| dc.description.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 | en_US |
