arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.04771cs.CVcs.AI
收藏

MADCrowner: 带边界的牙冠设计与模板变形与细化

MADCrowner: Margin Aware Dental Crown Design with Template Deformation and Refinement

Multimedia Laboratory, The Chinese University of Hong Kong（香港中文大学多媒体实验室）；College of Biomedical Engineering, Fudan University（复旦大学生物医学工程学院）；Sensetime Research（商汤科技研究院）；Department of Second Dental Center, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院第九人民医院第二牙科中心）；Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系）；Department of Computer Science, Rutgers University（罗格斯大学计算机科学系）；Centre for Perceptual and Interactive Intelligence (CPII) under InnoHK（InnoHK下的感知与交互智能中心）；Shanghai Stomatological Hospital, Fudan University（复旦大学上海牙科医院）

Linda Wei, Chang Liu, Wenran Zhang, Yuxuan Hu, Ruiyang Li, Feng Qi, Changyao Tian, Ke Wang, Yuanyuan Wang, Shaoting Zhang, Dimitris Metaxas, Hongsheng Li

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

MADCrowner通过结合模板变形和边缘分割网络，实现了高精度的牙冠设计，提升了几何精度和临床可行性。

摘要：

牙冠修复是治疗牙齿缺陷最常用的治疗方式之一，其中个性化牙冠设计至关重要。尽管计算机辅助设计（CAD）系统显著提高了牙冠设计的效率，但在临床工作流程中仍需要大量的手动调整。最近的研究探索了基于学习的方法在自动生成修复牙冠中的应用。然而，这些方法面临着空间分辨率不足、输出噪声大和表面重建过度延伸的挑战。为了解决这些限制，我们提出了总框架，一个带边界的网格生成框架，包括CrownDeformR和CrownSegger。受牙冠设计临床手动工作流程的启发，我们设计了CrownDeformR，根据解剖学上下文将初始模板变形为目标牙冠，该上下文由多尺度口腔扫描编码器提取。此外，我们引入了marginseg，一种新的边缘分割网络，用于提取目标牙的颈缘。CrownDeformR的性能在加入颈缘作为额外约束的情况下得到提升。它也被用作定制后处理方法的边界条件，以去除重建表面的过度延伸区域。我们构建了一个大规模的口腔扫描数据集，并进行了广泛的实验。所提出的方法在几何精度和临床可行性方面都显著优于现有方法。

英文摘要：

Dental crown restoration is one of the most common treatment modalities for tooth defect, where personalized dental crown design is critical. While computer-aided design (CAD) systems have notably enhanced the efficiency of dental crown design, extensive manual adjustments are still required in the clinic workflow. Recent studies have explored the application of learning-based methods for the automated generation of restorative dental crowns. Nevertheless, these approaches were challenged by inadequate spatial resolution, noisy outputs, and overextension of surface reconstruction. To address these limitations, we propose \totalframework, a margin-aware mesh generation framework comprising CrownDeformR and CrownSegger. Inspired by the clinic manual workflow of dental crown design, we designed CrownDeformR to deform an initial template to the target crown based on anatomical context, which is extracted by a multi-scale intraoral scan encoder. Additionally, we introduced \marginseg, a novel margin segmentation network, to extract the cervical margin of the target tooth. The performance of CrownDeformR improved with the cervical margin as an extra constraint. And it was also utilized as the boundary condition for the tailored postprocessing method, which removed the overextended area of the reconstructed surface. We constructed a large-scale intraoral scan dataset and performed extensive experiments. The proposed method significantly outperformed existing approaches in both geometric accuracy and clinical feasibility.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑