Jeon Su-Jin, Yun Jong-Pil, Yeom Han-Gyeol, Shin Woo-Sang, Lee Jong-Hyun, Jeong Seung-Hyun, Seo Min-Seock
Department of Conservative Dentistry, Wonkwang University Daejeon Dental Hospital, Daejeon, South Korea.
Safety System Research Group, Korea Institute of Industrial Technology (KITECH), Gyeongsan, South Korea.
Dentomaxillofac Radiol. 2021 Jul 1;50(5):20200513. doi: 10.1259/dmfr.20200513. Epub 2021 Jan 6.
The aim of this study was to evaluate the use of a convolutional neural network (CNN) system for predicting C-shaped canals in mandibular second molars on panoramic radiographs.
Panoramic and cone beam CT (CBCT) images obtained from June 2018 to May 2020 were screened and 1020 patients were selected. Our dataset of 2040 sound mandibular second molars comprised 887 C-shaped canals and 1153 non-C-shaped canals. To confirm the presence of a C-shaped canal, CBCT images were analyzed by a radiologist and set as the gold standard. A CNN-based deep-learning model for predicting C-shaped canals was built using Xception. The training and test sets were set to 80 to 20%, respectively. Diagnostic performance was evaluated using accuracy, sensitivity, specificity, and precision. Receiver-operating characteristics (ROC) curves were drawn, and the area under the curve (AUC) values were calculated. Further, gradient-weighted class activation maps (Grad-CAM) were generated to localize the anatomy that contributed to the predictions.
The accuracy, sensitivity, specificity, and precision of the CNN model were 95.1, 92.7, 97.0, and 95.9%, respectively. Grad-CAM analysis showed that the CNN model mainly identified root canal shapes converging into the apex to predict the C-shaped canals, while the root furcation was predominantly used for predicting the non-C-shaped canals.
The deep-learning system had significant accuracy in predicting C-shaped canals of mandibular second molars on panoramic radiographs.
本研究旨在评估卷积神经网络（CNN）系统在全景X线片上预测下颌第二磨牙C形根管的应用。
筛选2018年6月至2020年5月期间获得的全景和锥形束CT（CBCT）图像，选取1020例患者。我们的2040颗健康下颌第二磨牙数据集包括887个C形根管和1153个非C形根管。为确认C形根管的存在，由放射科医生分析CBCT图像并将其设为金标准。使用Xception构建基于CNN的预测C形根管的深度学习模型。训练集和测试集分别设定为80%和20%。使用准确度、灵敏度、特异度和精确度评估诊断性能。绘制受试者操作特征（ROC）曲线，并计算曲线下面积（AUC）值。此外，生成梯度加权类激活映射（Grad-CAM）以定位对预测有贡献的解剖结构。
CNN模型的准确度、灵敏度、特异度和精确度分别为95.1%、92.7%、97.0%和95.9%。Grad-CAM分析表明，CNN模型主要通过识别汇聚至根尖的根管形态来预测C形根管，而根分叉主要用于预测非C形根管。
该深度学习系统在全景X线片上预测下颌第二磨牙C形根管方面具有显著的准确度。
