Institute of Odontology, Faculty of Medicine, Vilnius University, Vilnius, Lithuania.
Institute of Theoretical Physics and Astronomy, Faculty of Physics, Vilnius University, Vilnius, Lithuania.
Sci Rep. 2022 Dec 28;12(1):22489. doi: 10.1038/s41598-022-27062-5.
Although teeth microcracks (MCs) have long been considered more of an aesthetic problem, their exact role in the structure of a tooth and impact on its functionality is still unknown. The aim of this study was to reveal the possibilities of an X-ray micro-computed tomography ([Formula: see text]CT) in combination with convolutional neural network (CNN) assisted voxel classification and volume segmentation for three-dimensional (3D) qualitative analysis of tooth microstructure and verify this approach with four extracted human premolars. Samples were scanned using a [Formula: see text]CT instrument (Xradia 520 Versa; ZEISS) and segmented with CNN to identify enamel, dentin, and cracks. A new CNN image segmentation model was trained based on "Multiclass semantic segmentation using DeepLabV3+" example and was implemented with "TensorFlow". The technique which was used allowed 3D characterization of all MCs of a tooth, regardless of the volume of the tooth in which they begin and extend, and the evaluation of the arrangement of cracks and their structural features. The proposed method revealed an intricate star-shaped network of MCs covering most of the inner tooth, and the main crack planes in all samples were arranged radially in two almost perpendicular directions, suggesting that the cracks could be considered as a planar structure.
虽然牙齿微裂纹（MCs）长期以来被认为更多是一个美学问题，但它们在牙齿结构中的确切作用及其对功能的影响仍不清楚。本研究的目的是揭示 X 射线微计算机断层扫描（µCT）与卷积神经网络（CNN）辅助体素分类和体积分割相结合，对牙齿微观结构进行三维（3D）定性分析的可能性，并使用四颗提取的人前磨牙验证该方法。样本使用 µCT 仪器（Xradia 520 Versa；ZEISS）进行扫描，并使用 CNN 进行分割以识别牙釉质、牙本质和裂纹。根据“使用 DeepLabV3+进行多类语义分割”示例，基于新的 CNN 图像分割模型进行训练，并通过“TensorFlow”实现。该技术可用于对牙齿的所有 MC 进行 3D 特征描述，而不受其起始和延伸的牙齿体积的影响，并可评估裂纹的排列及其结构特征。所提出的方法揭示了一个错综复杂的星状 MC 网络，覆盖了牙齿的大部分内部，并且所有样本中的主要裂纹面都呈放射状排列在两个几乎垂直的方向上，表明这些裂纹可以被认为是一种平面结构。
