<![CDATA[Dental panoramic image segmentation plays a crucial role in dental diagnosis, as it aids in the identification of dental conditions and other oral structures more quickly and accurately. However, manual segmentation processes are often time-consuming and require specialized expertise. Therefore, Artificial Intelligence (AI)-based technology presents a potential solution to enhance efficiency. This study aims to develop a deep learning algorithm for automatic segmentation of dental panoramic images. The model used was trained with 302 dental panoramic images across 32 classes, encompassing 9009 teeth. The segmentation process was carried out on the Roboflow platform, which provides evaluation metrics to assess the model’s performance. Evaluation results revealed a mean Average Precision (mAP) of 95%, recall of 93.1%, and precision of 93.7%, indicating a high level of accuracy in detecting and segmenting teeth. However, challenges arise in certain image conditions, such as teeth that are reduced to roots or teeth positioned abnormally. Overall, the model demonstrates significant potential to improve the efficiency and accuracy of dental panoramic image analysis. This research contributes significantly to the development of faster and more accurate AI-based dental diagnostic systems .]]>
Copyrights © 2025
