Back to all papers

Automated 3D cephalometry: A lightweight V-net for landmark localization on CBCT.

January 6, 2026pubmed logopapers

Authors

Baldini B,Rubiu G,Serafin M,Bologna M,Facchi GM,Baselli G,Tartaglia GM

Affiliations (7)

  • Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan 20133, Italy. Electronic address: [email protected].
  • SynbrAIn S.r.l., Via privata Giovacchino Belli 14, Milan 20127, Italy. Electronic address: [email protected].
  • Department of Biomedical Sciences for Health, University of Milan, Via Mangiagalli 31, Milan 20133, Italy. Electronic address: [email protected].
  • SynbrAIn S.r.l., Via privata Giovacchino Belli 14, Milan 20127, Italy. Electronic address: [email protected].
  • PHuSe Lab, Department of Computer Science, University of Milan, Milan 20133, Italy. Electronic address: [email protected].
  • Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan 20133, Italy. Electronic address: [email protected].
  • Ospedale Maggiore Policlinico, UOC Maxillo-Facial Surgery and Dentistry Fondazione IRCCS Cà Granda, Milan 20122, Italy; Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan 20133, Italy. Electronic address: [email protected].

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.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 8,200+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.