超越体积重叠：面向拓扑感知的冠状动脉分割的表面匹配
Beyond Volume Overlap: Surface Matching for Topology-Aware Coronary Artery Segmentation
AI总结：
针对冠状动脉分割中Dice指标忽视远端分支的问题，提出表面匹配度量与可微表面损失，在多个基准上显著提升表面F1并恢复缺失血管。
AI中文摘要：
在冠状动脉计算机断层扫描血管造影（CCTA）上准确分割冠状动脉对于诊断冠状动脉疾病至关重要。深度网络通常使用Dice系数进行训练和评估，但体积重叠指标不适用于细长管状解剖结构：由于大多数体素属于少数近端粗大节段，缺失远端分支几乎不影响Dice，尽管这会严重破坏临床使用所需的连通性。我们引入了一种表面度量，通过局部血管半径容差下的二分匹配来匹配预测和参考表面点，报告精确率、召回率和F1，并解耦假阳性（多余分支）和假阴性（缺失分支），这是对称Dice无法区分的。利用该度量，我们表明强Dice训练的基线遗漏的血管表面远多于其幻觉产生的，其高Dice掩盖了这种不对称性。在此基础上，我们提出了一种可微分的表面损失，同时抑制多余质量并恢复缺失结构，通过在两个公共基准（Image-CAS, ASOCA）上微调三个骨干网络（nnU-Net, SwinUNETR, NexToU）进行验证。与匹配轮数的对照组相比，它通过恢复缺失的远端血管显著提高了表面F1，同时保持相当的Dice。我们的发现主张测量和优化血管表面，而不是其重叠的体积。代码
英文摘要：
Accurate coronary artery segmentation on coronary computed tomography angiography (CCTA) is essential for diagnosing coronary artery disease. Deep networks are conventionally trained and evaluated with the Dice coefficient, but volume-overlap metrics are poorly suited to thin, tubular anatomy: since most voxels belong to a few thickproximal segments, a missing distal branch barely affects Dice despite severely disrupting the connectivity required for clinical use. We introduce a surface metric that matches predicted and reference surface points via bipartite assignment under a localized, vessel-radius tolerance, reporting precision, recall, and F1 with decoupled false positives (spurious branches) and false negatives (missed branches) a distinction the symmetric Dice cannot make. With it we show that a strong Dice-trained baseline omits far more vessel surface than it hallucinates, an asymmetry its high Dice hides. Building on this, we propose a differentiable surface loss that simultaneously suppresses spurious mass and recovers absent structure, validated by fine-tuning three backbones (nnU-Net, SwinUNETR, NexToU) on two public benchmarks (Image-CAS, ASOCA). Against a matched-epoch control, it significantly improves surface F1 by recovering missed distal vessels at comparable Dice. Our findings argue for measuring and optimizing the vessel surface, not the volume it overlaps. Code
