深度学习在全景片上检测根尖病变的研究
本研究将7层深度卷积神经网络(CNN)应用于全景牙科放射片检测根尖病变(AL),基于2001个牙段数据训练,以6名检查者多数投票为参考标准。CNN的AUC为0.85,敏感度0.65、特异度0.87,对明确AL的AUC达0.89,显示中等深度CNN在有限数据下具有满意的判别能力。
要点
- CNN检测根尖病变的AUC为0.85,敏感度0.65、特异度0.87。
- 仅评估明确病变时AUC升至0.89,敏感度提高。
- 磨牙敏感度高于其他牙型但特异度较低。
核心结论
- 中等深度CNN在有限图像数据上训练后,对全景片根尖病变检测显示出满意的判别能力。
研究设计与样本
- 基于2001个牙段的全景放射片合成数据集,训练并验证一个含4,299,651个权重的7层深度神经网络,采用10次重复分组洗牌和网格搜索调参。
- 参考标准为6名独立检查者按序数尺度(0无AL、1牙周膜增宽不确定、2明确病变)检测的多数投票。
主要发现
- 基础病例中不确定和明确AL的牙水平患病率均值(标准差)为0.16(0.03)。
- CNN的AUC为0.85(0.04),敏感度0.65(0.12)、特异度0.87(0.04)、阳性预测值0.49(0.10)、阴性预测值0.93(0.03)。
- 磨牙敏感度显著高于其他牙型,但特异度较低。
- 仅评估明确AL时AUC为0.89(0.04)。
- 将一致性边际增至6时AUC显著升至0.95(0.02),主要因敏感度增至0.74(0.19)。
临床怎么用
- 该CNN模型可作为全景片根尖病变筛查的辅助工具,高阴性预测值有助于排除病变。
局限性
- 训练数据量有限,模型深度中等,结论需外部验证。
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
INTRODUCTION: We applied deep convolutional neural networks (CNNs) to detect apical lesions (ALs) on panoramic dental radiographs. METHODS: Based on a synthesized data set of 2001 tooth segments from panoramic radiographs, a custom-made 7-layer deep neural network, parameterized by a total number of 4,299,651 weights, was trained and validated via 10 times repeated group shuffling. Hyperparameters were tuned using a grid search. Our reference test was the majority vote of 6 independent examiners who detected ALs on an ordinal scale (0, no AL; 1, widened periodontal ligament, uncertain AL; 2, clearly detectable lesion, certain AL). Metrics were the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive/negative predictive values. Subgroup analysis for tooth types was performed, and different margins of agreement of the reference test were applied (base case: 2; sensitivity analysis: 6). RESULTS: The mean (standard deviation) tooth level prevalence of both uncertain and certain ALs was 0.16 (0.03) in the base case. The AUC of the CNN was 0.85 (0.04). Sensitivity and specificity were 0.65 (0.12) and 0.87 (0.04,) respectively. The resulting positive predictive value was 0.49 (0.10), and the negative predictive value was 0.93 (0.03). In molars, sensitivity was significantly higher than in other tooth types, whereas specificity was lower. When only certain ALs were assessed, the AUC was 0.89 (0.04). Increasing the margin of agreement to 6 significantly increased the AUC to 0.95 (0.02), mainly because the sensitivity increased to 0.74 (0.19). CONCLUSIONS: A moderately deep CNN trained on a limited amount of image data showed satisfying discriminatory ability to detect ALs on panoramic radiographs.
引用
- Ekert T, Krois J, Meinhold L, et al. Deep Learning for the Radiographic Detection of Apical Lesions. J Endod. 2019. PMID: 31160078. doi:10.1016/j.joen.2019.03.016
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。