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.

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.

Background: This article analyzes differences in microbiological parameters and periodontal health conditions among three patient groups: those undergoing conventional orthodontic treatment with fixed appliances, patients undergoing orthodontic treatment with clear aligners, and a control group receiving no treatment. Materials and Methods: In this study, 60 patients were enrolled. The microbiological analysis employed a qualitative and semi-quantitative methodology of bacterial morphotype analysis. Results: The analyses revealed a significant difference in favor of clear oral and periodontal health aligners. This could be attributed to better bacterial biofilm removal and reduced mechanical stress on the periodontal ligament, factors facilitated by the ease of clear aligner removal. Significant differences (p-value < 0.05) were observed for the Full-Mouth Plaque Score, Full-Mouth Bleeding Score, Plaque Index, and periodontal health assessment measurements. Conclusions: Although overall hygiene appears to be improved in patients in the aligners group compared to those treated with conventional orthodontic appliances, there are no statistically significant results regarding plaque composition. Microbiological aspects will be further addressed using more specific techniques in the follow-up of this research.

Cephalometric analysis is a widely adopted procedure for clinical decision support in orthodontics. It involves manual identification of predefined anatomical landmarks on three-dimensional cone beam CT scans, followed by the computation of linear and angular measurements. To reduce processing time and operator dependency, this study aimed to develop a light-weight deep learning (DL) model capable of automatically localizing 16 anatomically defined landmarks. To ensure model robustness and generalizability, the model was trained on a dataset of 350 manually annotated CBCT scans acquired from various imaging systems, covering a wide range of patient ages and skeletal classifications. The trained model is a V-net, optimized for practical use in clinical workflows. The model achieved a mean localization error of 1.95 ± 1.06 mm, which falls within the clinically acceptable threshold of 2 mm. Moreover, the predicted landmarks were used to calculate cephalometric measurements and compare with manually derived values. The resulting errors was -0.15 ± 0.95° for angular measurements and 0.20 ± 0.28 mm for linear ones, with Bland-Altman analysis demonstrating strong agreement and acceptable variability. These results suggest that automated measurements can reliably replace manual ones. Given the clinical relevance of cephalometric parameters - particularly the ANB angle, which is critical for skeletal classification and orthodontic treatment planning - this model represents a promising clinical decision support tool. Additionally, its low computational complexity enables fast prediction, with mean inference time lower than 32 s per scan, promoting its integration into routine clinical settings due to both technical feasibility and robustness across heterogeneous datasets.

Serafin M, et al. Imaging Sci Dent. 2025 Jul;55:e26. https://doi.org/10.5624/isd.20250013

The ANB angle, the cephalometric parameter of choice for assessing the anteroposterior relationship between the maxilla and mandible, is subject to several limitations, prompting the investigation of alternative parameters. Objective: This study aimed to investigate the ABwise measurement as an alternative to the ANB angle for evaluating maxillomandibular relationships in orthodontics, particularly addressing the impact of skeletal discrepancies on conventional methods. Methods: A retrospective analysis was performed on a CBCT dataset of patients attending the University of Milan’s Department of Orthodontics and Maxillofacial Surgery, selected based on high-quality imaging, a full-cranium field of view, and a slice thickness between 150 and 300 μm. Eight craniofacial landmarks were annotated using the 3D Slicer software to calculate the ANB values and the new ABwise measurement. Statistical analyses included Spearman’s correlation (ρ), linear regression, and inter-rater agreement (Cohen’s κ score), with data classified into skeletal Classes I, II, and III based on defined thresholds. Results: 354 CBCT were selected and analyzed (mean age: 18.6 years). ABwise showed a strong correlation with the ANB angle (ρ = 0.805) and new normative ranges for ABwise were established: Class I (−1.4 ± 2.3 mm), Class II (>0.9 mm), and Class III (<−3.7 mm). Moderate agreement was observed between the ABwise and ANB classifications (κ = 0.527). ABwise effectively addressed limitations associated with divergence and vertical discrepancies, providing a more reliable assessment of skeletal sagittal relationships. Conclusions: ABwise presents a viable alternative to the ANB angle for three-dimensional cephalometric analysis, offering improved accuracy and alignment with radioprotection principles by reducing the CBCT field of view needed for its measurement. Further research is required in order to validate these findings across diverse populations and clinical scenarios.