Deep Learning Applications in Prosthodontics: A Systematic Review Publisher



R Rokhshad RATA ; K Khosravi KAMYAR ; Pt Motie Parisa TAFAZOLI ; Ts Sadeghi Termeh SARRAFAN ; Am Tehrani Azita MAZAHERI ; A Zarbakhsh ARASH ; M Revillaleon MARTA
Source: Journal of Prosthetic Dentistry Published:2025

Abstract

Statement of problem: Deep learning (DL) has been applied to aid dental professionals in diagnosis, treatment planning, and fabricating prostheses. However, an overview and the status of the main DL applications in prosthodontics is lacking. Purpose: The purpose of this systematic review was to evaluate DL applications for inlays, onlays, and tooth-supported crowns and fixed dental prostheses (FDPs), by predicting restoration outcomes, optimizing prosthetic design, assisting treatment planning, improving color matching, and automating landmark detection for removable partial denture (RPD) design and facial changes after complete denture (CD) treatment. Material and methods: A systematic review was completed in 6 databases: PubMed, EMBASE, Scopus, Web of Science, arXiv, IEEE, and Google Scholar. A manual search was also conducted. Two investigators evaluated the studies independently using the JBI Critical Appraisal checklist. A third examiner was consulted to resolve any lack of consensus. The included articles were classified based on the DL application: identification of restorations, prediction of restoration outcomes (such as debonding, wear, fracture resistance, surface roughness, microhardness, and flexural strength), assistance in treatment planning, prostheses design and manufacturing, shade matching, landmark detection for RPD planning, and analysis of facial changes after CD treatment. Results: Of 3359 screened studies, 31 met the eligibility criteria for inclusion. Among these, 10 studies demonstrated a low risk of bias across all domains of the JBI checklist. Most of the reviewed studies were concentrated on the design and manufacturing of dental prostheses (n=13) and used a variety of deep learning applications with generation (n=11) as the predominant task. The Convolutional Neural Network (CNN) was the most utilized model, appearing in 11 studies, followed by Generative Adversarial Networks (GAN) in 7 studies. Among the restorations considered, tooth-supported crowns were the most frequently assessed (n=14). Regarding data modalities, intraoral scanners (IOSs) were the most utilized in the studies (n=16). The highest accuracy of 99.4% for identifying gold restorations and the lowest accuracy of 60% for detecting an onlay and other restoration designs were reported. Based on the included studies, sensitivity ranged from 88.6% to 100%, and Intersection over Union (IoU) ranged from 60% to 90%. Conclusions: DL in prosthodontics, especially concerning prosthesis design and manufacturing, demonstrates significant potential. However, the standardization of methodologies and rigorous validation are essential to ensure the reliable and widespread clinical adoption of these DL-driven approaches. © 2025 Elsevier B.V., All rights reserved.