Can Artificial Intelligence-driven Cephalometric Analysis Replace Manual Tracing? A Systematic Review and Meta-analysis

Overview

Journal Eur J Orthod

Publisher Oxford University Press

Specialty Dentistry

Date 2024 Jun 19

PMID 38895901

Authors

Julie Hendrickx

Rellyca Sola Gracea

Michiel Vanheers

Nicolas Winderickx

Flavia Preda

Sohaib Shujaat

Reinhilde Jacobs

Affiliations

Soon will be listed here.

Abstract

Objectives: This systematic review and meta-analysis aimed to investigate the accuracy and efficiency of artificial intelligence (AI)-driven automated landmark detection for cephalometric analysis on two-dimensional (2D) lateral cephalograms and three-dimensional (3D) cone-beam computed tomographic (CBCT) images.

Search Methods: An electronic search was conducted in the following databases: PubMed, Web of Science, Embase, and grey literature with search timeline extending up to January 2024.

Selection Criteria: Studies that employed AI for 2D or 3D cephalometric landmark detection were included.

Data Collection And Analysis: The selection of studies, data extraction, and quality assessment of the included studies were performed independently by two reviewers. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. A meta-analysis was conducted to evaluate the accuracy of the 2D landmarks identification based on both mean radial error and standard error.

Results: Following the removal of duplicates, title and abstract screening, and full-text reading, 34 publications were selected. Amongst these, 27 studies evaluated the accuracy of AI-driven automated landmarking on 2D lateral cephalograms, while 7 studies involved 3D-CBCT images. A meta-analysis, based on the success detection rate of landmark placement on 2D images, revealed that the error was below the clinically acceptable threshold of 2 mm (1.39 mm; 95% confidence interval: 0.85-1.92 mm). For 3D images, meta-analysis could not be conducted due to significant heterogeneity amongst the study designs. However, qualitative synthesis indicated that the mean error of landmark detection on 3D images ranged from 1.0 to 5.8 mm. Both automated 2D and 3D landmarking proved to be time-efficient, taking less than 1 min. Most studies exhibited a high risk of bias in data selection (n = 27) and reference standard (n = 29).

Conclusion: The performance of AI-driven cephalometric landmark detection on both 2D cephalograms and 3D-CBCT images showed potential in terms of accuracy and time efficiency. However, the generalizability and robustness of these AI systems could benefit from further improvement.

Registration: PROSPERO: CRD42022328800.

Citing Articles

Reliability and accuracy of Artificial intelligence-based software for cephalometric diagnosis. A diagnostic study.

Mercier J, Rossi C, Sanchez I, Renovales I, Sahagun P, Templier L BMC Oral Health. 2024; 24(1):1309.

PMID: 39468520 PMC: 11520516. DOI: 10.1186/s12903-024-05097-6.

Utilization of a Cortical Xenogeneic Membrane for Guided Bone Regeneration: A Retrospective Case Series.

Debortoli C, Falguiere A, Campana F, Catherine J, Tardivo D, Lan R J Clin Med. 2024; 13(15).

PMID: 39124840 PMC: 11312857. DOI: 10.3390/jcm13154575.

References

Zeng M, Yan Z, Liu S, Zhou Y, Qiu L . Cascaded convolutional networks for automatic cephalometric landmark detection. Med Image Anal. 2020; 68:101904. DOI: 10.1016/j.media.2020.101904. View

Lagravere M, Low C, Flores-Mir C, Chung R, Carey J, Heo G . Intraexaminer and interexaminer reliabilities of landmark identification on digitized lateral cephalograms and formatted 3-dimensional cone-beam computerized tomography images. Am J Orthod Dentofacial Orthop. 2010; 137(5):598-604. DOI: 10.1016/j.ajodo.2008.07.018. View

Yang S, Song E, Lee E, Kang S, Yi W, Lee S . Ceph-Net: automatic detection of cephalometric landmarks on scanned lateral cephalograms from children and adolescents using an attention-based stacked regression network. BMC Oral Health. 2023; 23(1):803. PMC: 10604948. DOI: 10.1186/s12903-023-03452-7. View

Kim H, Shim E, Park J, Kim Y, Lee U, Kim Y . Web-based fully automated cephalometric analysis by deep learning. Comput Methods Programs Biomed. 2020; 194:105513. DOI: 10.1016/j.cmpb.2020.105513. View

Wang C, Huang C, Lee J, Li C, Chang S, Siao M . A benchmark for comparison of dental radiography analysis algorithms. Med Image Anal. 2016; 31:63-76. DOI: 10.1016/j.media.2016.02.004. View

Chen Y, Chen S, Huang H, Yao C, Chang H . Reliability of landmark identification in cephalometric radiography acquired by a storage phosphor imaging system. Dentomaxillofac Radiol. 2004; 33(5):301-6. DOI: 10.1259/dmfr/85147715. View

Huang Y, Fan F, Syben C, Roser P, Mill L, Maier A . Cephalogram synthesis and landmark detection in dental cone-beam CT systems. Med Image Anal. 2021; 70:102028. DOI: 10.1016/j.media.2021.102028. View

Lang Y, Lian C, Xiao D, Deng H, Thung K, Yuan P . Localization of Craniomaxillofacial Landmarks on CBCT Images Using 3D Mask R-CNN and Local Dependency Learning. IEEE Trans Med Imaging. 2022; 41(10):2856-2866. PMC: 9673501. DOI: 10.1109/TMI.2022.3174513. View

Schwendicke F, Chaurasia A, Arsiwala L, Lee J, Elhennawy K, Jost-Brinkmann P . Deep learning for cephalometric landmark detection: systematic review and meta-analysis. Clin Oral Investig. 2021; 25(7):4299-4309. PMC: 8310492. DOI: 10.1007/s00784-021-03990-w. View

10.

Tanikawa C, Lee C, Lim J, Oka A, Yamashiro T . Clinical applicability of automated cephalometric landmark identification: Part I-Patient-related identification errors. Orthod Craniofac Res. 2021; 24 Suppl 2:43-52. DOI: 10.1111/ocr.12501. View

11.

Le V, Kang J, Oh I, Kim J, Yang Y, Lee D . Effectiveness of Human-Artificial Intelligence Collaboration in Cephalometric Landmark Detection. J Pers Med. 2022; 12(3). PMC: 8954049. DOI: 10.3390/jpm12030387. View

12.

Hong W, Kim S, Choi J, Ahn J, Paeng J, Kim H . Automated Cephalometric Landmark Detection Using Deep Reinforcement Learning. J Craniofac Surg. 2023; 34(8):2336-2342. DOI: 10.1097/SCS.0000000000009685. View

13.

Hwang H, Moon J, Kim M, Donatelli R, Lee S . Evaluation of automated cephalometric analysis based on the latest deep learning method. Angle Orthod. 2021; 91(3):329-335. PMC: 8084461. DOI: 10.2319/021220-100.1. View

14.

Renard F, Guedria S, Palma N, Vuillerme N . Variability and reproducibility in deep learning for medical image segmentation. Sci Rep. 2020; 10(1):13724. PMC: 7426407. DOI: 10.1038/s41598-020-69920-0. View

15.

Ye H, Cheng Z, Ungvijanpunya N, Chen W, Cao L, Gou Y . Is automatic cephalometric software using artificial intelligence better than orthodontist experts in landmark identification?. BMC Oral Health. 2023; 23(1):467. PMC: 10329795. DOI: 10.1186/s12903-023-03188-4. View

16.

Schwendicke F, Krois J . Better Reporting of Studies on Artificial Intelligence: CONSORT-AI and Beyond. J Dent Res. 2021; 100(7):677-680. PMC: 8217901. DOI: 10.1177/0022034521998337. View

17.

Yun H, Hyun C, Baek S, Lee S, Seo J . A semi-supervised learning approach for automated 3D cephalometric landmark identification using computed tomography. PLoS One. 2022; 17(9):e0275114. PMC: 9518928. DOI: 10.1371/journal.pone.0275114. View

18.

Ma Q, Kobayashi E, Fan B, Nakagawa K, Sakuma I, Masamune K . Automatic 3D landmarking model using patch-based deep neural networks for CT image of oral and maxillofacial surgery. Int J Med Robot. 2020; 16(3):e2093. DOI: 10.1002/rcs.2093. View

19.

Noothout J, de Vos B, Wolterink J, Postma E, Smeets P, Takx R . Deep Learning-Based Regression and Classification for Automatic Landmark Localization in Medical Images. IEEE Trans Med Imaging. 2020; 39(12):4011-4022. DOI: 10.1109/TMI.2020.3009002. View

20.

Nalcaci R, Ozturk F, Sokucu O . A comparison of two-dimensional radiography and three-dimensional computed tomography in angular cephalometric measurements. Dentomaxillofac Radiol. 2010; 39(2):100-6. PMC: 3520203. DOI: 10.1259/dmfr/82724776. View