Microscope Center, Department of Conservative, Yonsei University College of Dentistry, Seoul, Korea.
Bionics Research Center, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul, Korea.
J Endod. 2023 Jun;49(6):710-719. doi: 10.1016/j.joen.2023.03.015. Epub 2023 Apr 4.
This study aimed to evaluate the use of deep convolutional neural network (DCNN) algorithms to detect clinical features and predict the three-year outcome of endodontic treatment on preoperative periapical radiographs.
A database of single-root premolars that received endodontic treatment or retreatment by endodontists with presence of three-year outcome was prepared (n = 598). We constructed a 17-layered DCNN with a self-attention layer (Periapical Radiograph Explanatory System with Self-Attention Network [PRESSAN-17]), and the model was trained, validated, and tested to 1) detect 7 clinical features, that is, full coverage restoration, presence of proximal teeth, coronal defect, root rest, canal visibility, previous root filling, and periapical radiolucency and 2) predict the three-year endodontic prognosis by analyzing preoperative periapical radiographs as an input. During the prognostication test, a conventional DCNN without a self-attention layer (residual neural network [RESNET]-18) was tested for comparison. Accuracy and area under the receiver-operating-characteristic curve were mainly evaluated for performance comparison. Gradient-weighted class activation mapping was used to visualize weighted heatmaps.
PRESSAN-17 detected full coverage restoration (area under the receiver-operating-characteristic curve = 0.975), presence of proximal teeth (0.866), coronal defect (0.672), root rest (0.989), previous root filling (0.879), and periapical radiolucency (0.690) significantly, compared to the no-information rate (P < .05). Comparing the mean accuracy of 5-fold validation of 2 models, PRESSAN-17 (67.0%) showed a significant difference to RESNET-18 (63.4%, P < .05). Also, the area under average receiver-operating-characteristic of PRESSAN-17 was 0.638, which was significantly different compared to the no-information rate. Gradient-weighted class activation mapping demonstrated that PRESSAN-17 correctly identified clinical features.
Deep convolutional neural networks can detect several clinical features in periapical radiographs accurately. Based on our findings, well-developed artificial intelligence can support clinical decisions related to endodontic treatments in dentists.
本研究旨在评估使用深度卷积神经网络（DCNN）算法来检测术前根尖片的临床特征并预测根管治疗的三年预后。
准备了一个数据库，其中包含由牙髓病专家进行根管治疗或再治疗的单根前磨牙，并且有三年的预后（n=598）。我们构建了一个具有自注意力层的 17 层 DCNN（根尖片解释系统与自注意力网络[PRESSAN-17]），并对模型进行了训练、验证和测试，以 1）检测 7 个临床特征，即全冠修复、邻牙存在、冠部缺损、根分歧、根管可视性、既往根管充填和根尖透光区，以及 2）通过分析术前根尖片作为输入来预测三年的根管预后。在预后测试中，测试了一个没有自注意力层的传统 DCNN（残差神经网络[RESNET]-18）进行比较。主要评估准确性和受试者工作特征曲线下面积以进行性能比较。使用梯度加权类激活映射可视化加权热图。
与无信息率相比，PRESSAN-17 显著检测到全冠修复（受试者工作特征曲线下面积=0.975）、邻牙存在（0.866）、冠部缺损（0.672）、根分歧（0.989）、既往根管充填（0.879）和根尖透光区（0.690）（P<0.05）。比较两个模型的 5 倍验证的平均准确性，PRESSAN-17（67.0%）与 RESNET-18（63.4%）有显著差异（P<0.05）。此外，PRESSAN-17 的平均受试者工作特征曲线下面积为 0.638，与无信息率有显著差异。梯度加权类激活映射表明，PRESSAN-17 正确地识别了临床特征。
深度卷积神经网络可以准确地检测根尖片中的几个临床特征。基于我们的发现，发达的人工智能可以为牙医提供与根管治疗相关的临床决策支持。
