Jin Long, Tang Ying, Zhou Wenyuan, Bai Bingbing, Yu Zezheng, Zhang Panpan, Gu Yongchun
Department of Radiology, Ninth People's Hospital of Suzhou, Soochow University, Suzhou, China.
Department of Pathology, Ninth People's Hospital of Suzhou, Soochow University, Suzhou, China.
Sci Rep. 2024 Dec 5;14(1):30392. doi: 10.1038/s41598-024-82378-8.
This study aimed to develop a deep learning system for the detection of three-rooted mandibular first molars (MFMs) on panoramic radiographs and to assess its diagnostic performance. Panoramic radiographs, together with cone beam computed tomographic (CBCT) images of the same subjects, were retrospectively collected from 730 patients, encompassing a total of 1444 MFMs (367 teeth were three-rooted and the remaining 1077 teeth were two-rooted). Five convolutional neural network (CNN) models (ResNet-101 and - 50, DenseNet-201, MobileNet-v3 and Inception-v3) were employed to classify three- and two-rooted MFMs on the panoramic radiographs. The diagnostic performance of each model was evaluated using standard metrics, including accuracy, sensitivity, specificity, precision, negative predictive value, and F1 score. Receiver operating characteristic (ROC) curve analyses were performed, with the CBCT examination taken as the gold standard.Among the five CNN models evaluated, ResNet-101 demonstrated superior diagnostic performance, and the AUC value attained was 0.907, significantly higher than that of all other models (all P < 0.01). The accuracy, sensitivity, and specificity were 87.5%, 83.6%, and 88.9%, respectively. DenseNet-201, however, showed the lowest diagnostic performance among the five models (all P < 0.01), with an AUC value of 0.701 and an accuracy of 73.2%. Overall, the performance of the CNNs diminished when using image patches containing only the distal half of MFMs, with AUC values ranging between 0.680 and 0.800. In contrast, the diagnostic performance of the two clinicians was poorer, with AUC values of only 0.680 and 0.632, respectively. In conclusion, the CNN-based deep learning system exhibited a high level of accuracy in the detection of three-rooted MFMs on panoramic radiographs.
本研究旨在开发一种深度学习系统，用于在全景X线片上检测下颌第一磨牙（MFM）的三根情况，并评估其诊断性能。回顾性收集了730例患者的全景X线片以及同一受试者的锥形束计算机断层扫描（CBCT）图像，共包括1444颗MFM（367颗为三根，其余1077颗为两根）。使用五个卷积神经网络（CNN）模型（ResNet-101和-50、DenseNet-201、MobileNet-v3和Inception-v3）对全景X线片上的三根和两根MFM进行分类。使用包括准确性、敏感性、特异性、精确性、阴性预测值和F1分数在内的标准指标评估每个模型的诊断性能。以CBCT检查作为金标准进行受试者操作特征（ROC）曲线分析。在评估的五个CNN模型中，ResNet-101表现出卓越的诊断性能，获得的AUC值为0.907，显著高于所有其他模型（所有P<0.01）。准确性、敏感性和特异性分别为87.5%、83.6%和88.9%。然而，DenseNet-201在五个模型中诊断性能最低（所有P<0.01），AUC值为0.701，准确性为73.2%。总体而言，当使用仅包含MFM远中半部的图像块时，CNN的性能会下降，AUC值在0.680至0.800之间。相比之下，两位临床医生的诊断性能较差，AUC值分别仅为0.680和0.632。总之，基于CNN的深度学习系统在全景X线片上检测三根MFM时表现出较高的准确性。
