Systematic Review of AI-Based Metal Artifact Reduction Algorithms in Dental Cone-Beam CT

A systematic review of seven studies (2015–2025) examined AI-driven metal artifact reduction algorithms for dental CBCT. No pooled diagnostic accuracy or image quality metrics were reported in the abstract.

• Seven studies (experimental, retrospective, phantom) were included, using deep learning architectures like U-Net variants.
• The review aimed to assess improvement in image quality and diagnostic reliability in scans with metallic restorations, implants, or orthodontic appliances.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.