Çetinkaya İrem, Çatmabacak Ekin Deniz, Öztürk Emir
Department of Endodontics, Faculty of Dentistry, Trakya University, Edirne 22030, Turkey.
Department of Computer Engineering, Faculty of Engineering, Trakya University Edirne 22030, Turkey.
Diagnostics (Basel). 2025 Mar 7;15(6):653. doi: 10.3390/diagnostics15060653.
Accurate localization of fractured endodontic instruments (FEIs) in periapical radiographs (PAs) remains a significant challenge. This study aimed to evaluate the performance of YOLOv8 and Mask R-CNN in detecting FEIs and root canal treatments (RCTs) and compare their diagnostic capabilities with those of experienced endodontists. A data set of 1050 annotated PAs was used. Mask R-CNN and YOLOv8 models were trained and evaluated for FEI and RCT detection. Metrics including accuracy, intersection over union (IoU), mean average precision at 0.5 IoU (mAP50), and inference time were analyzed. Observer agreement was assessed using inter-class correlation (ICC), and comparisons were made between AI predictions and human annotations. : YOLOv8 achieved an accuracy of 97.40%, a mAP50 of 98.9%, and an inference time of 14.6 ms, outperforming Mask R-CNN in speed and mAP50. Mask R-CNN demonstrated an accuracy of 98.21%, a mAP50 of 95%, and an inference time of 88.7 ms, excelling in detailed segmentation tasks. Comparative analysis revealed no statistically significant differences in diagnostic performance between the models and experienced endodontists. Both YOLOv8 and Mask R-CNN demonstrated high diagnostic accuracy and reliability, comparable to experienced endodontists. YOLOv8's rapid detection capabilities make it particularly suitable for real-time clinical applications, while Mask R-CNN excels in precise segmentation. This study establishes a strong foundation for integrating AI into dental diagnostics, offering innovative solutions to improve clinical outcomes. Future research should address data diversity and explore multimodal imaging for enhanced diagnostic capabilities.
在根尖片（PA）中准确确定根管内折断器械（FEIs）的位置仍然是一项重大挑战。本研究旨在评估YOLOv8和Mask R-CNN在检测FEIs和根管治疗（RCTs）方面的性能，并将它们的诊断能力与经验丰富的牙髓病医生的诊断能力进行比较。使用了一个包含1050张标注根尖片的数据集。对Mask R-CNN和YOLOv8模型进行了FEI和RCT检测的训练与评估。分析了包括准确率、交并比（IoU）、0.5 IoU时的平均精度均值（mAP50）和推理时间等指标。使用组内相关系数（ICC）评估观察者间的一致性，并对人工智能预测结果与人工标注结果进行比较。YOLOv8的准确率为97.40%，mAP50为98.9%，推理时间为14.6毫秒，在速度和mAP50方面优于Mask R-CNN。Mask R-CNN的准确率为98.21%，mAP50为95%，推理时间为88.7毫秒，在详细分割任务方面表现出色。对比分析显示，这些模型与经验丰富的牙髓病医生在诊断性能上没有统计学显著差异。YOLOv8和Mask R-CNN都显示出较高的诊断准确性和可靠性，与经验丰富的牙髓病医生相当。YOLOv8的快速检测能力使其特别适合实时临床应用，而Mask R-CNN在精确分割方面表现出色。本研究为将人工智能整合到牙科诊断中奠定了坚实基础，提供了创新解决方案以改善临床结果。未来的研究应解决数据多样性问题，并探索多模态成像以增强诊断能力。
