(TC33) External Cervical Resorption Detection Transformed: The Rise of Artificial Intelligence in Dental Imaging

Abstract: External cervical resorption (ECR) is a pathological process often discovered at advanced stages due to its asymptomatic nature. With cone beam computed tomography (CBCT) imaging becoming more accessible to dentists in the last decade, there has been a notable increase in incidental ECR findings. This observation is largely attributed to the limitations of 2-dimensional radiographs and restricted knowledge of its etiology. Recent advancements in artificial intelligence and machine learning have shown promising results in medical imaging. Deep convolutional neural networks (DCNNs) are a type of machine learning algorithm for computer vision. DCNNs have been successfully used for diagnosing oral diseases such as dental caries, periodontal diseases, and oral cancer. These AI models have demonstrated excellent performance in endodontics in identifying periapical lesions, apical foramen, root morphology, and curvature of the tooth for treatment planning. By enhancing diagnostic precision and aiding in treatment planning, these AI models contribute to more favorable treatment outcomes. The purpose of this table clinic is to propose the use of an AI algorithm that can assist clinicians in detecting all stages of ECR on intraoral radiographs, serving as a tool to help with developing a sound comprehensive treatment plan. This approach has the potential not only to assist in the early detection of lesions but also to facilitate their classification on 2-dimensional and 3-dimensional imaging and to predict their progression. Such capabilities are crucial for the effective management and treatment of ECR in the future.