多种深度网络在牙X线片龋齿检测中的性能比较
本研究基于自采集临床根尖片数据集,比较YOLOv5、DETR两种目标检测网络与UNet、Trans-UNet两种分割网络的龋齿检测性能,并以5名牙医在同一测试集上的检测结果作为参照。结果显示YOLOv5的F1-score(0.87)与Youden指数(0.76)均居首位,各网络与金标准呈中度一致性,网络间及训练良好的网络与牙医间差异无统计学意义(p>0.05)。结论推荐优先选用YOLOv5辅助龋齿检测。
要点
- YOLOv5在龋齿检测中F1-score达0.87,在受试网络中表现最优。
- 训练良好的深度网络与牙医检测之间差异无统计学意义(p>0.05)。
- 深度网络可作为牙医检测和诊断龋齿的辅助工具。
核心结论
- 在受试深度网络中,YOLOv5因指标较高被推荐优先用于龋齿检测。
- 训练良好的深度网络可作为牙医检测和诊断龋齿的良好辅助。
研究设计与样本
- 基于临床自采集根尖片数据集,比较YOLOv5、DETR目标检测网络与UNet、Trans-UNet分割网络的龋齿检测性能。
- 由5名牙医在同一测试数据集上进行龋齿检测作为参照。
- 获取牙位水平的precision、sensitivity、specificity、F1-score和Youden指数等指标并进行统计分析。
主要发现
- 龋齿检测F1-score排序为YOLOv5(0.87)、Trans-UNet(0.86)、DETR(0.82)、UNet(0.80)。
- Youden指数排序相同,分别为0.76、0.73、0.69和0.64。
- 所有网络与金标准之间呈中度一致性。
- 网络之间以及训练良好的网络与牙医之间的差异均无统计学意义(p>0.05)。
关键数值与推荐
- F1-score:YOLOv5 0.87、Trans-UNet 0.86、DETR 0.82、UNet 0.80。
- Youden指数:YOLOv5 0.76、Trans-UNet 0.73、DETR 0.69、UNet 0.64。
- 网络间及训练良好的网络与牙医间差异无统计学意义(p>0.05)。
临床怎么用
- 可优先考虑YOLOv5用于基于X线图像的龋齿检测。
- 将训练良好的深度网络作为辅助手段,支持医务人员检测和诊断龋齿。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVES: Deep networks have been preliminarily studied in caries diagnosis based on clinical X-ray images. However, the performance of different deep networks on caries detection is still unclear. This study aims to comprehensively compare the caries detection performances of recent multifarious deep networks with clinical dentist level as a bridge. METHODS: Based on the self-collected periapical radiograph dataset in clinic, four most popular deep networks in two types, namely YOLOv5 and DETR object detection networks, and UNet and Trans-UNet segmentation networks, were included in the comparison study. Five dentists carried out the caries detection on the same testing dataset for reference. Key tooth-level metrics, including precision, sensitivity, specificity, F1-score and Youden index, were obtained, based on which statistical analysis was conducted. RESULTS: The F1-score order of deep networks is YOLOv5 (0.87), Trans-UNet (0.86), DETR (0.82) and UNet (0.80) in caries detection. A same ranking order is found using the Youden index combining sensitivity and specificity, which are 0.76, 0.73, 0.69 and 0.64 respectively. A moderate level of concordance was observed between all networks and the gold standard. No significant difference (p > 0.05) was found between deep networks and between the well-trained network and dentists in caries detection. CONCLUSIONS: Among investigated deep networks, YOLOv5 is recommended to be priority for caries detection in terms of its high metrics. The well-trained deep network could be used as a good assistance for dentists to detect and diagnose caries. CLINICAL SIGNIFICANCE: The well-trained deep network shows a promising potential clinical application prospect. It can provide valuable support to healthcare professionals in facilitating detection and diagnosis of dental caries.
引用
- Ying S, Huang F, Shen X, et al. Performance comparison of multifarious deep networks on caries detection with tooth X-ray images. J Dent. 2024. PMID: 38556194. doi:10.1016/j.jdent.2024.104970
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。