Yollov11 Based Deep Learning Framework For Dental Abnormality Detection In Panoramic X-ray Image

Abstract

Dental abnormality detection from panoramic X-ray images is a critical task in modern dental diagnostics. Manual detection is often time-consuming and relies heavily on expert knowledge. This research proposes an Yollov11 Based Deep Learning Framework For Dental Abnormality Detection In Panoramic X-ray. Real world panoramic X-ray images were used, and all experiments were implemented using Python in the PyCharm environment. Multiple deep learning models were trained and integrated to perform object detection, focusing on both accuracy and computational efficiency suitable for practical use. The proposed framework achieved an object detection accuracy of over 90%, with high precision and recall, demonstrating reliable performance in identifying abnormal dental regions. The results indicate that a multi-model approach can significantly improve detection compared to single-model methods. The main objective of this research is to support dental practitioners by providing an automated tool that reduces manual effort and allows faster, more accurate diagnosis. This framework can help dentists detect dental diseases efficiently, making dental healthcare more effective and accessible