Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2605.03358 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917527613865984 |
|---|---|
| author | Mohapatra, Sidhartha Mohanty, Pallavi |
| author_facet | Mohapatra, Sidhartha Mohanty, Pallavi |
| contents | Clinicians trace cephalometric radiographs by following a structured anatomical workflow -- yet no prior system explicitly encodes this into computation. We present a five-phase anatomy-guided pipeline producing confidence-weighted spatial priors that shape HRNet-W32 training. The system achieves 1.04 mm mean radial error on 25 landmarks across 1,502 radiographs from 7+ imaging devices -- comparable to HYATT-Net (1.05 mm on CEPHA29) via explicit anatomical priors rather than learned attention. A three-way ablation isolates the mechanism: anatomical priors maintain a 1% validation-to-test gap, while removing priors yields an 88% gap (1.94 mm) -- despite identical validation convergence. A training x inference prior matrix confirms that (1) all models are inference-independent, (2) the 28-channel architecture alone provides no benefit, (3) random priors are partial and unstable (1.72 mm), and (4) only anatomically correct, image-specific priors yield 1.04 mm -- functioning as a training-time regularizer. No prior generation is needed at deployment. Five-fold cross-validation (p=0.0015), patient-level permutation testing (p<0.0001, n=151), reproduced baselines, Grad-CAM analysis, and clinical validation (100% skeletal classification across 151 patients including 72 boundary cases, kappa=1.00) provide converging evidence. Cross-domain experiments support the hypothesis that prior effectiveness depends on landmark spatial entropy -- confirmed prospectively across four domains. Supplementary materials included. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03358 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Tracing Like a Clinician: Anatomy-Guided Spatial Priors for Cephalometric Landmark Detection Mohapatra, Sidhartha Mohanty, Pallavi Computer Vision and Pattern Recognition Clinicians trace cephalometric radiographs by following a structured anatomical workflow -- yet no prior system explicitly encodes this into computation. We present a five-phase anatomy-guided pipeline producing confidence-weighted spatial priors that shape HRNet-W32 training. The system achieves 1.04 mm mean radial error on 25 landmarks across 1,502 radiographs from 7+ imaging devices -- comparable to HYATT-Net (1.05 mm on CEPHA29) via explicit anatomical priors rather than learned attention. A three-way ablation isolates the mechanism: anatomical priors maintain a 1% validation-to-test gap, while removing priors yields an 88% gap (1.94 mm) -- despite identical validation convergence. A training x inference prior matrix confirms that (1) all models are inference-independent, (2) the 28-channel architecture alone provides no benefit, (3) random priors are partial and unstable (1.72 mm), and (4) only anatomically correct, image-specific priors yield 1.04 mm -- functioning as a training-time regularizer. No prior generation is needed at deployment. Five-fold cross-validation (p=0.0015), patient-level permutation testing (p<0.0001, n=151), reproduced baselines, Grad-CAM analysis, and clinical validation (100% skeletal classification across 151 patients including 72 boundary cases, kappa=1.00) provide converging evidence. Cross-domain experiments support the hypothesis that prior effectiveness depends on landmark spatial entropy -- confirmed prospectively across four domains. Supplementary materials included. |
| title | Tracing Like a Clinician: Anatomy-Guided Spatial Priors for Cephalometric Landmark Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.03358 |