发表机构
Bioinformatics Institute, Agency for Science, Technology and Research (A*STAR); College of Computing and Data Science, Nanyang Technological University; National Heart Centre Singapore（生物信息学研究所，科技研究局（A*STAR）; 南洋理工大学计算与数据科学学院; 新加坡国家心脏中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PPCAR-Net通过投影细化的参数化网络，直接从稀疏X射线血管造影视图预测分支结构的中心线和半径，无需点匹配或三角测量，实现高精度和实时重建。
AI 中文摘要
稀疏视图的三维冠状动脉重建通常依赖于跨视图对应和三角测量，这容易受到血管重叠和缩短的影响，或者依赖于体积预测后提取血管图，这不能直接提供中心线和半径。我们引入了PPCAR-Net，一种投影细化的参数化冠状动脉重建网络，它直接预测分支结构的中心线和半径表示，无需显式点匹配、三角测量或中间体积。给定可变数量的分割视图，一个粗略预测器结合冻结的VGGT特征与学习的分支查询，以估计分支存在性、B样条中心线轨迹和密集半径轮廓。然后，投影引导的几何和半径细化器从输入视图中采样局部证据，并应用通过三维监督学习的残差校正。我们定量和定性地评估表示保真度和稀疏视图重建。在从CT衍生的冠状动脉解剖生成的模拟血管造影掩膜上，PPCAR-Net产生更好的连接动脉重建，并实现强大的中心线准确性，特别是对RCA，同时保持竞争力的体积重叠。从粗到细的推理耗时121毫秒，实现实时重建。
英文摘要
Sparse-view 3D coronary reconstruction commonly relies on cross-view correspondence and triangulation, which are vulnerable to vessel overlap and foreshortening, or on volumetric prediction followed by vascular-graph extraction, which does not directly provide centrelines and radii. We introduce PPCAR-Net, a projection-refined parametric coronary artery reconstruction network that directly predicts a branch-structured centreline-and-radius representation without explicit point matching, triangulation, or an intermediate volume. Given a variable number of segmented views, a coarse predictor combines frozen VGGT features with learned branch queries to estimate branch presence, B-spline centreline trajectories, and dense radius profiles. Projection-guided geometry and radius refiners then sample local evidence from the input views and apply residual corrections learned with 3D supervision. We evaluate representation fidelity and sparse-view reconstruction quantitatively and qualitatively. On simulated angiographic masks generated from CT-derived coronary anatomy, PPCAR-Net produces better connected artery reconstructions and achieves strong centreline accuracy, particularly for RCA, while maintaining competitive volumetric overlap. Coarse-to-fine inference takes 121 ms, enabling real-time reconstruction.
Comments22 pages, 5 figures, 10 tables, including references and appendix. Code and pretrained models: https://github.com/G2304138H/PPCAR-Net . Project page with video results: https://G2304138H.github.io/PPCAR-Net/
