EUVIMEDΑνακαλύψτε το EUVIMED
Crossref

Detection of Dens Invaginatus on Panoramic Radiographs Using Deep Learning Algorithms

Esra Nur Akgül iD, Burcu Gucyetmez Topal iD

International Journal of Paediatric Dentistry · 2026-01 · 36 (1) · 59-66

DOI: 10.1111/ipd.70027 ↗

At a glance

Journal article in International Journal of Paediatric Dentistry, published online on 2025-08-03. Written by Esra Nur Akgül and 1 co-authors. Institution: Faculty of Dentistry, Department of Paediatric Dentistry, Afyonkarahisar Health Sciences University, Afyonkarahisar, Turkey. Major MEDLINE topics: Deep Learning, Radiography, Panoramic, Dens in Dente. Cited 3 times so far (Crossref); 27 references. Funded by: Afyonkarahisar Health Sciences University Scientific Research Project Management Unit.

ΠερίληψηSubjectsΒιβλιογραφικά στοιχείαCiteRelated studies

Abstract (original language)

Background

Dens invaginatus is a developmental dental anomaly characterized by enamel folding into the dental papilla during odontogenesis. Early detection allows for appropriate management and reduces the risk of complex treatments.

Aim

This study aimed to evaluate the success and reliability of YOLOv5 and YOLOv8 deep learning models with two different labeling methods for the detection of teeth with dens invaginatus in panoramic radiographs.

Design

In this study, 656 panoramic radiographs of patients aged 8 to 18 were labeled for teeth with dens invaginatus in the anterior region using segmentation and detection methods. The labeling of the images was performed using the CranioCatch software (Eskişehir, Turkey) by two pediatric dentists.

Results

The YOLOv5 model achieved a precision, sensitivity, and F 1‐score of 0.945, 0.887, and 0.915 for detection, and 0.905, 0.928, and 0.916 for segmentation, respectively. The precision, sensitivity, and F 1‐score of the YOLOv8 model with the detection method were 0.950, 1, and 0.974, respectively, while these values were 0.940, 0.994, and 0.966 for the segmentation method.

Conclusion

It was observed that the YOLO models were successful in detecting dens invaginatus. It is believed that deep learning‐supported systems could be integrated into pediatric dentistry practice and serve as a decision support mechanism.

Subjects

MeSH terms (MEDLINE)

Deep LearningRadiography, PanoramicDens in DenteHumansAdolescentChildMaleAlgorithmsFemaleReproducibility of Results

Author keywords

YOLOartificial intelligencedens invaginatuspanoramic radiography

Authors and institutions

  • Faculty of Dentistry, Department of Paediatric Dentistry, Afyonkarahisar Health Sciences University, Afyonkarahisar, Turkey.

ORCID profiles: Esra Nur Akgül, Burcu Gucyetmez Topal

Funding

  • Afyonkarahisar Health Sciences University Scientific Research Project Management Unit

Cite

APA

Akgül, E. N., & Gucyetmez Topal, B. (2026). Detection of Dens Invaginatus on Panoramic Radiographs Using Deep Learning Algorithms. International Journal of Paediatric Dentistry, 36(1), 59-66. https://doi.org/10.1111/ipd.70027

Vancouver

Akgül EN, Gucyetmez Topal B. Detection of Dens Invaginatus on Panoramic Radiographs Using Deep Learning Algorithms. International Journal of Paediatric Dentistry. 2026;36(1):59-66. doi:10.1111/ipd.70027

BibTeX
@article{Akgl2026,
  author = {Akgül, Esra Nur and Gucyetmez Topal, Burcu},
  title = {Detection of Dens Invaginatus on Panoramic Radiographs Using Deep Learning Algorithms},
  journal = {International Journal of Paediatric Dentistry},
  year = {2026},
  volume = {36},
  number = {1},
  pages = {59--66},
  doi = {10.1111/ipd.70027}
}
Start for free →