Abstract
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.
Conclusion
The results of this study highlight the potential of the proposed deep learning model to function as an effective clinical decision support system (CDSS) in orthodontic workflows.
By automating the identification of anatomically relevant landmarks and providing accurate cephalometric measurements—such as the ANB angle, essential for skeletal classification—the model offers clinicians a reliable tool to enhance diagnostic efficiency and precision.
Its robust performance across varying imaging conditions and skeletal classes, combined with its low computational complexity, makes it well-suited for integration into routine practice, even in settings with limited resources. This tool may support clinicians in reducing inter-operator variability, improving diagnostic consistency, and streamlining treatment planning with reduced operating times.
This is one of the scientific articles published by one or more synbrAIn collaborators and data scientists.
If you would like to learn more, read the full article here.
