AI-Enhanced CBCT for Quantifying Orthodontic Root Resorption: Evidence from a Systematic Review and a Clinical Case of Severe Bilateral Canine Impaction

Abstract

Background: Artificial intelligence (AI) integrated with cone-beam computed tomography (CBCT) has rapidly advanced the diagnostic capability of orthodontics, particularly for quantifying external root resorption (ERR). High-risk scenarios such as bilateral maxillary canine impaction require objective tools to guide treatment decisions and prevent irreversible damage. Objectives: To evaluate the diagnostic accuracy and clinical applicability of AI-assisted CBCT for orthodontically induced ERR, and to demonstrate its value in a complex clinical case where decision-making regarding canine traction versus extraction required precise risk quantification and definition of biological limits. Methods: A systematic review following PRISMA 2020 guidelines was conducted in PubMed, ScienceDirect, and Cochrane Library (2015–September 2025). Eligible studies applied AI-enhanced CBCT to assess ERR in orthodontic patients. Additionally, a clinical case with bilaterally impacted maxillary canines was evaluated using CBCT with automated AI segmentation and manual refinement to quantify root volume changes and determine prognostic thresholds for treatment modification. Results: Nine studies met the inclusion criteria. AI-based imaging, predominantly convolutional neural networks, showed high diagnostic accuracy (up to 94%), improving reproducibility and reducing operator dependency. In the clinical case, volumetric monitoring showed rapid progression of ERR in the lateral incisors (LI) associated with a persistent unfavorable 3D spatial relationship between the canines and incisor roots, despite controlled distal traction with skeletal anchorage, leading to a timely change in the treatment plan and extraction of the severely compromised incisors with substitution by the canines. AI-generated data provided objective evidence supporting safer decision-making and prevented further structural deterioration. Conclusions: AI-enhanced CBCT enables early, objective, and quantifiable ERR assessment, strengthening prognosis-based decisions in orthodontics. Findings of this review and the clinical case highlight the translational relevance of AI for managing high-risk cases, such as maxillary canine impaction with extensive LI resorption, supporting future predictive AI models for safer canine traction.