Deep Learning for the Radiographic Detection of Apical Lesions
Deep Learning for the Radiographic Detection of Apical Lesions
复制标题
DOI：
10.1016/j.joen.2019.03.016
复制
发表时间：
2019-07-01
影响因子：
4.2
通讯作者：
Schwendicke, Falk
中科院分区：
文献类型：
--
作者：
Ekert, Thomas;Krois, Joachim;Schwendicke, Falk
引言：我们应用深度卷积神经网络（CNN）检测全景牙科X光片上的根尖病变（AL）。研究方法：基于来自全景X射线照片的2001个牙齿片段的合成数据集，通过10次重复的分组洗牌训练和验证了定制的7层深度神经网络，该网络由总数为4，299，651的权重参数化。使用网格搜索调整超参数。我们的参考测试是6名独立检查员的多数投票，他们在顺序量表上检测到AL（0，无AL; 1，牙周韧带增宽，不确定AL; 2，明显可检测的病变，确定AL）。AUC是受试者工作特征曲线下面积（AUC）、灵敏度、特异性和阳性/阴性预测值。对牙齿类型进行了亚组分析，并应用了参考试验的不同一致性边界（基础病例：2;敏感性分析：6）。结果：在基础病例中，不确定和确定AL的平均（标准差）牙齿水平患病率为0.16（0.03）。CNN的AUC为0.85（0.04）。敏感性为0.65（0.12），特异性为0.87（0.04）。得到的阳性预测值为0.49（0.10），阴性预测值为0.93（0.03）。磨牙的敏感性明显高于其他牙齿类型，而特异性较低。当仅评估某些AL时，AUC为0.89（0.04）。将一致性范围增加至6显著增加AUC至0.95（0.02），主要是因为灵敏度增加至0.74（0.19）。结论：在有限数量的图像数据上训练的中等深度的CNN显示出令人满意的在全景X射线照片上检测AL的辨别能力。
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.