Artificial intelligence-based incisive canal visualization for preventing and detecting post-implant injury, using cone beam computed tomography

Abstract

The aim of this study was to clinically validate an artificial intelligence (AI)-based tool for automatic segmentation of the mandibular incisive canal (MIC) on cone beam computed tomography (CBCT), enabling prevention and detection of iatrogenic implant-related nerve injuries. Patient records from University Hospitals Leuven were screened for CBCT related to implant surgery cases with nerve injuries. CBCT scans were imported into Virtual Patient Creator for canal segmentation and 3D model generation. Two oral radiologists compared the AI-segmented canals with respective CBCT images. Five observers then performed canal identification and injury detection (present/absent) and reported their confidence level on a five-point Likert scale. Ten patient cases were assessed (eight female, two male; age 49–81 years). The AI-based tool enabled clear visualization of bilateral MIC in both pre- and postoperative images, revealing implant-canal relationships consistent with recorded post-implant pain or neural disturbance. For preoperative assessment, the AI-based tool significantly improved incisive canal detection (by 25%; P = 0.025) and observer confidence (by 8%; P = 0.038). The AI-based tool proved to be clinically useful to enable bilateral MIC visualization on CBCT images. Through canal segmentation with integrated 3D modelling, preoperative canal detection and the experts’ confidence level were significantly improved.