Detection of Periapical Lesions on Dental Panoramic Images Based on Artificial Intelligence Using Cone Beam Computed Tomography

What this Trial Is About

This research focuses on improving the early detection of periapical lesions, which are dental injuries visible as radiolucent areas on dental images. These lesions can lead to serious local and systemic health problems, including infections and diseases affecting the heart, kidneys, and tendons. The study aims to develop an artificial intelligence (AI) algorithm to better identify these lesions using panoramic dental radiographs, which are commonly used but less sensitive than 3D imaging techniques like cone-beam computed tomography (CBCT). The study evaluates an AI system trained on both panoramic dental images and CBCT scans taken within three months of each other. The AI algorithm builds upon previous work and uses advanced learning techniques to enhance detection accuracy. The project compares the performance of panoramic radiography, retroalveolar radiography, and CBCT, with CBCT considered the gold standard. This approach seeks to maintain the benefit of panoramic imaging's lower radiation and broader view while improving lesion detection. Participants in the study have both panoramic dental images and CBCT scans taken within three months. Researchers analyze these images using the AI software to measure how well it detects periapical lesions, focusing on accuracy and specificity over a two-year period. The study also looks at the potential for earlier diagnosis to improve care, especially for groups like military personnel and athletes. Participants' involvement includes image review and data analysis, with the aim to advance diagnostic tools in dental health.

Detection of Periapical Lesions on Dental Panoramic Radiographs Based on Artificial Intelligence