Abstract

Recent advancements in deep learning have revolutionized the field of dental diagnostics, particularly in the detection and characterization of dental caries from radiographic images. Dental caries, a widespread oral health issue globally, necessitates precise and timely detection methods to mitigate its impact on patient health. Traditional diagnostic methods relying on visual inspection and radiographic imaging are subjective and prone to variability. In contrast, deep learning techniques offer a promising solution by automating detection processes through learned patterns from extensive datasets. This study proposes a comprehensive methodology utilizing state-of-the-art deep learning, specifically employing the YOLOv8.2.21 model for automatic detection and segmentation of dental caries from radiographs.