • Kukafka R. Digital Health Consumers on the Road to the Future. J Med Internet Res. 2019 Nov 21;21(11):e16359.
  • Chen KJ, Gao SS, Duangthip D, Lo ECM, Chu CH. Prevalence of early childhood caries among 5-year-old children: A systematic review. J Investig Clin Dent. 2019 Feb;10(1):e12376.
  • Wenzel A. Dental caries. In: Oral radiology Principles and Interpretation. St. Louis: Elsevier Mosby; 2014. p. 285-98.
  • Thomas MF, Ricketts DN, Wilson RF. Occlusal Caries Diagnosis in Molar teeth from Bitewing and Panoramic Radiographs. Prim Dent Care. 2001 Apr 1;8(2):63-9.
  • Pakbaznejad Esmaeili E, Pakkala T, Haukka J, Siukosaari P. Low reproducibility between oral radiologists and general dentists with regards to radiographic diagnosis of caries. Acta Odontol Scand [Internet]. 2018 Jul 4;76(5):346–50. Available from:
  • Akarslan ZZ, Akdevelioğlu M, Güngör K, Erten H. A comparison of the diagnostic accuracy of bitewing, periapical, unfiltered and filtered digital panoramic images for approximal caries detection in posterior teeth. Dentomaxillofacial Radiol. 2008 Dec;37(8):458-63.
  • Diniz MB, Rodrigues JA, Neuhaus KW, Cordeiro RCL, Lussi A. Influence of examiner’s clinical experience on the reproducibility and accuracy of radiographic examination in detecting occlusal caries. Clin Oral Investig. 2010 Oct 8;14(5):515-23.
  • Landis JR, Koch GG. The Measurement of Observer Agreement for Categorical Data. Biometrics. 1977 Mar;33(1):159.
  • Bulman JS, Osborn JF. Measuring diagnostic consistency. Br Dent J. 1989 May 20;166(10):377-81.
  • Wang C-W, Huang C-T, Lee J-H, Li C-H, Chang S-W, Siao M-J, et al. A benchmark for comparison of dental radiography analysis algorithms. Med Image Anal. 2016 Jul;31:63-76.
  • Valachovic RW, Douglass CW, Berkey CS, McNeil BJ, Chauncey HH. Examiner Reliability in Dental Radiography. J Dent Res. 1986 Mar 8;65(3):432-6.
  • Fortes JH, de Oliveira-Santos C, Matsumoto W, da Motta RJG, Tirapelli C. Influence of 2D vs 3D imaging and professional experience on dental implant treatment planning. Clin Oral Investig. 2019 Feb 16;23(2):929-36.
  • Francio LA, Silva FE, Valerio CS, Cardoso CA e A, Jansen WC, Manzi FR. Accuracy of various imaging methods for detecting misfit at the tooth-restoration interface in posterior teeth. Imaging Sci Dent. 2018;48(2):87.
  • Kamburoğlu K, Kolsuz E, Murat S, Yüksel S, Özen T. Proximal caries detection accuracy using intraoral bitewing radiography, extraoral bitewing radiography and panoramic radiography. Dentomaxillofacial Radiol. 2012 Sep;41(6):450-9.