Lian Luya, Zhu Tianer, Zhu Fudong, Zhu Haihua
Stomatology Hospital, School of Stomatology, Zhejiang University School of Medicine, Clinical Research Center for Oral Diseases of Zhejiang Province, Key Laboratory of Oral Biomedical Research of Zhejiang Province, Cancer Center of Zhejiang University, Hangzhou 310006, China.
Diagnostics (Basel). 2021 Sep 13;11(9):1672. doi: 10.3390/diagnostics11091672.
Deep learning methods have achieved impressive diagnostic performance in the field of radiology. The current study aimed to use deep learning methods to detect caries lesions, classify different radiographic extensions on panoramic films, and compare the classification results with those of expert dentists.
A total of 1160 dental panoramic films were evaluated by three expert dentists. All caries lesions in the films were marked with circles, whose combination was defined as the reference dataset. A training and validation dataset (1071) and a test dataset (89) were then established from the reference dataset. A convolutional neural network, called nnU-Net, was applied to detect caries lesions, and DenseNet121 was applied to classify the lesions according to their depths (dentin lesions in the outer, middle, or inner third D1/2/3 of dentin). The performance of the test dataset in the trained nnU-Net and DenseNet121 models was compared with the results of six expert dentists in terms of the intersection over union (IoU), Dice coefficient, accuracy, precision, recall, negative predictive value (NPV), and F1-score metrics.
nnU-Net yielded caries lesion segmentation IoU and Dice coefficient values of 0.785 and 0.663, respectively, and the accuracy and recall rate of nnU-Net were 0.986 and 0.821, respectively. The results of the expert dentists and the neural network were shown to be no different in terms of accuracy, precision, recall, NPV, and F1-score. For caries depth classification, DenseNet121 showed an overall accuracy of 0.957 for D1 lesions, 0.832 for D2 lesions, and 0.863 for D3 lesions. The recall results of the D1/D2/D3 lesions were 0.765, 0.652, and 0.918, respectively. All metric values, including accuracy, precision, recall, NPV, and F1-score values, were proven to be no different from those of the experienced dentists.
In detecting and classifying caries lesions on dental panoramic radiographs, the performance of deep learning methods was similar to that of expert dentists. The impact of applying these well-trained neural networks for disease diagnosis and treatment decision making should be explored.
深度学习方法在放射学领域取得了令人瞩目的诊断性能。本研究旨在使用深度学习方法检测龋损，对全景片上不同的影像学扩展进行分类，并将分类结果与专家牙医的结果进行比较。
由三位专家牙医对总共1160张牙科全景片进行评估。片中所有龋损均用圆圈标记，其组合被定义为参考数据集。然后从参考数据集中建立一个训练和验证数据集（1071张）以及一个测试数据集（89张）。应用一个名为nnU-Net的卷积神经网络来检测龋损，并应用DenseNet121根据龋损深度（牙本质外层、中层或内层三分之一D1/2/3中的牙本质龋损）对龋损进行分类。在交并比（IoU）、Dice系数、准确率、精确率、召回率、阴性预测值（NPV）和F1分数指标方面，将训练后的nnU-Net和DenseNet121模型中测试数据集的性能与六位专家牙医的结果进行比较。
nnU-Net得出的龋损分割IoU和Dice系数值分别为0.785和0.663，nnU-Net的准确率和召回率分别为0.986和0.821。在准确率、精确率、召回率、NPV和F1分数方面，专家牙医和神经网络的结果显示无差异。对于龋损深度分类，DenseNet121对D1类龋损的总体准确率为0.957，对D2类龋损为0.832，对D3类龋损为0.863。D1/D2/D3类龋损的召回结果分别为0.765、0.652和0.918。所有指标值，包括准确率、精确率、召回率、NPV和F1分数值，均被证明与经验丰富的牙医的结果无差异。
在检测和分类牙科全景X线片上的龋损时，深度学习方法的性能与专家牙医相似。应探索应用这些训练有素的神经网络对疾病诊断和治疗决策的影响。
