In vitro evaluation of AI-assisted CBCT analysis for detecting additional canals in mandibular premolars

TL;DR

This study shows that AI can help detect extra canals in teeth more accurately and quickly than specialists.

Contribution

The novel contribution is demonstrating AI's superior performance in detecting additional canals in mandibular premolars using CBCT.

Findings

AI system showed higher sensitivity (86.8%) and accuracy (90.0%) than specialists.

AI interpretation time was less than three seconds per case.

AI-based CBCT analysis is a rapid and reliable tool for endodontic planning.

Abstract

Failure to detect additional canals in mandibular premolars can compromise endodontic treatment outcomes. Hence, this in vitro
study compared an artificial intelligence-assisted CBCT analysis system with endodontic specialists for detecting additional canals, using
micro-CT as the gold standard. One hundred and fifty mandibular premolars were analyzed. The AI system demonstrated higher sensitivity
(86.8%) and accuracy (90.0%) than specialists, with comparable specificity and interpretation time of less than three seconds per case.
Thus, AI-based CBCT analysis appears to be a rapid and reliable adjunct for improved canal detection and preoperative endodontic
planning.