From Landmark to Diagnosis: Detection of a Systematic Pipeline Bias and Sobol Uncertainty Analysis of ANB-Based Skeletal Classification in a YOLO Cephalometric Detector

AI-based cephalometric landmark detection is usually evaluated with localization metrics only. This study traced uncertainty in a YOLO-based pipeline from landmark annotation to ANB-based skeletal classification. Fourteen YOLO configurations with bounding boxes of 40–150 px were trained on augmented samples from 120 lateral cephalograms. The models were evaluated on 11 test radiographs annotated by 22 orthodontists in two sessions. Systematic error was assessed by the directional coherence of landmark offsets. Propagation to the ANB angle was assessed by Monte Carlo simulation with empirical anisotropic error covariances and Sobol sensitivity analysis. All models showed a coherent offset (R = 0.983). Its magnitude increased with box size with a slope of 0.708. This value matches the 0.707 expected for coordinates exported from the box corner. A fixed shift in half the box size corrected the offset without use of test data. After correction, the best model reached a mean radial error of 1.26 mm (95% CI 0.96–1.61 mm). Larger boxes performed worse only on low-resolution radiographs. A-point (S1 = 0.741) dominated ANB variance, followed by B-point (0.157) and N-point (0.085). The ANB limits of agreement of the 40 px models were −2.05° to +1.44°. Skeletal-class concordance with the consensus was 96.9% for the models and 96.5% for individual observers. A single observer deviated from an independent reference by 1.33 mm. The best model deviated by 1.30 mm. Pipeline bias checks should precede benchmarking. A-point localization is the priority target for improving ANB-based diagnosis.

Authors

Institutions

Publication Details

Journal
Applied Sciences
Published
2026-11-18
DOI
https://doi.org/10.3390/app162211436
Primary Topic
Orthodontics and Dentofacial Orthopedics
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

From Landmark to Diagnosis: Detection of a Systematic Pipeline Bias and Sobol Uncertainty Analysis of ANB-Based Skeletal Classification in a YOLO Cephalometric Detector

Rafał Porowski, Jacek Kotuła, Marcin Konarzewski, Beata Kawala et al.
5 links
Applied Sciences
Orthodontics and Dentofacial Orthopedics
article

From Landmark to Diagnosis: Detection of a Systematic Pipeline Bias and Sobol Uncertainty Analysis of ANB-Based Skeletal Classification in a YOLO Cephalometric Detector

Rafał Porowski, Jacek Kotuła, Marcin Konarzewski, Beata Kawala, Joanna Lis, Michał Sarul, Krzysztof Kotuła, Jakub Polkowski
article en

Abstract

AI-based cephalometric landmark detection is usually evaluated with localization metrics only. This study traced uncertainty in a YOLO-based pipeline from landmark annotation to ANB-based skeletal classification. Fourteen YOLO configurations with bounding boxes of 40–150 px were trained on augmented samples from 120 lateral cephalograms. The models were evaluated on 11 test radiographs annotated by 22 orthodontists in two sessions. Systematic error was assessed by the directional coherence of landmark offsets. Propagation to the ANB angle was assessed by Monte Carlo simulation with empirical anisotropic error covariances and Sobol sensitivity analysis. All models showed a coherent offset (R = 0.983). Its magnitude increased with box size with a slope of 0.708. This value matches the 0.707 expected for coordinates exported from the box corner. A fixed shift in half the box size corrected the offset without use of test data. After correction, the best model reached a mean radial error of 1.26 mm (95% CI 0.96–1.61 mm). Larger boxes performed worse only on low-resolution radiographs. A-point (S1 = 0.741) dominated ANB variance, followed by B-point (0.157) and N-point (0.085). The ANB limits of agreement of the 40 px models were −2.05° to +1.44°. Skeletal-class concordance with the consensus was 96.9% for the models and 96.5% for individual observers. A single observer deviated from an independent reference by 1.33 mm. The best model deviated by 1.30 mm. Pipeline bias checks should precede benchmarking. A-point localization is the priority target for improving ANB-based diagnosis.

Applied SciencesVol. 16(22)
Jan Kochanowski University (PL), Military University of Technology in Warsaw (PL), Wroclaw Medical University (PL)
Uniwersytet Jana Kochanowskiego w Kielcach, Uniwersytet Medyczny im. Piastów Slaskich we Wroclawiu
Orthodontics and Dentofacial Orthopedics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon