The korean journal of orthodontics (대한치과교정학회지)

The Korean Association Of Orthodontists (대한치과교정학회)
권호 표지
DOI QR코드

DOI QR Code

Evaluation of a multi-stage convolutional neural network-based fully automated landmark identification system using cone-beam computed tomography-synthesized posteroanterior cephalometric images

  • Kim, Min-Jung (Department of Orthodontics, Graduate School, Kyung Hee University) ;
  • Liu, Yi (Department of Orthodontics, Peking University School of Stomatology) ;
  • Oh, Song Hee (Department of Oral and Maxillofacial Radiology, Graduate School, Kyung Hee University) ;
  • Ahn, Hyo-Won (Department of Orthodontics, Graduate School, Kyung Hee University) ;
  • Kim, Seong-Hun (Department of Orthodontics, Graduate School, Kyung Hee University) ;
  • Nelson, Gerald (Division of Orthodontics, Department of Orofacial Science, University of California San Francisco)
  • Received : 2020.09.08
  • Accepted : 2020.10.07
  • Published : 2021.03.25
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: To evaluate the accuracy of a multi-stage convolutional neural network (CNN) model-based automated identification system for posteroanterior (PA) cephalometric landmarks. Methods: The multi-stage CNN model was implemented with a personal computer. A total of 430 PA-cephalograms synthesized from cone-beam computed tomography scans (CBCT-PA) were selected as samples. Twenty-three landmarks used for Tweemac analysis were manually identified on all CBCT-PA images by a single examiner. Intra-examiner reproducibility was confirmed by repeating the identification on 85 randomly selected images, which were subsequently set as test data, with a two-week interval before training. For initial learning stage of the multi-stage CNN model, the data from 345 of 430 CBCT-PA images were used, after which the multi-stage CNN model was tested with previous 85 images. The first manual identification on these 85 images was set as a truth ground. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the errors in manual identification and artificial intelligence (AI) prediction. Results: The AI showed an average MRE of 2.23 ± 2.02 mm with an SDR of 60.88% for errors of 2 mm or lower. However, in a comparison of the repetitive task, the AI predicted landmarks at the same position, while the MRE for the repeated manual identification was 1.31 ± 0.94 mm. Conclusions: Automated identification for CBCT-synthesized PA cephalometric landmarks did not sufficiently achieve the clinically favorable error range of less than 2 mm. However, AI landmark identification on PA cephalograms showed better consistency than manual identification.

Keywords

References

  1. Major PW, Johnson DE, Hesse KL, Glover KE. Landmark identification error in posterior anterior cephalometrics. Angle Orthod 1994;64:447-54.
  2. Ulkur F, Ozdemir F, Germec-Cakan D, Kaspar EC. Landmark errors on posteroanterior cephalograms. Am J Orthod Dentofacial Orthop 2016;150:324-31. https://doi.org/10.1016/j.ajodo.2016.01.016
  3. Na ER, Aljawad H, Lee KM, Hwang HS. A comparative study of the reproducibility of landmark identification on posteroanterior and anteroposterior cephalograms generated from cone-beam computed tomography scans. Korean J Orthod 2019;49:41-8. https://doi.org/10.4041/kjod.2019.49.1.41
  4. Sicurezza E, Greco M, Giordano D, Maiorana F, Leonardi R. Accuracy of landmark identification on postero-anterior cephalograms. Prog Orthod 2012;13:132-40. https://doi.org/10.1016/j.pio.2011.10.003
  5. Pirttiniemi P, Miettinen J, Kantomaa T. Combined effects of errors in frontal-view asymmetry diagnosis. Eur J Orthod 1996;18:629-36. https://doi.org/10.1093/ejo/18.1.629
  6. Major PW, Johnson DE, Hesse KL, Glover KE. Effect of head orientation on posterior anterior cephalometric landmark identification. Angle Orthod 1996;66:51-60.
  7. Smektala T, Jedrzejewski M, Szyndel J, Sporniak-Tutak K, Olszewski R. Experimental and clinical assessment of three-dimensional cephalometry: a systematic review. J Craniomaxillofac Surg 2014;42:1795-801. https://doi.org/10.1016/j.jcms.2014.06.017
  8. Kamoen A, Dermaut L, Verbeeck R. The clinical significance of error measurement in the interpretation of treatment results. Eur J Orthod 2001;23:569-78. https://doi.org/10.1093/ejo/23.5.569
  9. Gribel BF, Gribel MN, Frazao DC, McNamara JA Jr, Manzi FR. Accuracy and reliability of craniometric measurements on lateral cephalometry and 3D measurements on CBCT scans. Angle Orthod 2011;81:26-35. https://doi.org/10.2319/032210-166.1
  10. Gribel BF, Gribel MN, Manzi FR, Brooks SL, McNamara JA Jr. From 2D to 3D: an algorithm to derive normal values for 3-dimensional computerized assessment. Angle Orthod 2011;81:3-10. https://doi.org/10.2319/032910-173.1
  11. Meiyappan N, Tamizharasi S, Senthilkumar KP, Janardhanan K. Natural head position: an overview. J Pharm Bioallied Sci 2015;7(Suppl 2):S424-7.
  12. El-Mangoury NH, Shaheen SI, Mostafa YA. Landmark identification in computerized posteroanterior cephalometrics. Am J Orthod Dentofacial Orthop 1987;91:57-61. https://doi.org/10.1016/0889-5406(87)90209-5
  13. Leonardi R, Annunziata A, Caltabiano M. Landmark identification error in posteroanterior cephalometric radiography. A systematic review. Angle Orthod 2008;784:761-5.
  14. Shokri A, Miresmaeili A, Farhadian N, Falah-Kooshki S, Amini P, Mollaie N. Effect of changing the head position on accuracy of transverse measurements of the maxillofacial region made on cone beam computed tomography and conventional posterioranterior cephalograms. Dentomaxillofac Radiol 2017;46:20160180. https://doi.org/10.1259/dmfr.20160180
  15. Oshagh M, Shahidi SH, Danaei SH. Effects of image enhancement on reliability of landmark identification in digital cephalometry. Indian J Dent Res 2013;24:98-103. https://doi.org/10.4103/0970-9290.114958
  16. Arik SO, Ibragimov B, Xing L. Fully automated quantitative cephalometry using convolutional neural networks. J Med Imaging (Bellingham) 2017; 4:014501. https://doi.org/10.1117/1.JMI.4.1.014501
  17. Park JH, Hwang HW, Moon JH, Yu Y, Kim H, Her SB, et al. Automated identification of cephalometric landmarks: part 1-comparisons between the latest deep-learning methods YOLOV3 and SSD. Angle Orthod 2019;89:903-9. https://doi.org/10.2319/022019-127.1
  18. Hwang HW, Park JH, Moon JH, Yu Y, Kim H, Her SB, et al. Automated identification of cephalometric landmarks: part 2-might it be better than human? Angle Orthod 2019;90:69-76.
  19. Takahashi R, Matsubara T, Uehara K. Multi-stage convolutional neural networks for robustness to scale transformation. Paper presented at: 2017 International Symposium on Nonlinear Theory and Its Applications; 2017 Dec 4-7; Cancun, Mexico. Cancun: NOLTA, 2017. p. 692-5.
  20. Anwar SM, Majid M, Qayyum A, Awais M, Alnowami M, Khan MK. Medical image analysis using convolutional neural networks: a review. J Med Syst 2018;42:226. https://doi.org/10.1007/s10916-018-1088-1
  21. Yadav SS, Jadhav SM. Deep convolutional neural network based medical image classification for disease diagnosis. J Big Data 2019;6:113. https://doi.org/10.1186/s40537-019-0276-2
  22. Schwendicke F, Golla T, Dreher M, Krois J. Convolutional neural networks for dental image diagnostics: a scoping review. J Dent 2019;91:103226. https://doi.org/10.1016/j.jdent.2019.103226
  23. Park JJ, Kim KA, Nam Y, Choi MH, Choi SY, Rhie J. Convolutional-neural-network-based diagnosis of appendicitis via CT scans in patients with acute abdominal pain presenting in the emergency department. Sci Rep 2020;10:9556. https://doi.org/10.1038/s41598-020-66674-7