State Key Laboratory of Oral Diseases, National Clinical Research Center for Oral Diseases, National Center for Stomatology, West China School of Stomatology, Sichuan University, Chengdu 610041, PR China; Department of Prosthodontics, West China Hospital of Stomatology, Sichuan University, Chengdu 610041, PR China.
College of Computer Science, Sichuan University, Chengdu 610065, PR China.
J Dent. 2024 May;144:104971. doi: 10.1016/j.jdent.2024.104971. Epub 2024 Mar 26.
In prosthodontic procedures, traditional computer-aided design (CAD) is often time-consuming and lacks accuracy in shape restoration. In this study, we combined implicit template and deep learning (DL) to construct a precise neural network for personalized tooth defect restoration.
Ninety models of right maxillary central incisor (80 for training, 10 for validation) were collected. A DL model named ToothDIT was trained to establish an implicit template and a neural network capable of predicting unique identifications. In the validation stage, teeth in validation set were processed into corner, incisive, and medium defects. The defective teeth were inputted into ToothDIT to predict the unique identification, which actuated the deformation of the implicit template to generate the highly customized template (DIT) for the target tooth. Morphological restorations were executed with templates from template shape library (TSL), average tooth template (ATT), and DIT in Exocad (GmbH, Germany). RMS, width, length, aspect ratio, incisal edge curvature, incisive end retraction, and guiding inclination were introduced to assess the restorative accuracy. Statistical analysis was conducted using two-way ANOVA and paired t-test for overall and detailed differences.
DIT displayed significantly smaller RMS than TSL and ATT. In 2D detailed analysis, DIT exhibited significantly less deviations from the natural teeth compared to TSL and ATT.
The proposed DL model successfully reconstructed the morphology of anterior teeth with various degrees of defects and achieved satisfactory accuracy. This approach provides a more reliable reference for prostheses design, resulting in enhanced accuracy in morphological restoration.
This DL model holds promise in assisting dentists and technicians in obtaining morphology templates that closely resemble the original shape of the defective teeth. These customized templates serve as a foundation for enhancing the efficiency and precision of digital restorative design for defective teeth.
在修复学程序中，传统的计算机辅助设计（CAD）往往耗时且在形状恢复方面缺乏准确性。本研究结合隐式模板和深度学习（DL），构建了一个用于个性化牙体缺损修复的精确神经网络。
收集 90 个右侧上颌中切牙模型（80 个用于训练，10 个用于验证）。训练了一个名为 ToothDIT 的 DL 模型，以建立一个能够预测独特标识的隐式模板和神经网络。在验证阶段，将验证集中的牙齿处理成角、切端和中段缺损。将有缺陷的牙齿输入 ToothDIT 以预测独特标识，从而激活隐式模板的变形，为目标牙齿生成高度定制的模板（DIT）。使用 Exocad（德国 GmbH）中的模板形状库（TSL）、平均牙模板（ATT）和 DIT 执行形态修复。使用均方根（RMS）、宽度、长度、纵横比、切缘曲率、切端退缩和引导倾斜来评估修复精度。使用双向方差分析和配对 t 检验对整体和详细差异进行统计分析。
DIT 的 RMS 明显小于 TSL 和 ATT。在 2D 详细分析中，与 TSL 和 ATT 相比，DIT 显示出与天然牙齿的偏差明显更小。
所提出的 DL 模型成功地重建了具有不同程度缺损的前牙形态，并取得了令人满意的准确性。这种方法为义齿设计提供了更可靠的参考，从而提高了形态修复的准确性。
该 DL 模型有望帮助牙医和技术人员获得与缺损牙齿原始形状非常相似的形态模板。这些定制模板为增强数字化修复设计对缺损牙齿的效率和精度提供了基础。
