Optimization of the three-dimensional cephalometric analysis using deep machine learning

The goal of this study was to create a new convolutional neural network (CNN) model system for landmarking cephalometric points on DICOM slices of conebeam computed tomography for future 3D cephalometrics and to evaluate its accuracy. The current study demonstrates that when determining ceph points on 3D conebeam computed tomography (CBCT) scans of the head, considering the problem of keypoint detection as a segmentation problem can provide an accurate and generalised performance in the case of a limited 3D dataset.

The constructed CNN demonstrated a mean absolute error (MAE) of 2.78 mm by distance across all points and a standard deviation (SD) of 1.59 mm by distance across all points.

Conclusion. The study shows that the segmentation approach for CNN learning to determine cephalometric points on anatomical 3D models based on CBCTs is highly efficient. The proposed method, when embedded in specialized software, has the potential to significantly reduce the time-consuming workflow used by experts.

1. Cintra O., Grybauskas S., Vogel C.J., Latkauskiene D., Gama N.A. Jr. Digital platform for planning facial asymmetry orthodontic-surgical treatment preparation. Dental press journal of orthodontics. 2018;23(3):80-93.

2. Codari M., Caffini M., Tartaglia G.M., Sforza C., Baselli G. Computer-aided cephalometric landmark annotation for CBCT data. Int J Computer Assisted Radiol Surg. 2017;12(1):113-121.

3. Gupta A., Kharbanda O.P., Sardana V., Balachandran R., Sardana H.K. A knowledge-based algorithm for automatic detection of cephalometric landmarks on CBCT images. Int J Computer Assisted Radiol Surg. 2015;10(11):1737-1752.

4. Kang S.H., Jeon K., Kim H.J., Seo J.K., Lee S.H. Automatic three-dimensional cephalometric annotation system using three-dimensional convolutional neural networks: a developmental trial. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization. 2020;8(2):210-218.

5. Lee S.M., Kim H.P., Jeon K., Lee S.H., Seo J.K. Automatic 3D cephalometric annotation system using shadowed 2D image-based machine learning. Physics in Medicine & Biology. 2019;64(5):055002.

6. Makram M., Kamel H. Reeb graph for automatic 3D cephalometry. IJIP. 2014;8(2):17-29.

7. Montúfar J., Romero M., Scougall-Vilchis R.J. Automatic 3-dimensional cephalometric landmarking based on active shape models in related projections. Am J Orthodont Dentofac Orthoped. 2018;153(3):449-458.

8. Montúfar J., Romero M., Scougall-Vilchis R.J. Hybrid approach for automatic cephalometric landmark annotation on cone-beam computed tomography volumes. Am J Orthodont Dentofac Orthoped. 2018;154(1):140-150.

9. Muraev A.A., Kibardin I.A., Oborotistov N.Yu., Ivanov S.S., Persin L.S. (2018) Use of neural network algorithms for the automated placement of cephalometric points on Lateral Ceph. REJR 8(4):16-22

10. Muraev A.A., Tsai P., Kibardin I., Oborotistov N., Shirayeva T., Ivanov S., Ivanov S., Guseynov N., Aleshina O., Bosykh Y., Safyanova E., Andreischev A., Rudoman S., Dolgalev A., Matyuta M., Karagodsky V., Tuturov N. Frontal cephalometric landmarking: humans vs artificial neural networks. Int J Computerized Dentistry. 2020;23(2):139-148.

11. Nalçaci R., Oztürk F., Sökücü O. A comparison of two-dimensional radiography and three-dimensional computed tomography in angular cephalometric measurements. Dentomaxillofacial Radiol. 2010;39 (2) : 100-106.

12. Neelapu B.C., Kharbanda O.P., Sardana V., Gupta A., Vasamsetti S., Balachandran R., Sardana H.K. Automatic localisation of three-dimensional cephalometric landmarks on CBCT images by extracting symmetry features of the skull. Dentomaxillofacial Radiol. 2018;47(2):20170054.

13. Shahidi Sh., Oshagh M., Gozin F., Salehi P., Danaei S.M. Accuracy of computerized automatic identification of cephalometric landmarks by a designed soft ware. Dentomaxillofacial Radiol. 2013;42(1):2011018720110187.

14. Vlijmen van O.J., Maal T., Bergé S.J., Bronkhorst E.M., Katsaros C., Kuijpers-Jagtman A.M. A comparison between 2D and 3D cephalometry on CBCT scans of human skulls. Int J Oral Maxillofac Surg. 2010;39(2):156-160.

15. Wang R.H., Ho C.T., Lin H.H, Lo L.J. Th ree-dimensional cephalometry for orthognathic planning: Normative data and analyses. J Formosan Med Association. 2020;119(1):191-203.

16. Yun H.S., Jang T.J., Lee S.M., Lee S.H., Seo J.K. Learning-based local-to-global landmark annotation for automatic 3D cephalometry. Physics in Med Biol. 2020;65(8):085018.