基于深度学习的全景片自动牙位图表归档
本研究旨在全景片(PR)上自动检测、分割并标注牙齿、牙冠、充填体、根管充填、种植体及残根。以2000张人工标注PR为参考,采用基于Mask R-CNN与Resnet-50的深度学习方法结合规则启发式与组合搜索算法,在1800张PR上训练验证,200张测试。检测、分割、标注F1分别达0.993、0.952、0.97。
要点
- 深度学习可自动检测、分割并标注全景片中的牙齿及修复体。
- 检测、分割与标注的F1分数分别最高达0.993、0.952、0.97。
- 该方法为全景片自动图表归档的进一步发展提供了有前景的基础。
核心结论
- 所提方法为全景片自动图表归档的进一步发展提供了有前景的基础。
研究设计与样本
- 研究基于2000张人工标注的全景片,其中1800张用于训练和验证,200张作为测试集。
- 采用基于Mask R-CNN与Resnet-50的深度学习方法,结合规则启发式算法和组合搜索算法。
主要发现
- 检测任务的F1分数最高达0.993。
- 分割任务的F1分数最高达0.952。
- 标注任务的F1分数最高达0.97。
临床怎么用
- 深度学习可能辅助临床医生总结全景片上的影像学发现。
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
OBJECTIVE: The aim of this study is to automatically detect, segment and label teeth, crowns, fillings, root canal fillings, implants and root remnants on panoramic radiographs (PR(s)). MATERIAL AND METHODS: As a reference, 2000 PR(s) were manually annotated and labeled. A deep-learning approach based on mask R-CNN with Resnet-50 in combination with a rule-based heuristic algorithm and a combinatorial search algorithm was trained and validated on 1800 PR(s). Subsquently, the trained algorithm was applied onto a test set consisting of 200 PR(s). F1 scores, as a measure of accuracy, were calculated to quantify the degree of similarity between the annotated ground-truth and the model predictions. The F1-score considers the harmonic mean of precison (positive predictive value) and recall (specificity). RESULTS: The proposes method achieved F1 scores up to 0.993, 0.952 and 0.97 for detection, segmentation and labeling, respectivley. CONCLUSION: The proposed method forms a promising foundation for the further development of automatic chart filing on PR(s). CLINICAL SIGNIFICANCE: Deep learning may assist clinicians in summarizing the radiological findings on panoramic radiographs. The impact of using such models in clinical practice should be explored.
引用
- Vinayahalingam S, Goey RS, Kempers S, et al. Automated chart filing on panoramic radiographs using deep learning. J Dent. 2021. PMID: 34715247. doi:10.1016/j.jdent.2021.103864
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。