To develop a deep learning model for diagnosing lesions associated with impacted third molars.
Developed a deep learning-based diagnostic tool.
Tested the tool in clinical settings.
Evaluated the model's performance against standard diagnostic practices.
The model demonstrated high accuracy in diagnosing second-molar lesions.
It served as an effective decision-support system, especially in limited resource environments.
Abstract
This DL-based diagnostic tool may serve as a valuable decision-support system, particularly in clinical settings with limited access to specialized dental expertise.