Verification of Convolutional Neural Network Cephalometric Landmark Identification
Source abstract
Abstract
Introduction: The mass-harvesting of digitized medical data has prompted their use as a clinical and research tool. The purpose of this study was to compare the accuracy and reliability of artificial intelligence derived cephalometric landmark identification with that of human observers. Methods: Ten pre-treatment digital lateral cephalometric radiographs were randomly selected from a university post-graduate clinic. The x- and y-coordinates of 21 (i.e., 42 points) hard and soft tissue landmarks were identified by 6 specialists, 19 residents, 4 imaging technicians, and a commercially available convolutional neural network artificial intelligence platform (CephX, Orca Dental, Hertzylia, Israel). Wilcoxon, Spearman and Bartlett tests were performed to compare agreement of human and AI landmark identification. Results: Six x- or y-coordinates (14.28%) were found to be statistically different, with only one being outside the 2 mm range of acceptable error, and with 97.6% of coordinates found to be within this range. Conclusions: The use of convolutional neural network artificial intelligence as a tool for cephalometric landmark identification was found to be highly accurate and can serve as an aid in orthodontic diagnosis.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Dental Radiography and Imaging · Orthodontics and Dentofacial Orthopedics · Forensic Anthropology and Bioarchaeology Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Orthodontics, Maurice and Gabriella Goldschlager School of Dental Medicine, Tel Aviv University, Tel Aviv 6997801, Israel
Department of Oral Pathology, Oral Medicine, and Maxillofacial Imaging, Sackler Faculty of Medicine, Maurice and Gabriella Goldschlager School of Dental Medicine, Tel Aviv University, Tel Aviv 6997801, Israel
Department of Oral Rehabilitation, The Goldschleger School of Dental Medicine, Sackler Faculty of Medicine, Tel Aviv 6997801, Israel
References (66)
Show source-provided references
1. Irwin, J.O. (1998). Biometric method, past, present, and future. Historical Anthropometrics, Ashgate.
2. Wilhelm Conrad Röntgen and the discovery of X-rays
3. History of X-ray in dentistry
4. A new X-ray technique and its application to orthodontia
5. Development of the norm concept in orthodontics
6. Cephalometric appraisal of orthodontic results
7. Variations in facial relationship10.1016/0002-9416(48)90015-3 ↗
8. Cephalometrics for you and me10.1016/0002-9416(53)90082-7 ↗
9. The Frankfort-Mandibular Incisor Angle (FMIA) In Orthodontic Diagnosis, Treatment Planning and Prognosis
10. A roentgenographic cephalometric analysis of cephalo-facio-dental relationships10.1016/0002-9416(55)90171-8 ↗
11. Broadbent, B.H., Broadbent, B.H., and Golden, W.H. (1975). Bolton Standards of Dentofacial Developmental Growth, C. V. Mosby.
12. The mesh diagram and cephalometrics
13. Prediction of mandibular growth rotation10.1016/0002-9416(69)90036-0 ↗
14. Jarabak, J.R., and Fizzell, J.A. (1972). Technique and Treatment with Light-Wire Edgewise Appliance, The C. V. Mosby Company. [2nd ed.].
15. The Wits appraisal of jaw disharmony10.1016/0002-9416(75)90065-2 ↗
16. Ricketts, R.M., Bench, R., Gugino, C., Hilgers, J., and Schulhof, R. (1979). Visual treatment objective or V.T.O. Bioprogressive Therapy, Rocky Mountain Orthodontics.
17. A method of cephalometric evaluation10.1016/S0002-9416(84)90352-X ↗
18. Problems and limitations of cephalometric analysis in orthodontics10.14219/jada.archive.1956.0204 ↗
19. The reliability of head film measurements. 1. Landmark identification10.1016/0002-9416(71)90028-5 ↗
20. Hunter, W.S., and Carlson, D.S. (1991). Toward a general model for clinical craniofacial research. Essays in Honor of Robert E, Center for Human Growth and Development, University of Michigan.
21. Cephalometric landmarks identification and reproducibility: A meta analysis10.1016/S0889-5406(97)70242-7 ↗
22. History of imaging in orthodontics from Broadbent to cone-beam computed tomography10.1016/j.ajodo.2015.09.007 ↗
23. Computerized transverse axial tomography10.1259/0007-1285-46-552-1023 ↗
24. Evidence supporting the use of cone-beam computed tomography in orthodontics10.14219/jada.archive.2012.0148 ↗
25. Assessment of phantom dosimetry and image quality of i-CAT FLX cone-beam computed tomography10.1016/j.ajodo.2013.07.013 ↗
26. Computer applications in orthodontics
27. Computer-aided headfilm analysis: The University of California San Francisco method10.1016/0002-9416(80)90039-1 ↗
28. A comparison of traditional and computerized methods of cephalometric analysis10.1093/ejo/3.1.15 ↗
29. Verification and standardization of cephalometric coordinate data10.1016/0010-468X(80)90068-9 ↗
30. Software development for the management of cephalometric radiographic data10.1016/0010-468X(80)90126-9 ↗
31. A Pascal computer program for digitizing lateral cephalometric radiographs10.1016/0002-9416(85)90040-5 ↗
32. A preliminary study of computer recognition and identification of skeletal landmarks as a new method of cephalometric analysis10.1179/bjo.11.3.143 ↗
33. Knowledge-based landmarking of cephalograms10.1016/0010-4809(86)90023-6 ↗
34. Automatic landmarking of cephalograms10.1016/0010-4809(89)90005-0 ↗
35. An image processing system for locating craniofacial landmarks10.1109/42.293920 ↗
36. Automatic computerized radiographic identification of cephalometric landmarks10.1016/S0889-5406(98)70289-6 ↗
37. An evaluation of active shape models for the automatic identification of cephalometric landmarks10.1093/ejo/22.5.499 ↗
38. Desvignes, M., Romaniuk, B., Clouard, R., Demoment, R., Revenu, M., and Deshayes, M.J. (2000, January 3–7). First steps toward automatic location of landmarks on X-ray images. Proceedings of the 15th International Conference on Pattern Recognition ICPR-2000, Barcelona, Spain.
39. Innes, A., Ciesielski, V., Mamutil, J., and John, S. (2002, January 24–27). Landmark Detection for Cephalometric Radiology Images using Pulse Coupled Neural Networks. Proceedings of the International Conference on Artificial Intelligence (IC-AI’02), Las Vegas, NV, USA.
40. Cellular neural networks and dynamic enhancement for cephalometric landmarks detection
41. Active Shape Models-Their training and application10.1006/cviu.1995.1004 ↗
42. Automatic Cephalometric Analysis10.2319/120506-491.1 ↗
43. Automated 2-D cephalometric analysis on X-ray images by a model-based approach10.1109/TBME.2006.876638 ↗
44. Accuracy of computerized automatic identification of cephalometric landmarks10.1067/mod.2000.110168 ↗
45. Saad, A.A., El-Bialy, A., Kandil, A.H., and Sayed, A.A. (2005, January 19–21). Automatic cephalometric analysis using active appearance model and simulated annealing. Proceedings of the International Conference on Graphics, Vision and Image Processing, Cairo, Egypt.
46. Automated Cephalometry: System Performance Reliability Using Landmark-Dependent Criteria10.2319/092908-508R.1 ↗
47. An evaluation of cellular neural networks for the automatic identification of cephalometric landmarks on digital images
48. Automatic landmarking of cephalograms using active appearance models10.1093/ejo/cjp099 ↗
49. Ciresan, D.C., Meier, U., Masci, J., Gambardella, L.M., and Schmidhuber, J. (2011, January 16–22). Flexible, high performance convolutional neural networks for image classification. Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, Barcelona, Spain.
50. Accuracy of computerized automatic identification of cephalometric landmarks by a designed software10.1259/dmfr.20110187 ↗
51. Automatic cephalometric landmark detection using Zernike moments and template matching10.1007/s11760-013-0432-7 ↗
52. Lindner, C., and Cootes, T.F. (2015, January 16–19). Fully automatic cephalometric evaluation using Random Forest regression-voting. Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI), New York, NY, USA.
53. Fully automated quantitative cephalometry using convolutional neural networks10.1117/1.JMI.4.1.014501 ↗
54. Hassoun, M.H. (1995). Fundamentals of Artificial Neural Networks, The MIT Press.10.1109/JPROC.1996.503146 ↗
55. Collobert, R., and Weston, J. (2008, January 1). A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning. Proceedings of the 25th International Conference on Machine Learning, ICML ‘08, Helsinki, Finland.10.1145/1390156.1390177 ↗
56. Craig, M., Adapa, R., Pappas, I., Menon, D., and Stamatakis, E. (2018, January 5–8). Deep graph convolutional neural networks identify frontoparietal control and default mode network contributions to mental imagery manuscript. Proceedings of the 2018 Conference on Cognitive Computational Neuroscience, Philadelphia, PA, USA.10.32470/CCN.2018.1162-0 ↗
57. Jacobson AJacobson, R.L. (2006). Radiographic Cephalometry: From Basics to 3D Imaging, Quintessence Publishing Co. Limited. [2nd ed.].
58. A novel training algorithm for convolutional neural network10.1007/s40747-016-0024-6 ↗
59. Glorot, X., and Yoshua, B. (2010, January 13). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS), Sardinia, Italy.
60. Evaluation and comparison of anatomical landmark detection methods for cephalometric X-Ray images: A grand challenge10.1109/TMI.2015.2412951 ↗
61. An artificial intelligence based application to optimize orthodontic referrals in a public oral healthcare system10.1053/j.sodo.2021.05.011 ↗
62. Deep anatomical context feature learningfor cephalometric landmark detection10.1109/JBHI.2020.3002582 ↗
63. Machine learning and orthodontics, current trends and the future opportunities: A scoping review
64. Deep learning-based regression and classification for automatic landmark localizationin medical images10.1109/TMI.2020.3009002 ↗
65. The role of AI and machine learning in contemporary orthodontics10.25259/APOS_148_2020 ↗
66. Artificial intelligence in orthodontics: Evaluation of a fully automated cephalometric analysis using a customized convolutional neural network10.1007/s00056-019-00203-8 ↗