Vilkomir Katerina, Phen Cody, Baldwin Fiondra, Cole Jared, Herndon Nic, Zhang Wenjian
Department of Computer Science, East Carolina University, Greenville, NC, USA.
School of Dental Medicine, East Carolina University, Greenville, NC, USA.
Imaging Sci Dent. 2024 Sep;54(3):257-263. doi: 10.5624/isd.20240020. Epub 2024 Aug 12.
The purpose of this study was to classify mandibular molar furcation involvement (FI) in periapical radiographs using a deep learning algorithm.
Full mouth series taken at East Carolina University School of Dental Medicine from 2011-2023 were screened. Diagnostic-quality mandibular premolar and molar periapical radiographs with healthy or FI mandibular molars were included. The radiographs were cropped into individual molar images, annotated as " healthy" or " FI," and divided into training, validation, and testing datasets. The images were preprocessed by PyTorch transformations. ResNet-18, a convolutional neural network model, was refined using the PyTorch deep learning framework for the specific imaging classification task. CrossEntropyLoss and the AdamW optimizer were employed for loss function training and optimizing the learning rate, respectively. The images were loaded by PyTorch DataLoader for efficiency. The performance of ResNet-18 algorithm was evaluated with multiple metrics, including training and validation losses, confusion matrix, accuracy, sensitivity, specificity, the receiver operating characteristic (ROC) curve, and the area under the ROC curve.
After adequate training, ResNet-18 classified healthy . FI molars in the testing set with an accuracy of 96.47%, indicating its suitability for image classification.
The deep learning algorithm developed in this study was shown to be promising for classifying mandibular molar FI. It could serve as a valuable supplemental tool for detecting and managing periodontal diseases.
本研究的目的是使用深度学习算法对根尖片上的下颌磨牙根分叉病变（FI）进行分类。
筛选了2011年至2023年在东卡罗来纳大学牙医学院拍摄的全口系列片。纳入具有健康或根分叉病变的下颌磨牙的诊断质量的下颌前磨牙和磨牙根尖片。将根尖片裁剪为单个磨牙图像，标注为“健康”或“根分叉病变”，并分为训练集、验证集和测试集。图像通过PyTorch变换进行预处理。使用PyTorch深度学习框架对卷积神经网络模型ResNet-18进行优化，以用于特定的成像分类任务。分别采用交叉熵损失函数和AdamW优化器进行损失函数训练和学习率优化。通过PyTorch数据加载器加载图像以提高效率。使用多种指标评估ResNet-18算法的性能，包括训练和验证损失、混淆矩阵、准确率、灵敏度、特异性、受试者工作特征（ROC）曲线以及ROC曲线下面积。
经过充分训练后，ResNet-18在测试集中对健康和根分叉病变磨牙的分类准确率为96.47%，表明其适用于图像分类。
本研究开发的深度学习算法在分类下颌磨牙根分叉病变方面显示出前景。它可作为检测和管理牙周疾病的有价值的辅助工具。
