Dental implant brand and angle identification using deep neural networks

Artificial neural networks development in prosthodontics - a systematic mapping review

OBJECTIVES

This study aimed to systematically categorize the available literature and offer a comprehensive overview of artificial neural network (ANN) prediction models in prosthodontics. Specifically, the present research introduces a systematic analysis of ANN aims, data, architectures, evaluation metrics, and limitations in prosthodontics.

DATA

The review included articles published until June 2024. The search terms included "prosthodontics" (and related MeSH terms), "neural networks", and "deep learning". Out of 597 identified articles, 70 reports remained after deduplication and screening (2007-2024). Of these, 33 % were from 2023. Implant prosthodontics was the focus in approximately 29 % of reports, and non-implant prosthodontics in 71 %.

SOURCES

Data were collected through electronic searches of PubMed MedLine, PubMed Central, ScienceDirect, Web of Science, and IEEE Xplore databases, along with manual searches in specific journals.

STUDY SELECTION

This study focused on English-language research articles and conference proceedings detailing the development and implementation of ANN prediction models specifically designed for prosthodontics.

CONCLUSIONS

This study shows how ANN models are used in implant and non-implant prosthodontics, with various types of data, architectures, and metrics used for their development and evaluation. It also reveals limitations in ANN development, particularly in the data lifecycle.

CLINICAL SIGNIFICANCE

This study equips practitioners with insights, guiding them in optimizing clinical protocols through ANN integration and facilitating informed decision-making on commercially available systems. Additionally, it supports regulatory efforts, smoothing the path for AI integration in dentistry. Moreover, it sets a trajectory for future exploration, identifying untapped tools and research avenues, fostering interdisciplinary collaborations, and driving innovation in the field.

Deep learning in the overall process of implant prosthodontics: A state-of-the-art review

Artificial intelligence represented by deep learning has attracted attention in the field of dental implant restoration. It is widely used in surgical image analysis, implant plan design, prosthesis shape design, and prognosis judgment. This article mainly describes the research progress of deep learning in the whole process of dental implant prosthodontics. It analyzes the limitations of current research, and looks forward to the future development direction.

Two-step deep learning models for detection and identification of the manufacturers and types of dental implants on panoramic radiographs

The purpose of this study is to develop two-step deep learning models that can automatically detect implant regions on panoramic radiographs and identify several types of implants. A total of 1,574 panoramic radiographs containing 3675 implants were included. The implant manufacturers were Kyocera, Dentsply Sirona, Straumann, and Nobel Biocare. Model A was created to detect oral implants and identify the manufacturers using You Only Look Once (YOLO) v7. After preparing the image patches that cropped the implant regions detected by model A, model B was created to identify the implant types per manufacturer using EfficientNet. Model A achieved very high performance, with recall of 1.000, precision of 0.979, and F1 score of 0.989. It also had accuracy, recall, precision, and F1 score of 0.98 or higher for the classification of the manufacturers. Model B had high classification metrics above 0.92, exception for Nobel's class 2 (Parallel). In this study, two-step deep learning models were built to detect implant regions, identify four manufacturers, and identify implant types per manufacturer.

Identification of dental implant systems from low-quality and distorted dental radiographs using AI trained on a large multi-center dataset

Most artificial intelligence (AI) studies have attempted to identify dental implant systems (DISs) while excluding low-quality and distorted dental radiographs, limiting their actual clinical use. This study aimed to evaluate the effectiveness of an AI model, trained on a large and multi-center dataset, in identifying different types of DIS in low-quality and distorted dental radiographs. Based on the fine-tuned pre-trained ResNet-50 algorithm, 156,965 panoramic and periapical radiological images were used as training and validation datasets, and 530 low-quality and distorted images of four types (including those not perpendicular to the axis of the fixture, radiation overexposure, cut off the apex of the fixture, and containing foreign bodies) were used as test datasets. Moreover, the accuracy performance of low-quality and distorted DIS classification was compared using AI and five periodontists. Based on a test dataset, the performance evaluation of the AI model achieved accuracy, precision, recall, and F1 score metrics of 95.05%, 95.91%, 92.49%, and 94.17%, respectively. However, five periodontists performed the classification of nine types of DISs based on four different types of low-quality and distorted radiographs, achieving a mean overall accuracy of 37.2 ± 29.0%. Within the limitations of this study, AI demonstrated superior accuracy in identifying DIS from low-quality or distorted radiographs, outperforming dental professionals in classification tasks. However, for actual clinical application of AI, extensive standardization research on low-quality and distorted radiographic images is essential.

Advancements in artificial intelligence algorithms for dental implant identification: A systematic review with meta-analysis

STATEMENT OF PROBLEM

The evidence regarding the application of artificial intelligence (AI) in identifying dental implant systems is currently inconclusive. The available studies present varying results and methodologies, making it difficult to draw definitive conclusions.

PURPOSE

The purpose of this systematic review with meta-analysis was to comprehensively analyze and evaluate articles that investigate the application of AI in identifying and classifying dental implant systems.

MATERIAL AND METHODS

An electronic systematic review was conducted across 3 databases: MEDLINE/PubMed, Cochrane, and Scopus. Additionally, a manual search was performed. The inclusion criteria consisted of peer-reviewed studies investigating the accuracy of AI-based diagnostic tools on dental radiographs for identifying and classifying dental implant systems and comparing the results with those obtained by expert judges using manual techniques-the search strategy encompassed articles published until September 2023. The Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool was used to assess the quality of included articles.

RESULTS

Twenty-two eligible articles were included in this review. These articles described the use of AI in detecting dental implants through conventional radiographs. The pooled data showed that dental implant identification had an overall accuracy of 92.56% (range 90.49% to 94.63%). Eleven studies showed a low risk of bias, 6 demonstrated some concern risk, and 5 showed a high risk of bias.

CONCLUSIONS

AI models using panoramic and periapical radiographs can accurately identify and categorize dental implant systems. However, additional well-conducted research is recommended to identify the most common implant systems.