Detection of interproximal recurrent caries on bitewing radiographs using artificial intelligence Based on Deep Learning

Rationale for the Project Implementation

Secondary caries is a common concern for oral health that affects individuals worldwide. Despite advancements in preventive dentistry, secondary caries continues to have a high incidence, and the diagnosis of secondary caries, particularly in interproximal areas, remains a clinical challenge. Bitewing radiography is commonly used in dentistry for detecting caries, but the accuracy of visual interpretation varies among dentists, and this lack of consensus can lead to missed diagnoses or overestimation of caries, resulting in excessive costs for patients. Early detection of secondary caries is crucial to prevent further tooth decay and ensure a favorable prognosis. In recent years, artificial intelligence (AI) has emerged as a promising tool for automating medical image analysis, offering potential solutions to improve diagnostic accuracy and efficiency. However, there have been few studies examining the ability of AI to detect secondary caries. The most recent study in the field used the YOLOv5 model, which is six generations older than YOLOv11, which is expected to provide higher diagnostic accuracy. This study aims to develop and validate one of the latest AI-based algorithms for detecting secondary interproximal caries in bitewing radiography, with the goal of improving early diagnosis and treatment planning in dental caries management to assist dentists in making accurate diagnoses and preventing both underdiagnosis and overdiagnosis.

Principal Investigator: Dr. Farzaneh Samavat
Start Year: 2025