EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

Development and external validation of an AI pipeline for automated estimation of a radiographic DMFT (rDMFT) score from panoramic radiographs: a feasibility study

Babak Saravi iD, Veronika Shavlokhova, Ashraf Türky, Daman Deep Singh, Felix Schrader, Andreas Vollmer, Norbert Kübler, Christoph Sproll, Lara Schorn

Clinical Oral Investigations · 2026

DOI: 10.1007/s00784-026-07214-x ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Clinical Oral Investigations, 2026. Verfasst von Babak Saravi und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oral, Maxillofacial and Facial Plastic Surgery, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldor…. Hauptthemen laut MEDLINE: Radiography, Panoramic, DMF Index, Dental Caries, Artificial Intelligence. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To assess the feasibility of estimating a radiographic Decayed-Missing-Filled-Teeth score (rDMFT), a proxy for the clinical DMFT index, from a single panoramic radiograph with a position-aware deep-learning pipeline. Materials and methods A tooth-status detector and a tooth-numbering detector (32 FDI positions), trained on DENTEX 2023, were combined in a position-aware read-out (one tooth per FDI position, third molars excluded, missing teeth = 28 − occupied positions) and validated on 100 panoramic radiographs from an independent hospital against a two-dentist, radiograph-based reference (intraclass correlation coefficient, ICC; mean absolute error, MAE; Bland–Altman analysis).

Results

Against the reference, the pipeline reached an ICC of 0.84 (95% CI 0.74 to 0.90) and an MAE of 2.38, below the between-dentist agreement in point estimate (ICC 0.88, MAE 2.13), with larger errors against each dentist alone (MAE 3.00 and 2.73) and a bias of + 1.14 units from caries over-detection; agreement was highest for filled (r 0.90) and lowest for decayed teeth (r 0.34; dentists 0.16). In the 26 radiographs with missing teeth the missing count was exact in 42% (62% within ± 1 tooth), and missing teeth were over-called in 15 of 74 complete dentitions; tooth loss was no longer overlooked (26 of 26 detected), but the overall ICC was 0.84 versus 0.90 without numbering.

Conclusions

Automated rDMFT estimation is feasible, but agreement was lower in point estimate than between two dentists, with larger errors against each dentist. The missing component now responds to actual tooth loss but remains imprecise and is over-called in some complete dentitions; the decayed component is unreliable. The pipeline is a research building block, not a decision-support or triage tool. Clinical relevance rDMFT is a radiographic proxy, not a clinical measure, and the pipeline is not proposed for clinical use; any application would first require validation in unselected cohorts against clinically determined reference standards.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Radiography, PanoramicDMF IndexDental CariesArtificial IntelligenceDeep LearningHumansFeasibility StudiesFemaleMaleReproducibility of Results

Stichwörter der Autor:innen

Artificial intelligenceDeep learningDental cariesExternal validationPanoramic radiographyRadiographic DMFT (rDMFT)

Autor:innen und Institutionen

  • Department of Oral, Maxillofacial and Facial Plastic Surgery, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Düsseldorf, 40225, Germany. babak.saravi@med.uni-duesseldorf.de.
  • Department of Oral and Maxillofacial Surgery, University Clinic Ruppin-Brandenburg, Neuruppin, 16816, Germany.
  • Department of Oral, Maxillofacial and Facial Plastic Surgery, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Düsseldorf, 40225, Germany.
  • Department of Oral and Maxillofacial Plastic Surgery, University Hospital of Würzburg, Würzburg, 97070, Germany.

ORCID-Profile: Babak Saravi

Zitieren

APA

Saravi, B., Shavlokhova, V., Türky, A., Singh, D. D., Schrader, F., Vollmer, A., Kübler, N., Sproll, C., & Schorn, L. (2026). Development and external validation of an AI pipeline for automated estimation of a radiographic DMFT (rDMFT) score from panoramic radiographs: a feasibility study. Clinical Oral Investigations. https://doi.org/10.1007/s00784-026-07214-x

Vancouver

Saravi B, Shavlokhova V, Türky A, Singh DD, Schrader F, Vollmer A, et al. Development and external validation of an AI pipeline for automated estimation of a radiographic DMFT (rDMFT) score from panoramic radiographs: a feasibility study. Clinical Oral Investigations. 2026. doi:10.1007/s00784-026-07214-x

BibTeX
@article{Saravi2026,
  author = {Saravi, Babak and Shavlokhova, Veronika and Türky, Ashraf and Singh, Daman Deep and Schrader, Felix and Vollmer, Andreas and Kübler, Norbert and Sproll, Christoph and Schorn, Lara},
  title = {Development and external validation of an AI pipeline for automated estimation of a radiographic DMFT (rDMFT) score from panoramic radiographs: a feasibility study},
  journal = {Clinical Oral Investigations},
  year = {2026},
  doi = {10.1007/s00784-026-07214-x}
}
Kostenlos starten →