@inproceedings{hou2026automatic,
  title     = {Automatic Cephalometric Landmark Localization on {CBCT}-Derived Digitally Reconstructed Radiographs for Skeletal Malocclusion Classification},
  author    = {Hou, Benjamin and Almpani, Konstantinia and Lee, Janice S. and Lu, Zhiyong},
  booktitle = {Oral and Dental Image Analysis (ODIN 2026)},
  series    = {Lecture Notes in Computer Science},
  publisher = {Springer},
  year      = {2026},
  note      = {Accepted for publication},
  doi = {10.48550/arxiv.2608.16535},
  eprint = {2608.16535},
  archiveprefix = {arXiv},
  abstract = {Manual cephalometric landmark annotation is important for craniofacial assessment but is labor-intensive and difficult to scale. We introduce CephViT, a Vision Transformer-based model for automated 2D lateral cephalometric landmark localization, and evaluate its use in downstream skeletal malocclusion classification. CephViT was trained and benchmarked on a public lateral cephalogram dataset, achieving a mean radial error of 1.28 +/- 1.42 mm and a successful detection rate of 92.0\% at 3.0 mm. Because the private evaluation cohort consisted of 3D CBCT scans, lateral cephalogram-like digitally reconstructed radiographs (DRRs) were generated from each volume and used as 2D inputs to the landmark localization model. Landmark coordinates were normalized into a common coordinate frame, and skeletal malocclusion classification was performed using landmarks shared between the reference and DRR-based pipelines. Classification performance using DRR-localized landmarks was comparable to that obtained using manually annotated reference landmarks, with accuracies of 70.0\% and 68.3\%, respectively. These results support the feasibility of automated cephalometric analysis on CBCT-derived DRRs for skeletal malocclusion assessment.},
  code = {https://huggingface.co/nlm-dir/CephViT},
}