Accuracy of automated cephalometric landmark detection with artificial intelligence: a systematic review

Melissa Castillo Jimenez, Melissacj981223@gmail.com, Maylon Felix Guerra Reyes and Guerramaylon6@gmail.com

SAP Artificial Intelligence in Dentistry, 2025

Abstract: 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.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://southam.pub/journals/files/aid/aid202519en.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cwf:aidart:aid202519

DOI: 10.62486/aid202519

Access Statistics for this article

More articles in SAP Artificial Intelligence in Dentistry from South American Publishing
Bibliographic data for series maintained by South American Publishing Journals Manager ().