The use and performance of artificial intelligence applications in dental and maxillofacial radiology: A systematic review

Abstract

Objectives: To investigate the current clinical applications and diagnostic performance of artificial intelligence (AI) in dental and maxillofacial radiology (DMFR). Methods: Studies using applications related to DMFR to develop or implement AI models were sought by searching five electronic databases and four selected core journals in the field of DMFR. The customized assessment criteria based on QUADAS-2 were adapted for quality analysis of the studies included. Results: The initial electronic search yielded 1862 titles, and 50 studies were eventually included. Most studies focused on AI applications for an automated localization of cephalometric landmarks, diagnosis of osteoporosis, classification/segmentation of maxillofacial cysts and/or tumors, and identification of periodontitis/periapical disease. The performance of AI models varies among different algorithms. Conclusion: The AI models proposed in the studies included exhibited wide clinical applications in DMFR. Nevertheless, it is still necessary to further verify the reliability and applicability of the AI models prior to transferring these models into clinical practice.

Artificial intelligence in fixed implant prosthodontics: a retrospective study of 106 implant-supported monolithic zirconia crowns inserted in the posterior jaws of 90 patients

“…In the medical field, AI uses algorithms and software applications to approximate human cognition in the analysis of complex data, approaching levels of human expertise, changing the role of computer-assisted diagnosis from a 'second-opinion' tool to a more collaborative one [28]. The development of AI applications is already remarkable, particularly in radiology and 3D imaging, as an aid to human clinicians in diagnostic and treatment planning, and recently AI has been integrated into image processing software and CAD, with promising results [29].…”

“…AI systems can also be extremely useful in dentistry, as their common feature is that they need data to be processed to build algorithms useful for determining actions [17,18,28,29], and the dentist produces a large amount of digital data that can be extremely useful to take advantage of AI benefits [17].…”

Recent Trends and Future Direction of Dental Research in the Digital Era

“…The most valuable indication for the use of AI and ML in dentistry is the entire field of diagnostic imaging in dento-maxillofacial radiology [27,28]. Currently, applications and research in AI purposes in dental radiology focus on automated localization of cephalometric landmarks, diagnosis of osteoporosis, classification/segmentation of maxillofacial cysts and/or tumors, and identification of periodontitis/periapical disease.…”

Current Applications, Opportunities, and Limitations of AI for 3D Imaging in Dental Research and Practice

“…The methodological quality of the included studies was evaluated using the assessment criteria proposed by Hung et al [11]. For proposed AI models for diagnosis/classification of a certain condition, four studies [16][17][18][19] were rated as having a "high" or an "unclear" risk of concern in the domain of subject selection because the testing dataset only consisted of images from subjects with the condition of interest.…”

“…In the field of dental and maxillofacial radiology (DMFR), reports on AI models used for diagnostic purposes and treatment planning cover a wide range of clinical applications, including automated localization of craniofacial anatomical structures/pathological changes, classification of maxillofacial cysts and/or tumors, and diagnosis of caries and periodontal lesions [11]. According to the literature related to clinical applications of AI in DMFR, most of the proposed machine learning algorithms were developed using two-dimensional (2D) diagnostic images, such as periapical, panoramic, and cephalometric radiographs [11]. However, 2D images have several limitations, including image magnification and distortion, superimposition of anatomical structures, and the lack of three-dimensional information for relevant landmarks/pathological changes.…”