Development and external validation of an AI pipeline for automated estimation of a radiographic DMFT (rDMFT) score from panoramic radiographs: a feasibility study.
4 affiliations
- 1Department of Oral, Maxillofacial and Facial Plastic Surgery, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Düsseldorf, 40225, Germany. [email protected].
- 2Department of Oral and Maxillofacial Surgery, University Clinic Ruppin-Brandenburg, Neuruppin, 16816, Germany.
- 3Department of Oral, Maxillofacial and Facial Plastic Surgery, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Düsseldorf, 40225, Germany.
- 4Department of Oral and Maxillofacial Plastic Surgery, University Hospital of Würzburg, Würzburg, 97070, Germany.
Abstract
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.
Related
- Development and clinical validation of an artificial intelligence-assisted radiographic system for predicting periodontal pocket severity using full-mouth radiographs.
- Toward a National Tuberculosis Lateral-Flow Urine Lipoarabinomannan (LF-LAM) External Quality Assessment Program in Thailand: Feasibility Demonstration Through Panel Development, Validation, and Proficiency Testing, March 2025–April 2026
- Development and External Validation of Machine Learning Models for Ionized Calcium Estimation in Hypoalbuminemia
- HPTLC Method Development and Validation for Simultaneous Estimation of Rifaximin and Metronidazole Benzoate in Combined Tablet Dosage Form
- AI-Based Automated Segmentation of the Mandibular Cortex and Mental Foramen for Radiomorphometric Measurement on Panoramic Radiographs: A Feasibility Study
BibTeX
@article{saravi2026development,
title = {{Development and external validation of an AI pipeline for automated estimation of a radiographic DMFT (rDMFT) score from panoramic radiographs: a feasibility study.}},
author = {Babak Saravi and Veronika Shavlokhova and Ashraf Türky and Daman Deep Singh and Felix Schrader and Andreas Vollmer and Norbert Kübler and Christoph Sproll and Lara Schorn},
journal = {Clinical oral investigations},
year = {2026},
month = oct,
doi = {10.1007/s00784-026-07214-x},
url = {https://europepmc.org/article/MED/42875660},
note = {CC BY},
}
RIS
TY - JOUR
TI - Development and external validation of an AI pipeline for automated estimation of a radiographic DMFT (rDMFT) score from panoramic radiographs: a feasibility study.
AU - Babak Saravi
AU - Veronika Shavlokhova
AU - Ashraf Türky
AU - Daman Deep Singh
AU - Felix Schrader
AU - Andreas Vollmer
AU - Norbert Kübler
AU - Christoph Sproll
AU - Lara Schorn
PY - 2026
DA - 2026/10/15
JO - Clinical oral investigations
DO - 10.1007/s00784-026-07214-x
UR - https://europepmc.org/article/MED/42875660
AB - 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.
SN - 1432-6981
SN - 1436-3771
ER -