EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Development and evaluation of an AI model for dental implant type detection: A comparison of diagnostic accuracy between a deep learning model and dental professionals

Walaa Magdy Ahmed iD, Amr Ahmed Azhari iD, Abdulrahman Almufti, Zainab Majed Alsadah, Amr Fawzy Abdelhamid Ahmed, Anas Lahiq iD, Khaled Ahmed Fawaz iD

Journal of Prosthodontics · 2026

DOI: 10.1111/jopr.70064 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Journal of Prosthodontics, 2026. Verfasst von Walaa Magdy Ahmed und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Restorative Dentistry, Faculty of Dentistry, King Abdulaziz University, Jeddah, Saudi Arabia. Hauptthemen laut MEDLINE: Deep Learning, Dental Implants, Dentists, Artificial Intelligence. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To develop a deep‐learning system for identifying five dental implant brands from periapical radiographs and compare its diagnostic accuracy with dental professionals and evaluate successive You Only Look Once (YOLO) architectures (v7–v12) to justify model selection. Materials and Methods A dataset of 5851 periapical radiographs was compiled and divided into training, validation, and test partitions (80/10/10). After filtering to five brands (Adin, Dentium, Noris, OSSTEM, and Straumann), YOLO‐based object detection models (versions 7–12) were trained and tested under identical conditions. The YOLOv12x model was adopted for final evaluation based on its optimal balance of accuracy and inference speed. Human performance was assessed using 100 held‐out test images (20 per brand) via a multiple‐choice web survey distributed to six clinician groups. Diagnostic metrics included mean average precision at IoU 0.50 (mAP@50), mAP@50–95, precision, recall, and accuracy.

Results

The model achieved an mAP@50 of 0.989 (98.9%), an mAP@50–95 of 0.900 (90.0%), a precision of 0.969 (96.9%), and a recall of 0.977 (97.7%) across brands. Across YOLO generations, performance improved from mAP@50–95 = 0.817 (YOLOv7) to 0.905 (YOLOv12x). Fifty‐two clinicians completed 5,200 image evaluations; the model significantly outperformed all clinician subgroups (one‐way ANOVA with Tukey HSD, p < 0.001). Transformer‐based DF‐DETR achieved mAP@50–95 = 0.878, confirming YOLOv12x's superior efficiency–accuracy trade‐off.

Conclusions

A high‐performing model identified implant brands on periapical radiographs and outperformed clinicians across experience levels. Comparative analysis across YOLO architectures validated its measurable advantage in accuracy and speed. Lack of external validation and dataset imbalance are important limitations; future work will include external, multisite data and human–AI workflow evaluation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningDental ImplantsDentistsArtificial IntelligenceHumansRadiography, Dental

Stichwörter der Autor:innen

Deep Learning ModelYOLOv12dental implantdental professionals

Substanzen

Dental Implants

Autor:innen und Institutionen

  • Department of Restorative Dentistry, Faculty of Dentistry, King Abdulaziz University, Jeddah, Saudi Arabia.
  • Master Prosthodontic Program, Faculty of Dentistry, Riyadh Elm University, Riyadh, Saudi Arabia.
  • Dental Department, East Jeddah General Hospital, Ministry of Health, Jeddah, Saudi Arabia.
  • Department Artificial Intelligence, Tachyhealth Company, Lewes, Delaware, USA.
  • Department of Prosthodontics, Aseer Dental Specialized Center, Abha, Saudi Arabia.
  • Department of Orthopedic Surgery, Faculty of Medicine, Cairo University, Cairo, Egypt.

ORCID-Profile: Walaa Magdy Ahmed, Amr Ahmed Azhari, Anas Lahiq, Khaled Ahmed Fawaz

Zitieren

APA

Ahmed, W. M., Azhari, A. A., Almufti, A., Alsadah, Z. M., Ahmed, A. F. A., Lahiq, A., & Fawaz, K. A. (2026). Development and evaluation of an AI model for dental implant type detection: A comparison of diagnostic accuracy between a deep learning model and dental professionals. Journal of Prosthodontics. https://doi.org/10.1111/jopr.70064

Vancouver

Ahmed WM, Azhari AA, Almufti A, Alsadah ZM, Ahmed AFA, Lahiq A, et al. Development and evaluation of an AI model for dental implant type detection: A comparison of diagnostic accuracy between a deep learning model and dental professionals. Journal of Prosthodontics. 2026. doi:10.1111/jopr.70064

BibTeX
@article{Ahmed2026,
  author = {Ahmed, Walaa Magdy and Azhari, Amr Ahmed and Almufti, Abdulrahman and Alsadah, Zainab Majed and Ahmed, Amr Fawzy Abdelhamid and Lahiq, Anas and Fawaz, Khaled Ahmed},
  title = {Development and evaluation of an AI model for dental implant type detection: A comparison of diagnostic accuracy between a deep learning model and dental professionals},
  journal = {Journal of Prosthodontics},
  year = {2026},
  doi = {10.1111/jopr.70064}
}
Kostenlos starten →