SBRF-Det: Scale-Boundary Representative Fusion for Multi-Finding Detection in Panoramic Dental Radiographs
Diagnostics · 08.10.2026 · 16 (19) · 3259
DOI: 10.3390/diagnostics16193259 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 08.10.2026. Verfasst von Furkan Karatas und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Prosthetic Dentistry, Faculty of Dentistry, Igdir University, Igdir 76000, Turkey. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Panoramic dental radiographs frequently contain multiple coexisting pathological, anatomical, and treatment-related findings that vary in scale, contrast, and boundary definition. Although recent one-stage detectors provide strong performance, reliable localization of small or weakly defined findings remains challenging.
Methods
We propose SBRF-Det, a one-stage multi-finding detector integrating scale-dependent representative allocation with boundary-conditioned local–global feature fusion at P4/16. The method was evaluated on OralXrays-9, comprising 12,688 panoramic radiographs and 84,099 retained annotations across nine categories, using a fixed 2688-image hold-out cohort. Twenty-two detector configurations were compared under a common protocol, and A0–A2 were further assessed using three independent seeds and paired radiograph-level bootstrap analysis.
Results
SBRF-Det achieved 0.8777 precision, 0.8979 recall, 0.9152 mAP50, and 0.7029 mAP50-95. Relative to the matched YOLO12l baseline, mAP50-95 increased by 0.95 percentage points. Performance remained class dependent, with apical periodontitis reaching 0.4526 mAP50-95 versus 0.8401–0.8842 for implants, porcelain crowns, and ceramic bridges. SBRF-Det used 93.06 GFLOPs versus 95.99 for A0, but inference latency increased from 5.946 to 8.851 ms/image. Three-seed experiments preserved the A0–A1–A2 ordering, while paired bootstrap intervals for A2–A0 and A2–A1 excluded zero.
Conclusions
SBRF-Det improves strict localization through representative and boundary-aware feature modeling, but the gain is modest and introduces a runtime trade-off. Patient-linked, multi-center, and reader-centered validation remains necessary before clinical deployment.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Prosthetic Dentistry, Faculty of Dentistry, Igdir University, Igdir 76000, Turkey.
- Department of Prosthetic Dentistry, Faculty of Dentistry, Ataturk University, Erzurum 25240, Turkey.
- Department of Computer Engineering, Faculty of Engineering and Architecture, Bitlis Eren University, Bitlis 13000, Turkey.
- Department of Health Information Management and Technology, College of Applied Medical Sciences, King Faisal University, Al-Ahsa 31982, Saudi Arabia.
- Department of Software Engineering, Faculty of Engineering and Natural Sciences, Istanbul Topkapi University, Istanbul 34000, Turkey.
- Department of Computer Engineering, Faculty of Engineering, Igdir University, Igdir 76000, Turkey.
ORCID-Profile: Furkan Karatas, Omer Aslan, Mehmet Burukanli, Shahid Mohammad Ganie, Merve Ersoy, Faruk Ozger, Ishak Pacal
Zitieren
APA
Karatas, F., Aslan, O., Burukanli, M., Ganie, S. M., Ersoy, M., Ozger, F., & Pacal, I. (2026). SBRF-Det: Scale-Boundary Representative Fusion for Multi-Finding Detection in Panoramic Dental Radiographs. Diagnostics, 16(19), 3259. https://doi.org/10.3390/diagnostics16193259
Vancouver
Karatas F, Aslan O, Burukanli M, Ganie SM, Ersoy M, Ozger F, et al. SBRF-Det: Scale-Boundary Representative Fusion for Multi-Finding Detection in Panoramic Dental Radiographs. Diagnostics. 2026;16(19):3259. doi:10.3390/diagnostics16193259
BibTeX
@article{Karatas2026,
author = {Karatas, Furkan and Aslan, Omer and Burukanli, Mehmet and Ganie, Shahid Mohammad and Ersoy, Merve and Ozger, Faruk and Pacal, Ishak},
title = {SBRF-Det: Scale-Boundary Representative Fusion for Multi-Finding Detection in Panoramic Dental Radiographs},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {19},
pages = {3259},
doi = {10.3390/diagnostics16193259}
}
EUVIMED