Accuracy of automated cephalometric landmark detection with artificial intelligence: a systematic review
SAP Artificial Intelligence in Dentistry · 2025
DOI: 10.62486/aid202519 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift SAP Artificial Intelligence in Dentistry, 2025. Verfasst von Melissa Castillo Jimenez und 1 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Cephalometric analysis depends on manual landmark identification, which is time-consuming and observer-dependent. Artificial intelligence has been proposed to automate this step, but reported accuracy varies.
Methods
Following PRISMA 2020, PubMed, OpenAlex, and Crossref were searched for studies published from 2018 to 2025 that evaluated artificial intelligence models for cephalometric landmark detection against manual annotation. Risk of bias was assessed with QUADAS-2.
Results
Forty-three studies were included, most using convolutional neural networks on lateral cephalograms. Mean radial error ranged from 0.62 mm to 2.67 mm across studies, and success detection rate at a 2 mm threshold ranged from 26.8% to 97.3%.
Conclusions
Artificial intelligence detects cephalometric landmarks with clinically acceptable mean radial error in most studies, but success detection rate at the 2 mm threshold remains heterogeneous and varies with landmark and dataset. External validation on clinical cohorts is still scarce.
Zitieren
APA
Jimenez, M. C., & Reyes, M. F. G. (2025). Accuracy of automated cephalometric landmark detection with artificial intelligence: a systematic review. SAP Artificial Intelligence in Dentistry. https://doi.org/10.62486/aid202519
Vancouver
Jimenez MC, Reyes MFG. Accuracy of automated cephalometric landmark detection with artificial intelligence: a systematic review. SAP Artificial Intelligence in Dentistry. 2025. doi:10.62486/aid202519
BibTeX
@article{Jimenez2025,
author = {Jimenez, Melissa Castillo and Reyes, Maylon Felix Guerra},
title = {Accuracy of automated cephalometric landmark detection with artificial intelligence: a systematic review},
journal = {SAP Artificial Intelligence in Dentistry},
year = {2025},
doi = {10.62486/aid202519}
}
EUVIMED