Tracing Like a Clinician: Anatomy-Guided Spatial Priors for Cephalometric Landmark Detection

TL;DR

This paper introduces an anatomy-guided initialization pipeline for cephalometric landmark detection, significantly improving accuracy and generalization over prior methods by incorporating clinical domain knowledge.

Contribution

The authors develop a five-phase anatomy-guided approach that produces spatial priors, enhancing landmark detection accuracy and robustness compared to existing techniques.

Findings

Achieves 1.04 mm mean radial error on 25 landmarks, surpassing prior state-of-the-art.

Removing anatomical priors reduces generalization, leading to higher errors on test data.

Replacing anatomical priors with random Gaussian positions worsens performance, confirming the importance of correct anatomical priors.

Abstract

When orthodontists trace cephalometric radiographs, they follow a structured workflow: identify the soft tissue profile, partition the skull into anatomical regions, trace contours, and locate landmarks using geometric definitions -- yet no automated system replicates this reasoning. We present a five-phase anatomy-guided initialization pipeline that translates this clinical workflow into computational operations, producing confidence-weighted spatial attention priors for a downstream HRNet-W32 detector. On 1,502 radiographs from three sources spanning 7+ imaging devices, the system achieves 1.04 mm mean radial error on 25 landmarks -- surpassing prior state-of-the-art (1.23 mm on 19 landmarks) by 15.4%, with twelve landmarks below 1 mm. A three-way controlled ablation reveals two striking findings. First, removing anatomical priors does not merely slow convergence -- it destroys generalization: both models converge to ~1.03 mm on validation, but diverge to 1.94 vs. 1.04 mm on the test set. Second, replacing anatomical priors with random-position Gaussians produces even worse generalization (2.24 mm), confirming that the improvement derives from anatomically correct positioning, not additional input channels. Clinical domain knowledge encoded as spatial priors provides an inductive bias that architecture and data augmentation alone do not provide.