DEEP LEARNING FOR EARLY DETECTION OF DENTAL CARIES USING INTRAORAL IMAGES

Abstract

Abstract: Dental caries remains one of the most prevalent oral diseases worldwide, affecting individuals across all age groups. Early diagnosis of dental caries is essential to prevent tooth destruction, pain, and expensive restorative procedures. Traditional diagnostic methods such as visual examination and radiography are often subjective and dependent on clinician expertise. Recent advancements in Artificial Intelligence (AI), particularly Deep Learning (DL), have demonstrated significant potential in improving the accuracy and efficiency of caries detection using intraoral images. This research paper explores the application of deep learning models for the early detection of dental caries using intraoral imaging techniques. The study discusses various convolutional neural network (CNN) architectures, datasets, preprocessing methods, training procedures, performance evaluation metrics, advantages, limitations, and future directions. The paper also presents comparative tables highlighting the performance of different deep learning models in dental diagnostics. The findings indicate that deep learning systems can substantially enhance early caries detection and support dentists in clinical decision-making. Keywords: Deep Learning, Dental Caries, Intraoral Images, Artificial Intelligence, Convolutional Neural Networks, Oral Healthcare, Medical Imaging