Background Cephalometric analysis is traditionally performed on skull lateral teleradiographs for orthodontic diagnosis and treatment planning. However, the skull flattened over a 2D film presents projection distortions and superimpositions to various extents depending on landmarks relative position. When a CBCT scan is indicated for mixed reasons, cephalometric assessments can be performed directly on CBCT scans with a distortion free procedure. The aim of the present study is to compare these two methods for orthodontic cephalometry. Methods 114 CBCTs were selected, reconstructed lateral cephalometries were obtained by lateral radiographic projection of the entire volume from the right and left sides. 2D and 3D cephalometric tracings were performed. Since paired t-tests between left and right-side measurements found no statistically significant differences, mean values between sides were considered for both 2D and 3D values. The following measurements were evaluated: PNS-A; S-N; N-Me; N-ANS; ANS-Me; Go-Me; Go-S; Go-Co; SNA, SNB, ANB; BaŜN; S-N^PNS-ANS; PNS-ANS^Go-Me; S-N^Go-Me. Intraclass correlation coefficients, paired t-test, correlation coefficient and Bland–Altman analysis were performed to compare these techniques. Results The values of intra- and inter-rater ICC showed excellent repeatability and reliability: the average (± SD) intraobserver ICCs were 0.98 (± 0.01) and 0.97(± 0.01) for CBCT and RLCs, respectively; Inter-rater reliability resulted in an average ICC (± SD) of 0.98 (± 0.01) for CBCT and 0.94 (± 0.03) for RLC. The paired t-tests between CBCT and reconstructed lateral cephalograms revealed that Go-Me, Go-S, PNS-ANS^Go-Me and S-N^Go-Me measurements were statistically different between the two modalities. All the evaluated sets of measurements showed strong positive correlation; the bias and ranges for the 95% Limits of Agreement showed higher levels of agreement between the two modalities for unpaired measurements with respect to bilateral ones. Conclusion The cephalometric measurements laying on the mid-sagittal plane can be evaluated on CBCT and used for orthodontic diagnosis as they do not show statistically significant differences with those measured on 2D lateral cephalograms. For measurements that are not in the mid-sagittal plane, the future development of specific algorithms for distortion correction could help clinicians deduct all the information needed for orthodontic diagnosis from the CBCT scan.

The objective of this paper is to define normal values of a novel 3D cephalometric analysis and to define the links through an artificial neural network (ANN). Methods: One hundred and fifteen CBCTs of Class I young patients, distributed among gender-adjusted developmental groups, were selected. Three operators identified 18 cephalometric landmarks from which 36 measurements were obtained. The repeatability was assessed through the ICC. Two-dimensional values were extracted by an automatic function, and the mean value and standard deviation were compared by paired Student’s t-tests. Correlation coefficient gave the relationships between 2D and 3D measurements for each group. The values were computed with the ANN to evaluate the parameters normality link and displayed by Pajek software. Results: The ICC assessed an excellent (≥0.9) repeatability. Normal values were extracted, and compared with 2D measurements, they showed a high correlation on the mid-sagittal plane, reaching 1.00, with the lowest 0.71 on the lateral plane. The ANN showed strong links between the values with the centrality of the go-sagittal plane compared to the rest. Conclusions: The study provides a set of 3D cephalometric values obtained by the upper and lower 95% CI for the mean divided into the developmental stage subgroups. The two-dimensional measurements showed variable concordance, while the ANN showed a centrality between the parameters.

Objectives The aim of the present systematic review and meta-analysis is to assess the accuracy of automated landmarking using deep learning in comparison with manual tracing for cephalometric analysis of 3D medical images. Methods PubMed/Medline, IEEE Xplore, Scopus and ArXiv electronic databases were searched. Selection criteria were: ex vivo and in vivo volumetric data images suitable for 3D landmarking (Problem), a minimum of five automated landmarking performed by deep learning method (Intervention), manual landmarking (Comparison), and mean accuracy, in mm, between manual and automated landmarking (Outcome). QUADAS-2 was adapted for quality analysis. Meta-analysis was performed on studies that reported as outcome mean values and standard deviation of the difference (error) between manual and automated landmarking. Linear regression plots were used to analyze correlations between mean accuracy and year of publication. Results The initial electronic screening yielded 252 papers published between 2020 and 2022. A total of 15 studies were included for the qualitative synthesis, whereas 11 studies were used for the meta-analysis. Overall random effect model revealed a mean value of 2.44 mm, with a high heterogeneity (I2 = 98.13%, τ2 = 1.018, p-value < 0.001); risk of bias was high due to the presence of issues for several domains per study. Meta-regression indicated a significant relation between mean error and year of publication (p value = 0.012). Conclusion Deep learning algorithms showed an excellent accuracy for automated 3D cephalometric landmarking. In the last two years promising algorithms have been developed and improvements in landmarks annotation accuracy have been done.