DMF-T assessment on panoramic images using deep learning-based convolutional neural network algorithm
5 affiliations
- 1Department of Oral and Maxillofacial Radiology, Izmir Tinaztepe University School of Dentistry
- 2Private dentist at Sigma Dental Clinic
- 3Department of Computer Sciences, Karadeniz Technical University School of Science
- 4Department of Oral and Maxillofacial Radiology, Ege University School of Dentistry
- 5Department of Engineering Sciences, Izmir Katip Celebi University School of Engineering and Architecture
Abstract
Automated, image-based evaluation of oral health indices can improve diagnostic consistency and support large-scale surveillance of dental disease. Leveraging recent advances in deep learning–based object detection, this study investigates a convolutional neural network approach for quantifying the Decayed, Missing, and Filled Teeth (DMFT) index from panoramic radiographs. A total of 1,316 anonymized digital panoramic images from patients aged > 18 years were retrospectively collected and annotated according to World Health Organization criteria. Using the FDI numbering system, teeth were labeled as Healthy, Decayed, or Filled, and Missing teeth were identified by comparison with a complete 32-tooth reference framework. The dataset was randomly partitioned into training, validation, and test subsets. For automated tooth-level analysis, a YOLOv11-based CNN object detection framework was implemented to simultaneously detect and classify individual teeth on panoramic images. Model performance was assessed using precision, recall, F1-score, mean average precision (mAP), and missing-tooth detection accuracy. The YOLOv11-based model achieved high overall performance for automated DMFT assessment ([email protected] = 0.839; F1-score = 0.819). Classification performance was highest for Filled teeth, whereas detection and classification of Decayed teeth were comparatively less accurate. Missing teeth were identified with an accuracy of 95.48%. These findings indicate that the proposed YOLOv11-based framework provides reliable, tooth-level DMFT estimation from panoramic radiographs and has potential as a decision-support tool for epidemiological surveillance and clinical practice. Further methodological optimization is warranted to enhance early caries detection performance.
Related
- Interpretable attention-deficit hyperactivity disorder diagnosis from functional magnetic resonance imaging via hybrid convolutional neural network–transformer learning and multi-level graph-based comprehensibility
- SCN security situation assessment and prediction model based on improved selective convolutional network
- Deep Learning-Based Classification of Melanoma Using Dermoscopic Images: Comparative Evaluation of Convolutional Neural Network and DenseNet Models.
- A novel morphological assessment approach for abdominal aortic aneurysms: automated segmentation and measurement using a semi-supervised deep learning algorithm
- Evaluation of the Position of Impacted Maxillary Canines on Panoramic Radiographs Using Deep Learning with CBCT as the Reference Standard
BibTeX
@article{aslan2026dmft,
title = {{DMF-T assessment on panoramic images using deep learning-based convolutional neural network algorithm}},
author = {Elif Aslan and Ali Canberk Ulusoy and Onur Mutlu and Erinc Onem and Elif Sener and Ali Mert and B. Guniz Baksi},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-63568-y},
url = {https://doi.org/10.1038/s41598-026-63568-y},
note = {CC BY},
}
RIS
TY - JOUR
TI - DMF-T assessment on panoramic images using deep learning-based convolutional neural network algorithm
AU - Elif Aslan
AU - Ali Canberk Ulusoy
AU - Onur Mutlu
AU - Erinc Onem
AU - Elif Sener
AU - Ali Mert
AU - B. Guniz Baksi
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-63568-y
UR - https://doi.org/10.1038/s41598-026-63568-y
AB - Automated, image-based evaluation of oral health indices can improve diagnostic consistency and support large-scale surveillance of dental disease. Leveraging recent advances in deep learning–based object detection, this study investigates a convolutional neural network approach for quantifying the Decayed, Missing, and Filled Teeth (DMFT) index from panoramic radiographs. A total of 1,316 anonymized digital panoramic images from patients aged > 18 years were retrospectively collected and annotated according to World Health Organization criteria. Using the FDI numbering system, teeth were labeled as Healthy, Decayed, or Filled, and Missing teeth were identified by comparison with a complete 32-tooth reference framework. The dataset was randomly partitioned into training, validation, and test subsets. For automated tooth-level analysis, a YOLOv11-based CNN object detection framework was implemented to simultaneously detect and classify individual teeth on panoramic images. Model performance was assessed using precision, recall, F1-score, mean average precision (mAP), and missing-tooth detection accuracy. The YOLOv11-based model achieved high overall performance for automated DMFT assessment ([email protected] = 0.839; F1-score = 0.819). Classification performance was highest for Filled teeth, whereas detection and classification of Decayed teeth were comparatively less accurate. Missing teeth were identified with an accuracy of 95.48%. These findings indicate that the proposed YOLOv11-based framework provides reliable, tooth-level DMFT estimation from panoramic radiographs and has potential as a decision-support tool for epidemiological surveillance and clinical practice. Further methodological optimization is warranted to enhance early caries detection performance.
SN - 2045-2322
ER -