
This research evaluates the diagnostic accuracy of an AI model based on U²-Net architecture for detecting periapical lesions in dental panoramic radiographs. Using 400 anonymized radiographs, the model achieved a Dice score of 0.8 and strong precision (0.82), recall (0.77), and F1-score (0.8). The findings suggest that AI can serve as a valuable adjunct tool for clinicians in diagnosing periapical radiolucencies and enhancing clinical workflow.
Like
Save
Share