1 Undergraduate Student, Department of Oral Medicine, Radiology, and Special Care Dentistry, Saveetha Dental College and Hospitals, Saveetha Institute of Dental and Technical Sciences (SIMATS), Saveetha University, Chennai.
2 Senior Lecturer, Department of Oral Medicine, Radiology, and Special Care Dentistry, Saveetha Dental College and Hospitals, Saveetha Institute of Dental and Technical Sciences (SIMATS), Saveetha University, Chennai.
Received: 20th Feb, 2026 | Revised: 4th Mar, 2026 | Accepted: 25th Mar, 2026 | Available Online: 10th Apr, 2026
Introduction: Dental implants have become a widely accepted treatment option for replacing missing teeth, with various implant systems available. Accurate identification of these systems is crucial for treatment planning, implant placement, and follow-up care. Currently, implant identification relies on manual interpretation of radiographs, which can be time-consuming and prone to errors. Recent advancements in artificial intelligence (AI) and machine learning offer opportunities to automate this process. This retrospective study aims to develop and evaluate an AI-based system for automatic identification of dental implant systems from digital Intraoral Periapical radiographs.
Materials and Method: A machine learning approach was used to detect the implant system using three different AI models: logistic regression, neural network, and Naïve Bayes algorithms in Orange software (University of Ljubljana, Slovenia). Performance evaluation was done using accuracy, sensitivity, specificity, precision, recall, F1 score, and AUC-ROC (area under the receiver operating characteristic) curve.
Results: Among the tested models, the neural network consistently delivered the best performance in terms of classification accuracy, AUC, and recall. The neural network achieved an accuracy of 94.2%, sensitivity of 92.8%, specificity of 95.6%, precision of 93.1%, recall of 92.8%, F1 score of 92.9%, and AUC-ROC of 0.971. Logistic regression achieved moderate performance with accuracy of 86.4%, while Naïve Bayes demonstrated the lowest performance with accuracy of 79.3%.
Conclusion: AI models showed high accuracy in the classification of the implant systems under investigation from the digital intraoral periapical (RVG) images and can be promising and reliable to incorporate in research and practice. The neural network model demonstrated superior performance, suggesting its potential as a clinical decision support tool for rapid and accurate dental implant identification.
Keywords: Precision, Ambiguous, Pioneered, Mastery, Dental Implants, Artificial Intelligence, Machine Learning, Radiograph Classification.
How to cite this article: Pragya S, Lokesh Kumar S. Automatic Identification of Dental Implant Systems from Digital Intraoral Periapical Radiographs - An AI Based Retrospective Study. Int J Drug Deliv Technol. 2026;16(29s):75-80. DOI: 10.25258/ijddt.16.29s.10
Source of support: Nil.
Conflict of interest: The authors declare no conflict of interest.