Potential and impact of artificial intelligence algorithms in dento-maxillofacial radiology

Abstract

Objectives: Novel artificial intelligence (AI) learning algorithms in dento-maxillofacial radiology (DMFR) are continuously being developed and improved using advanced convolutional neural networks. This review provides an overview of the potential and impact of AI algorithms in DMFR. Materials and methods: A narrative review was conducted on the literature on AI algorithms in DMFR. Results: In the field of DMFR, AI algorithms were mainly proposed for (1) automated detection of dental caries, periapical pathologies, root fracture, periodontal/peri-implant bone loss, and maxillofacial cysts/tumors; (2) classification of mandibular third molars, skeletal malocclusion, and dental implant systems; (3) localization of cephalometric landmarks; and (4) improvement of image quality. Data insufficiency, overfitting, and the lack of interpretability are the main issues in the development and use of image-based AI algorithms. Several strategies have been suggested to address these issues, such as data augmentation, transfer learning, semi-supervised training, few-shot learning, and gradient-weighted class activation mapping. Conclusions: Further integration of relevant AI algorithms into one fully automatic end-to-end intelligent system for possible multi-disciplinary applications is very likely to be a field of increased interest in the future. Clinical relevance: This review provides dental practitioners and researchers with a comprehensive understanding of the current development, performance, issues, and prospects of image-based AI algorithms in DMFR.