Accuracy of transfer learning in predicting peri-implantitis onset from intraoral radiograph: A multi-center longitudinal retrospective study
Clinical Oral Investigations · 19.10.2026 · 30 (11)
DOI: 10.1007/s00784-026-07181-3 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Clinical Oral Investigations, online erschienen am 19.10.2026. Verfasst von Muhammad H A Saleh und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Periodontics and Oral Medicine, University of Michigan School of Dentistry, Ann Arbor, MI, USA. muhsaleh@umich.edu. Hauptthemen laut MEDLINE: Peri-Implantitis, Radiography, Dental. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
The growing application of artificial intelligence in dentistry has opened new opportunities for predicting peri-implantitis (PI) using convolutional neural networks (CNNs). Transfer learning, where knowledge from a model pre-trained on a large dataset is adapted to a new, domain-specific task, may enhance performance, particularly when medical datasets are limited. This study evaluated the ability of several pre-trained CNN architectures applied to baseline 2D intraoral radiographs to predict peri-implantitis onset.
Methods
A retrospective multi-center study was conducted at the University of Michigan and King’s College London. A total of 195 implants (146 from Michigan and 49 from London) placed in 108 maintained patients were included. For each implant, a baseline periapical radiograph taken up to one year after prosthetic restoration was analyzed. Five pre-trained CNN architectures (ResNet50, DenseNet, VGG16, InceptionV3, EfficientNet) were combined with four transfer learning strategies: feature extraction (hybrid and non-hybrid), partial fine-tuning (50% of layers), and full fine-tuning. Models were trained using patient-wise splits to avoid leakage, and performance was evaluated on an independent test set using accuracy, area under the ROC curve (AUC), sensitivity, and specificity.
Results
All CNN architectures showed variable performance across transfer learning strategies. The non-hybrid feature extraction approach provided the most consistent discrimination, with the best models achieving AUC values between 0.74 and 0.83. InceptionV3 reached the highest AUC (0.83). Fine-tuning strategies yielded modest or low performance, with AUCs generally ranging from 0.42 to 0.69 across architectures.
Conclusion
Non-hybrid feature extraction applied to pre-trained CNNs showed the most promising, though moderate, performance for predicting PI onset from baseline intraoral radiographs. These findings indicate that transfer learning may assist early risk stratification in implant dentistry, but larger prospective studies are needed before clinical adoption. Clinical relevance Deep learning models may serve as adjunctive tools to identify implants at higher risk for future PI based on routine baseline radiographs, supporting more individualized maintenance protocols and earlier preventive interventions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Periodontics and Oral Medicine, University of Michigan School of Dentistry, Ann Arbor, MI, USA. muhsaleh@umich.edu.
- Centre for Host Microbiome Interactions, Faculty of Dentistry, Oral and Craniofacial Sciences, King's College London, London, UK.
- Department of Periodontics and Oral Medicine, University of Michigan School of Dentistry, Ann Arbor, MI, USA.
- Department of Oral Medicine, Oral Pathology, Oral and Maxillofacial Surgery, University of Tripoli School of Dentistry, Tripoli, Libya.
- Department of Clinical and Experimental Medicine, University of Foggia, Foggia, 71122, Italy.
- Department of Medicine and Surgery, LUM University, Casamassima, 70010, Italy. troiano@lum.it.
Zitieren
APA
Saleh, M. H. A., Nibali, L., Alrmali, A. E., Caponio, V. C. A., Santamaria, P., Fanelli, F., Zhurakivska, K., Wang, H. L., & Troiano, G. (2026). Accuracy of transfer learning in predicting peri-implantitis onset from intraoral radiograph: A multi-center longitudinal retrospective study. Clinical Oral Investigations, 30(11). https://doi.org/10.1007/s00784-026-07181-3
Vancouver
Saleh MHA, Nibali L, Alrmali AE, Caponio VCA, Santamaria P, Fanelli F, et al. Accuracy of transfer learning in predicting peri-implantitis onset from intraoral radiograph: A multi-center longitudinal retrospective study. Clinical Oral Investigations. 2026;30(11). doi:10.1007/s00784-026-07181-3
BibTeX
@article{Saleh2026,
author = {Saleh, Muhammad H A and Nibali, Luigi and Alrmali, Abdusalam E and Caponio, Vito Carlo Alberto and Santamaria, Pasquale and Fanelli, Francesco and Zhurakivska, Khrystyna and Wang, Hom-Lay and Troiano, Giuseppe},
title = {Accuracy of transfer learning in predicting peri-implantitis onset from intraoral radiograph: A multi-center longitudinal retrospective study},
journal = {Clinical Oral Investigations},
year = {2026},
volume = {30},
number = {11},
doi = {10.1007/s00784-026-07181-3}
}
EUVIMED