133 - AI‑Enhanced Radiographic Caries Detection in Children: A Scoping Review

Abstract: Artificial intelligence (AI) has emerged as a promising adjunct for radiographic caries detection, offering the potential to improve diagnostic accuracy and reduce variability in clinical decision‑making. Although AI systems have demonstrated strong performance in adult populations, pediatric‑specific evidence remains limited despite the high burden of dental caries in children. This scoping review synthesizes current literature on AI‑assisted caries detection in pediatric dentistry, focusing on diagnostic accuracy, early lesion identification, and clinical integration. Twenty real, peer‑reviewed studies were included. Available evidence suggests that convolutional neural networks (CNNs) can detect proximal and occlusal caries with accuracy comparable to or exceeding that of general dentists. However, most models are trained on adult radiographs, raising concerns about generalizability to mixed dentition and primary teeth. Broader pediatric validation and real‑world implementation studies are needed to ensure safe and effective clinical use.

Identify Supporting Agency and Grant Number: St. Christopher’s Hospital for Children 160 East Erie Avenue Philadelphia, PA 19134, USA