PDF(Pubmed)
Abstract：
BACKGROUND: To develop and validate a deep learning model for automated assessment of endodontic case difficulty from periapical radiographs.
METHODS: A dataset of 1,386 periapical radiographs was compiled from two clinical sites. Two dentists and two endodontists annotated the radiographs for difficulty using the \"simple assessment\" criteria from the American Association of Endodontists\' case difficulty assessment form in the Endocase application. A classification task labeled cases as \"easy\" or \"hard\", while regression predicted overall difficulty scores. Convolutional neural networks (i.e. VGG16, ResNet18, ResNet50, ResNext50, and Inception v2) were used, with a baseline model trained via transfer learning from ImageNet weights. Other models was pre-trained using self-supervised contrastive learning (i.e. BYOL, SimCLR, MoCo, and DINO) on 20,295 unlabeled dental radiographs to learn representation without manual labels. Both models were evaluated using 10-fold cross-validation, with performance compared to seven human examiners (three general dentists and four endodontists) on a hold-out test set.
RESULTS: The baseline VGG16 model attained 87.62% accuracy in classifying difficulty. Self-supervised pretraining did not improve performance. Regression predicted scores with ± 3.21 score error. All models outperformed human raters, with poor inter-examiner reliability.
CONCLUSIONS: This pilot study demonstrated the feasibility of automated endodontic difficulty assessment via deep learning models.
METHODS: A dataset of 1,386 periapical radiographs was compiled from two clinical sites. Two dentists and two endodontists annotated the radiographs for difficulty using the \"simple assessment\" criteria from the American Association of Endodontists\' case difficulty assessment form in the Endocase application. A classification task labeled cases as \"easy\" or \"hard\", while regression predicted overall difficulty scores. Convolutional neural networks (i.e. VGG16, ResNet18, ResNet50, ResNext50, and Inception v2) were used, with a baseline model trained via transfer learning from ImageNet weights. Other models was pre-trained using self-supervised contrastive learning (i.e. BYOL, SimCLR, MoCo, and DINO) on 20,295 unlabeled dental radiographs to learn representation without manual labels. Both models were evaluated using 10-fold cross-validation, with performance compared to seven human examiners (three general dentists and four endodontists) on a hold-out test set.
RESULTS: The baseline VGG16 model attained 87.62% accuracy in classifying difficulty. Self-supervised pretraining did not improve performance. Regression predicted scores with ± 3.21 score error. All models outperformed human raters, with poor inter-examiner reliability.
CONCLUSIONS: This pilot study demonstrated the feasibility of automated endodontic difficulty assessment via deep learning models.
摘要：
背景：开发和验证一种深度学习模型，用于从根尖周射线照片自动评估牙髓病例困难。
方法：从两个临床地点编制了1,386个根尖周X线片的数据集。两名牙医和两名牙髓医师在Endocase申请中使用美国牙髓医师协会的“简单评估”标准对X射线照片进行了困难注释。分类任务将案例标记为“简单”或“困难”，而回归预测总体难度得分。使用了卷积神经网络（即VGG16、ResNet18、ResNet50、ResNext50和Inceptionv2），使用通过从ImageNet权重的迁移学习训练的基线模型。其他模型使用自监督对比学习进行预训练(即BYOL，SimCLR,MoCo,和DINO）在20,295个未标记的牙科射线照片上学习没有手动标签的表示。这两个模型都使用10倍交叉验证进行了评估，与保持测试装置中的七名人类检查者（三名普通牙医和四名牙髓医生）相比。
结果：基线VGG16模型在分类难度方面达到了87.62%的准确率。自我监督的预训练并没有提高性能。回归预测得分，得分误差为±3.21。所有模型的性能都优于人类评估者，具有较差的考试者间可靠性。
结论：这项初步研究证明了通过深度学习模型进行自动牙髓困难评估的可行性。
方法：从两个临床地点编制了1,386个根尖周X线片的数据集。两名牙医和两名牙髓医师在Endocase申请中使用美国牙髓医师协会的“简单评估”标准对X射线照片进行了困难注释。分类任务将案例标记为“简单”或“困难”，而回归预测总体难度得分。使用了卷积神经网络（即VGG16、ResNet18、ResNet50、ResNext50和Inceptionv2），使用通过从ImageNet权重的迁移学习训练的基线模型。其他模型使用自监督对比学习进行预训练(即BYOL，SimCLR,MoCo,和DINO）在20,295个未标记的牙科射线照片上学习没有手动标签的表示。这两个模型都使用10倍交叉验证进行了评估，与保持测试装置中的七名人类检查者（三名普通牙医和四名牙髓医生）相比。
结果：基线VGG16模型在分类难度方面达到了87.62%的准确率。自我监督的预训练并没有提高性能。回归预测得分，得分误差为±3.21。所有模型的性能都优于人类评估者，具有较差的考试者间可靠性。
结论：这项初步研究证明了通过深度学习模型进行自动牙髓困难评估的可行性。
