Korean J Orthod.  2022 Jul;52(4):287-297. 10.4041/kjod21.248.

Accuracy of artificial intelligence-assisted landmark identification in serial lateral cephalograms of Class III patients who underwent orthodontic treatment and two-jaw orthognathic surgery

• Hong M
• Kim I
• Cho JH
• Kang KH
• Kim M
• Kim SJ
• Kim YJ
• Sung SJ
• Kim YH
• Lim SH
• Kim N
• Baek SH

• KMID: 2532152
• DOI: http://doi.org/10.4041/kjod21.248

Abstract

Objective
To investigate the pattern of accuracy change in artificial intelligence-assisted landmark identification (LI) using a convolutional neural network (CNN) algorithm in serial lateral cephalograms (Lat-cephs) of Class III (C-III) patients who underwent twojaw orthognathic surgery.
Methods
A total of 3,188 Lat-cephs of C-III patients were allocated into the training and validation sets (3,004 Lat-cephs of 751 patients) and test set (184 Lat-cephs of 46 patients; subdivided into the genioplasty and non-genioplasty groups, n = 23 per group) for LI. Each C-III patient in the test set had four Lat-cephs: initial (T0), pre-surgery (T1, presence of orthodontic brackets [OBs]), post-surgery (T2, presence of OBs and surgical plates and screws [S-PS]), and debonding (T3, presence of S-PS and fixed retainers [FR]). After mean errors of 20 landmarks between human gold standard and the CNN model were calculated, statistical analysis was performed.
Results
The total mean error was 1.17 mm without significant difference among the four timepoints (T0, 1.20 mm; T1, 1.14 mm; T2, 1.18 mm; T3, 1.15 mm). In comparison of two time-points ([T0, T1] vs. [T2, T3]), ANS, A point, and B point showed an increase in error (p < 0.01, 0.05, 0.01, respectively), while Mx6D and Md6D showeda decrease in error (all p < 0.01). No difference in errors existed at B point, Pogonion, Menton, Md1C, and Md1R between the genioplasty and non-genioplasty groups.
Conclusions
The CNN model can be used for LI in serial Lat-cephs despite the presence of OB, S-PS, FR, genioplasty, and bone remodeling.

Keyword

Convolutional neural network; Landmark identification; Two-jaw orthognathic surgery; Serial lateral encephalogram

Figure

• 

  Figure 1 Composition of the test set. T0, initial.

• 

  Figure 2 General schematic of the cascade convolution neural network algorithm for artificial intelligence-assisted landmark identification.

• 

  Figure 3 The skeletal and dental landmarks. See Table 2 for definitions of the other landmarks.

Reference

1. Im DH, Kim TW, Nahm DS, Chang YI. 2003; Current trends in orthodontic patients in Seoul National University Dental Hospital. Korean J Orthod. 33:63–72.

2. Piao Y, Kim SJ, Yu HS, Cha JY, Baik HS. 2016; Five-year investigation of a large orthodontic patient population at a dental hospital in South Korea. Korean J Orthod. 46:137–45. DOI: 10.4041/kjod.2016.46.3.137. PMID: 27226959. PMCID: PMC4879316. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84969750108&origin=inward.

3. Nielsen IL. 1989; Maxillary superimposition: a comparison of three methods for cephalometric evaluation of growth and treatment change. Am J Orthod Dentofacial Orthop. 95:422–31. DOI: 10.1016/0889-5406(89)90304-1. PMID: 2718972. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=0024671043&origin=inward.

4. Johnston C, Burden D, Kennedy D, Harradine N, Stevenson M. 2006; Class III surgical-orthodontic treatment: a cephalometric study. Am J Orthod Dentofacial Orthop. 130:300–9. DOI: 10.1016/j.ajodo.2005.01.023. PMID: 16979487. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=33748472099&origin=inward.

5. Hutton TJ, Cunningham S, Hammond P. 2000; An evaluation of active shape models for the automatic identification of cephalometric landmarks. Eur J Orthod. 22:499–508. DOI: 10.1093/ejo/22.5.499. PMID: 11105406. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=0034293430&origin=inward.

6. Leonardi R, Giordano D, Maiorana F, Spampinato C. 2008; Automatic cephalometric analysis. Angle Orthod. 78:145–51. DOI: 10.2319/120506-491.1. PMID: 18193970. PMCID: PMC8165048. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=38349065440&origin=inward.

7. Leonardi R, Giordano D, Maiorana F. 2009; An evaluation of cellular neural networks for the automatic identification of cephalometric landmarks on digital images. J Biomed Biotechnol. 2009:717102. DOI: 10.1155/2009/717102. PMID: 19753320. PMCID: PMC2742650. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=70349233924&origin=inward.

8. Arık SÖ, Ibragimov B, Xing L. 2017; Fully automated quantitative cephalometry using convolutional neural networks. J Med Imaging (Bellingham). 4:014501. DOI: 10.1117/1.JMI.4.1.014501. PMID: 28097213. PMCID: PMC5220585. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85009516223&origin=inward.

9. Lee JH, Yu HJ, Kim MJ, Kim JW, Choi J. 2020; Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networks. BMC Oral Health. 20:270. DOI: 10.1186/s12903-020-01256-7. PMID: 33028287. PMCID: PMC7541217. PMID: afefdf9724c3499f8ceb3b2da99bc7dc. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85092450683&origin=inward.

10. Vandaele R, Aceto J, Muller M, Péronnet F, Debat V, Wang CW, et al. 2018; Landmark detection in 2D bioimages for geometric morphometrics: a multi-resolution tree-based approach. Sci Rep. 8:538. DOI: 10.1038/s41598-017-18993-5. PMID: 29323201. PMCID: PMC5765108. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85040459251&origin=inward.

11. Khanagar SB, Al-Ehaideb A, Vishwanathaiah S, Maganur PC, Patil S, Naik S, et al. 2021; Scope and performance of artificial intelligence technology in orthodontic diagnosis, treatment planning, and clinical decision-making - a systematic review. J Dent Sci. 16:482–92. DOI: 10.1016/j.jds.2020.05.022. PMID: 33384838. PMCID: PMC7770284. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85085929984&origin=inward.

12. Kim J, Kim I, Kim YJ, Kim M, Cho JH, Hong M, et al. 2021; Accuracy of automated identification of lateral cephalometric landmarks using cascade convolutional neural networks on lateral cephalograms from nationwide multi-centres. Orthod Craniofac Res. 24 Suppl 2:59–67. DOI: 10.1111/ocr.12493. PMID: 33973341. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85121947432&origin=inward.

13. Wang CW, Huang CT, Hsieh MC, Li CH, Chang SW, Li WC, et al. 2015; Evaluation and comparison of anatomical landmark detection methods for cephalometric X-ray images: a grand challenge. IEEE Trans Med Imaging. 34:1890–900. DOI: 10.1109/TMI.2015.2412951. PMID: 25794388. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84940910741&origin=inward.

14. Wang CW, Huang CT, Lee JH, Li CH, Chang SW, Siao MJ, et al. 2016; A benchmark for comparison of dental radiography analysis algorithms. Med Image Anal. 31:63–76. DOI: 10.1016/j.media.2016.02.004. PMID: 26974042. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84960353898&origin=inward.

15. Hwang HW, Park JH, Moon JH, Yu Y, Kim H, Her SB, et al. 2020; Automated identification of cephalometric landmarks: part 2-Might it be better than human? Angle Orthod. 90:69–76. DOI: 10.2319/022019-129.1. PMID: 31335162. PMCID: PMC8087057. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85077404522&origin=inward.

16. Lin TY, Goyal P, Girshick R, He K, Dollar P. 2020; Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell. 42:318–27. DOI: 10.1109/TPAMI.2018.2858826. PMID: 30040631. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85050389019&origin=inward.

17. Ronneberger O, Fischer P, Brox T. 2015. U-Net: convolutional networks for biomedical image segmentation. arXiv. 04597 [Preprint]. Available from: https://doi.org/10.48550/arXiv.1505.04597. cited 2020 Dec 15.

18. Roden-Johnson D, English J, Gallerano R. 2008; Comparison of hand-traced and computerized cephalograms: landmark identification, measurement, and superimposition accuracy. Am J Orthod Dentofacial Orthop. 133:556–64. DOI: 10.1016/j.ajodo.2006.03.041. PMID: 18405820. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=41649110231&origin=inward.

19. Ohba S, Nakao N, Nakatani Y, Yoshimura H, Minamizato T, Kawasaki T, et al. 2015; Effects of vertical movement of the anterior nasal spine on the maxillary stability after Le Fort I osteotomy for pitch correction. J Craniofac Surg. 26:e481–5. DOI: 10.1097/SCS.0000000000001968. PMID: 26267571. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84941763229&origin=inward.

20. Venkategowda PR, Prakash AT, Roy ET, Shetty KS, Thakkar S, Maurya R. 2017; Stability of vertical, horizontal and angular parameters following superior repositioning of maxilla by Le Fort I osteotomy: a cephalometric study. J Clin Diagn Res. 11:ZC10–4. DOI: 10.7860/JCDR/2017/22455.9133. PMID: 28274035. PMCID: PMC5324480. PMID: 48282d71af1641a99b0939efaf551007. PMID: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85008657214&origin=inward.