Back to all papers

Reliability-Aware View-Adaptive Consensus for 3D Cephalometric Landmark Identification.

July 29, 2026pubmed logopapers

Authors

Choi MH,Kim JE,Huh KH,Lee SS,Heo MS,Yi WJ

Affiliations (4)

  • Department of Biomedical Radiation Sciences, Graduate School of Convergence Science and Technology, Seoul National University, 1 Gwanak-ro, Seoul, 08826, Republic of Korea.
  • Department of Oral and Maxillofacial Radiology, School of Dentistry and Dental Research Institute, Seoul National University, 1 Gwanak-ro, Seoul, 08826, Republic of Korea.
  • Department of Biomedical Radiation Sciences, Graduate School of Convergence Science and Technology, Seoul National University, 1 Gwanak-ro, Seoul, 08826, Republic of Korea. [email protected].
  • Department of Oral and Maxillofacial Radiology, School of Dentistry and Dental Research Institute, Seoul National University, 1 Gwanak-ro, Seoul, 08826, Republic of Korea. [email protected].

Abstract

Cone-beam computed tomography (CBCT)-based three-dimensional (3D) cephalometric analysis relies on accurate anatomical landmark identification, yet manual annotation is time-consuming and subject to inter- and intra-observer variability. While volumetric convolutional neural networks can improve accuracy, their computational and memory demands limit practical deployment. Multi-view consensus offers an efficient alternative by predicting per-view two-dimensional (2D) heatmaps and fusing them geometrically, but its performance can degrade when view-dependent uncertainty produces unreliable results. We propose a reliability-aware view-adaptive consensus framework for 3D cephalometric landmark identification from CBCT projection views. A shared-weight 2D network predicts per-view 2D heatmaps and landmark reliability scores, which adaptively modulate each view's contribution in an end-to-end differentiable geometric consensus. This framework yields deterministic fusion without stochastic inlier sampling or multi-stage refinement. With 5-fold cross-validation, the proposed method achieved the lowest mean radial error (1.26 mm; 95 <math xmlns="http://www.w3.org/1998/Math/MathML"><mo>%</mo></math> CI [1.20, 1.33]) and the highest successful detection rate at 2 mm (88.41 <math xmlns="http://www.w3.org/1998/Math/MathML"><mo>%</mo></math> ), while maintaining low computational loads. Ablation studies further validated the key design choices and highlighted a favorable accuracy-efficiency trade-off with a limited number of views.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ 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.