Abdelazim Riem, Fouad Eman M
Department of Information Systems, Faculty of Information Technology, Misr University for Science and Technology, Giza, Egypt.
Division of Endodontics, Faculty of Oral and Dental Surgery, Misr University for Science and Technology, Giza, Egypt.
BDJ Open. 2024 Oct 1;10(1):76. doi: 10.1038/s41405-024-00260-1.
The detection and early diagnosis of root fractures can be challenging; this difficulty applies particularly to newly qualified dentists. Aside from clinical examination, diagnosis often requires radiographic assessment. Nonetheless, human fallibility can introduce errors due to a lack of experience.
The proposed system aimed to assist in detecting root fractures through the integration of artificial intelligence techniques into the diagnosis process as a step for automating dental diagnosis and decision-making processes.
A total of 400 radiographic images of fractured and unfractured teeth were obtained for the present research. Data handling techniques were implemented to balance the distribution of the samples. The AI-based system used the voting technique for five different pretrained models namely, VGG16, VGG19, ResNet50. DenseNet121, and DenseNet169 to perform the analysis. The parameters used for the analysis of the models are loss and accuracy curves.
VGG16 exhibited notable success with low training and validation losses (0.09% and 0.18%, respectively), high specificity, sensitivity, and positive predictive value (PPV). VGG19 showed potential overfitting concerns, while ResNet50 displayed progress in minimizing loss but exhibited bias toward unfractured cases. DenseNet121 effectively addressed overfitting and noise issues, achieving balanced metrics and impressive PPVs for both fractured and unfractured cases (0.933 and 0.898 respectively). With increased depth, DenseNet169 demonstrated enhanced generalization capability.
The proposed AI- based system demonstrated high precision and sensitivity for detecting root fractures in endodontically treated teeth by utilizing the voting method.
牙根折裂的检测和早期诊断可能具有挑战性；这一困难尤其适用于刚获得资格的牙医。除了临床检查外，诊断通常还需要进行影像学评估。然而，由于缺乏经验，人为失误可能会导致错误。
所提出的系统旨在通过将人工智能技术集成到诊断过程中，协助检测牙根折裂，以此作为实现牙科诊断和决策过程自动化的一个步骤。
本研究共获取了400张有折裂和无折裂牙齿的影像学图像。采用数据处理技术来平衡样本的分布。基于人工智能的系统使用投票技术，对五个不同的预训练模型，即VGG16、VGG19、ResNet50、DenseNet121和DenseNet169进行分析。用于模型分析的参数是损失曲线和准确率曲线。
VGG16在低训练损失和验证损失（分别为0.09%和0.18%）、高特异性、敏感性和阳性预测值（PPV）方面表现出显著成功。VGG19显示出潜在的过拟合问题，而ResNet50在最小化损失方面取得了进展，但对无折裂病例存在偏差。DenseNet121有效地解决了过拟合和噪声问题，在折裂和未折裂病例中均实现了平衡的指标和令人印象深刻的PPV（分别为0.933和0.898）。随着深度的增加，DenseNet169表现出更强的泛化能力。
所提出的基于人工智能的系统通过使用投票方法，在检测根管治疗牙齿的牙根折裂方面显示出高精度和高敏感性。
