通过可微分体素化，从分割图自动学习血管的参数化模型。
Parametric shape models for vessels learned from segmentations via differentiable voxelization
- 用可微分体素化将分割图转为参数化血管模型，无需真值参数
- 基于三次B样条建模中心线与半径，保证几何平滑连续
- 生成高保真网格，适合后续编辑，适用于复杂血管结构
血管是人体中结构复杂的解剖部位，已有多种表示方式。尽管体素化最为常见，但网格和参数化模型因其优良性质在诸多应用中至关重要。然而这些表示通常由分割结果提取，彼此独立使用。本文提出一种通过可微变换统一三类表示的框架。利用可微分体素化，我们通过形状到分割的拟合过程自动提取血管的参数化模型，从分割中学习形状参数，无需真实形状参数作为监督。血管采用三次B样条参数化中心线与半径，确保构造上的光滑与连续性。从学习到的形状参数中可微分地提取网格，生成可后处理的高保真网格。实验在主动脉、动脉瘤及脑血管上验证了方法对复杂血管几何结构的精确捕捉能力。
原文摘要 · Abstract (English)
Vessels are complex structures in the body that have been studied extensively in multiple representations. While voxelization is the most common of them, meshes and parametric models are critical in various applications due to their desirable properties. However, these representations are typically extracted through segmentations and used disjointly from each other. We propose a framework that joins the three representations under differentiable transformations. By leveraging differentiable voxelization, we automatically extract a parametric shape model of the vessels through shape-to-segmentation fitting, where we learn shape parameters from segmentations without the explicit need for ground-truth shape parameters. The vessel is parametrized as centerlines and radii using cubic B-splines, ensuring smoothness and continuity by construction. Meshes are differentiably extracted from the learned shape parameters, resulting in high-fidelity meshes that can be manipulated post-fit. Our method can accurately capture the geometry of complex vessels, as demonstrated by the volumetric fits in experiments on aortas, aneurysms, and brain vessels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。