Clinical Validation of Deep Learning for Segmentation of Multiple Dental Features in Periapical Radiographs.

Periapical radiographs are routinely used in dental practice for diagnosis and treatment planning purposes. However, they often suffer from artifacts, distortions, and superimpositions, which can lead to potential misinterpretations. Thus, an automated detection system is required to overcome these challenges.

Automatic feature segmentation in dental panoramic radiographs.

Objective: The purpose of the present study was to verify the diagnostic performance of an AI system for the automatic detection of teeth, caries, implants, restorations, and fixed prosthesis on panoramic radiography.

Methods: This is a cross-sectional study. A dataset comprising 1000 panoramic radiographs collected from 500 adult patients was analyzed by an AI system and compared with annotations provided by two oral and maxillofacial radiologists.