Deep Learning-Based Dental Caries Diagnosis on Panoramic Radiographies: Performance of YOLOv8 Versus Human Observers
: The YOLOv8x model achieved diagnostic performance comparable to less experienced clinicians in detecting dental caries on paediatric panoramic radiographs but did not reach expert-level accuracy. These findings suggest that deep learning models may serve as supportive tools in panoramic caries assessment rather than replacements for expert interpretation.
Authors
- Muhammed Enes Naralan (ORCID: https://orcid.org/0000-0002-2444-4322)
- A Nese Citak Kurt (ORCID: https://orcid.org/0000-0002-7529-0116)
- İrem Okumuş (ORCID: https://orcid.org/0000-0003-1471-4605)
- Kader Biçengil (ORCID: https://orcid.org/0009-0002-5896-3056)
Institutions
- Recep Tayyip Erdoğan University (TR)
- Turkish Society of Hematology (TR)
Publication Details
- Journal
- Diagnostics
- Published
- 2026-04-13
- DOI
- https://doi.org/10.3390/diagnostics16081150
- Primary Topic
- Dental Radiography and Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00