[Research on automated orthodontic tooth arrangement by integrating multi-source structural information and dental arch prediction].

内容摘要

To address the issues of time-consuming manual tooth alignment, reliance on physician experience, and insufficient structural constraints in automated methods in traditional orthodontic treatment planning, this paper proposes an automated tooth alignment network model that integrates multi-source geometric information learning. First, this study uses tooth mesh data as input to construct a graph convolution-based network for extracting tooth geometric features, fully utilizing the topological connectivity and local geometric features of the tooth model to enhance the extraction of tooth morphological features. Then, an arch line prediction network is designed to guide the teeth to align orderly along the natural arch line by explicitly modeling the tooth alignment trajectory, thereby ensuring the anatomical rationality and aesthetics of the overall structure. Based on this, this study designs collision avoidance loss and arch alignment loss to reduce geometric conflicts between adjacent teeth and constrain the overall posture, making the alignment results more stable and realistic. To verify the effectiveness of the method, validation experiments were conducted on multiple sets of real dental arch data, and comparisons were made with mainstream methods such as tooth alignment network (TaligNet), parameterized spatial transformation network (PSTN), and Transformer-based network for tooth alignment (TANet). The results show that the proposed method improves the evaluation metrics to varying degrees, fully integrates global and local geometric information, improves tooth posture coordination and alignment smoothness, and provides efficient and standardized intelligent support for digital orthodontic treatment planning. 针对传统正畸治疗规划中牙齿手动排列耗时、依赖医师自身经验以及自动化方法中结构约束不足的问题，本文提出了一种融合多源几何信息学习的自动排牙网络模型。首先，本研究以牙齿网格数据为输入，构建基于图卷积的牙齿几何特征提取网络，以充分利用牙齿模型的拓扑连接关系与局部几何特征，增强对牙齿形态的特征提取；随后，设计牙弓线预测网络，通过显式建模牙齿排列轨迹，引导牙齿沿自然牙弓线有序排布，从而保证整体结构的解剖合理性与美观性；在此基础上，本研究设计碰撞避免损失与牙弓对齐损失，用于减少相邻牙齿间的几何冲突并约束整体姿态，使排列结果更加稳定与真实。为验证方法的有效性，本文在多组真实牙列数据上进行了验证实验，并与牙齿排列网络（TaligNet）、参数化空间变换网络（PSTN）和基于变换器的排牙网络（TANet）等主流方法进行对比。研究结果表明，本文方法在评价指标上均有不同幅度的提升，能够充分融合全局与局部几何信息，改善牙齿姿态协调性和排列平滑性，为数字化正畸治疗规划提供了高效、标准化的智能支持。.