Performance and clinical applicability of AI models for jawbone lesion classification: a systematic review with meta-analysis and introduction of a clinical interpretation score
Dentomaxillofacial Radiology · 01.02.2026 · 55 (2) · 130-143
DOI: 10.1093/dmfr/twaf086 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 04.12.2025. Verfasst von Jonas Ver Berne und 2 weiteren Autor:innen. Beteiligte Einrichtung: OMFS-IMPATH Research Group, Department of Imaging and Pathology, Catholic University Leuven, Leuven 3000, Belgium. Hauptthemen laut MEDLINE: Artificial Intelligence, Jaw Neoplasms, Jaw Cysts. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 50 Literaturangaben.
Abstract (Originalsprache)
Objectives
To evaluate the diagnostic accuracy and generalizability of artificial-intelligence (AI) models for radiographic classification of jawbone cysts and tumours, and to propose a Clinical Interpretation Score (CIS) that rates the transparency and real-world readiness of published AI tools.
Methods
Eligible studies reporting sensitivity and specificity of AI classifiers on panoramic radiographs or cone-beam CT were retrieved. Two reviewers applied Joanna Briggs Institute (JBI) risk-of-bias criteria and extracted 2 × 2 tables and relevant metrics. Pooled estimates were calculated with random-effects meta-analysis; heterogeneity was quantified with I2.
Results
Nineteen studies were included, predominantly reporting convolutional neural networks. Pooled specificity was consistently high (≥0.90) across lesions, whereas sensitivity ranged widely (0.50-1.00). Stafne bone cavities achieved near-perfect metrics; ameloblastoma and odontogenic keratocyst showed moderate sensitivity (0.62-0.85) but retained high specificity. Cone-beam CT improved sensitivity relative to panoramic imaging. Substantial heterogeneity (I2 > 50% in most comparisons) reflected variable prevalence, imaging protocols and validation strategies.
Conclusions
Artificial-intelligence models demonstrate promising diagnostic performance in classifying several jawbone lesions, though their accuracy is influenced by imaging modality, lesion type, and prevalence. Despite encouraging technical results, many studies lack transparent reporting and external validation, limiting their clinical interpretability. The CIS provides a structured framework to evaluate the methodological transparency and clinical readiness of AI tools, helping to distinguish between technically sound models and those suitable for integration into diagnostic workflows.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- OMFS-IMPATH Research Group, Department of Imaging and Pathology, Catholic University Leuven, Leuven 3000, Belgium.
- Department of Pathology, University Hospitals Leuven, Leuven 3000, Belgium.
- Department of Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven 3000, Belgium.
- Department of Dentistry, Karolinska Institutet, Huddinge 141 52, Sweden.
ORCID-Profile: Jonas Ver Berne
Zitieren
APA
Ver Berne, J., Ton That, M., & Jacobs, R. (2026). Performance and clinical applicability of AI models for jawbone lesion classification: a systematic review with meta-analysis and introduction of a clinical interpretation score. Dentomaxillofacial Radiology, 55(2), 130-143. https://doi.org/10.1093/dmfr/twaf086
Vancouver
Ver Berne J, Ton That M, Jacobs R. Performance and clinical applicability of AI models for jawbone lesion classification: a systematic review with meta-analysis and introduction of a clinical interpretation score. Dentomaxillofacial Radiology. 2026;55(2):130-143. doi:10.1093/dmfr/twaf086
BibTeX
@article{VerBerne2026,
author = {Ver Berne, Jonas and Ton That, Minh and Jacobs, Reinhilde},
title = {Performance and clinical applicability of AI models for jawbone lesion classification: a systematic review with meta-analysis and introduction of a clinical interpretation score},
journal = {Dentomaxillofacial Radiology},
year = {2026},
volume = {55},
number = {2},
pages = {130--143},
doi = {10.1093/dmfr/twaf086}
}
EUVIMED