基于深度学习实现临床可用的三维牙齿分割
本研究训练了一个全自动深度学习模型,在4000例口内扫描数据上标注并由专家审核。在200例保留扫描集上,模型达到逐面准确率96.94%、平均面积准确率98.26%和受试者工作特征曲线下面积0.9991,显著优于现有基线方法。模型仅需约24秒生成分割结果,而基线方法超过5分钟,人类专家需15分钟。在500例错颌畸形和/或异常牙齿患者的临床性能测试中,96.9%的分割结果满足临床应用要求,2.9%自动触发警报需人工改进,仅0.2%需要返工。
要点
- 深度学习模型在200例保留扫描集上达到逐面准确率96.94%、平均面积准确率98.26%、AUC 0.9991。
- 模型生成分割结果约需24秒,基线方法超过5分钟,人类专家需15分钟。
- 500例临床测试中,96.9%分割结果满足临床应用,2.9%触发人工改进警报,0.2%需返工。
核心结论
- 深度学习有潜力提高牙科治疗和数字化牙科的疗效与效率。
研究设计与样本
- 研究训练了一个全自动深度学习模型,使用由经验丰富的人类专家标注的4000例口内扫描数据集。
- 在200例保留扫描数据集上评估模型性能,并与现有基线方法比较。
- 进行了500例错颌畸形和/或异常牙齿患者的临床性能测试。
主要发现
- 在200例保留扫描集上,模型达到逐面准确率96.94%、平均面积准确率98.26%、受试者工作特征曲线下面积0.9991,显著优于现有基线方法。
- 模型生成分割输出仅需约24秒,而基线方法超过5分钟,人类专家需15分钟。
- 在500例患者的临床性能测试中,96.9%的分割结果满足临床应用要求,2.9%自动触发警报需人工改进,仅0.2%需要返工。
局限性
- 原文未报告局限性。
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
Digital dentistry plays a pivotal role in dental health care. A critical step in many digital dental systems is to accurately delineate individual teeth and the gingiva in the 3-dimension intraoral scanned mesh data. However, previous state-of-the-art methods are either time-consuming or error prone, hence hindering their clinical applicability. This article presents an accurate, efficient, and fully automated deep learning model trained on a data set of 4,000 intraoral scanned data annotated by experienced human experts. On a holdout data set of 200 scans, our model achieves a per-face accuracy, average-area accuracy, and area under the receiver operating characteristic curve of 96.94%, 98.26%, and 0.9991, respectively, significantly outperforming the state-of-the-art baselines. In addition, our model takes only about 24 s to generate segmentation outputs, as opposed to >5 min by the baseline and 15 min by human experts. A clinical performance test of 500 patients with malocclusion and/or abnormal teeth shows that 96.9% of the segmentations are satisfactory for clinical applications, 2.9% automatically trigger alarms for human improvement, and only 0.2% of them need rework. Our research demonstrates the potential for deep learning to improve the efficacy and efficiency of dental treatment and digital dentistry.
引用
- Hao J, Liao W, Zhang YL, et al. Toward Clinically Applicable 3-Dimensional Tooth Segmentation via Deep Learning. J Dent Res. 2021. PMID: 34719980. doi:10.1177/00220345211040459
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。