Accurate segmentation of the tooth point cloud is of great significance for diagnosis clinical assisting and treatment planning. Existing methods mostly employ semantic segmentation, focusing on the semantic feature between different types of teeth. However, due to the tightly packed structure of teeth, unclear boundaries, and the diversity of complex cases such as missing teeth, malposed teeth, semantic segmentation often struggles to achieve satisfactory results when dealing with complex dental cases. To address these issues, this paper propose BATISNet, a boundary-aware instance network for tooth point cloud segmentation. This network model consists of a feature extraction backbone and an instance segmentation module. It not only focuses on extracting the semantic features of different types of teeth but also learns the instance features of individual teeth. It helps achieve more robust and accurate tooth instance segmentation in complex clinical scenarios such as missing teeth and malposed teeth. Additionally, to further enhance the completeness and accuracy of tooth boundary segmentation, a boundary-aware loss function is designed to specifically supervise the boundary segmentation between instances. It mitigates effectively tooth adhesion and boundary ambiguity issues. Extensive experimental results show that BATISNet outperforms existing methods in tooth integrity segmentation, providing more reliable and detailed data support for practical clinical applications.

翻译：牙齿点云的精确分割对于辅助临床诊断与治疗规划具有重要意义。现有方法多采用语义分割，侧重于不同类型牙齿间的语义特征。然而，由于牙齿排列紧密、边界不清，以及存在缺牙、错位牙等复杂病例的多样性，语义分割在处理复杂牙科病例时往往难以取得理想效果。为解决这些问题，本文提出BATISNet，一种用于牙齿点云分割的边界感知实例网络。该网络模型由特征提取主干和实例分割模块组成，不仅关注提取不同类型牙齿的语义特征，同时学习单个牙齿的实例特征，有助于在缺牙、错位牙等复杂临床场景中实现更鲁棒、更精确的牙齿实例分割。此外，为进一步提升牙齿边界分割的完整性与准确性，设计了一种边界感知损失函数，专门监督实例间的边界分割，有效缓解牙齿粘连与边界模糊问题。大量实验结果表明，BATISNet在牙齿完整性分割方面优于现有方法，为实际临床应用提供了更可靠、更详细的数据支持。