发表机构
University of Lincoln; Lincolnshire Heart Centre; United Lincolnshire Teaching Hospitals Trust; De Montfort University（林肯大学; 林肯郡心脏中心; 联合林肯郡教学医院信托基金; 德蒙福特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出BCS及可微替代物soft-BCS，用于评估冠状动脉分割的分叉连通性，发现其与FFR-CT决策一致性相关，建议同时报告分支恢复及连通性的度量。
AI 中文摘要
基于CT血管造影的血流储备分数（FFR-CT）可模拟患者特异性血管模型中的血流，其准确性不仅取决于体积重叠，还依赖于分割树的连通性：某一分割可达到较高的Dice系数，但可能切断一处分叉，导致下游子树丢失，进而反转治疗决策。clDice和Skeleton Recall等拓扑感知损失作用于全局中心线，可能遗漏局部断裂。本研究提出分叉连通性评分（BCS），该评分针对每个真实分叉评估连通性，以及其可微训练替代物soft-BCS。BCS捕捉到标准度量遗漏的分割质量属性：它对连通性断裂反应强烈，而在保持连通性的狭窄情况下基本不变。较高的BCS与求解器在预测几何结构和真实几何结构上做出的FFR-CT决策一致性更密切相关，在严重病变中最为明显（OR值2.16，95%置信区间[1.23,4.18]）。两个决策来自同一求解器，因此这反映的是几何保真度而非临床保真度。在训练中，soft-BCS和Skeleton Recall恢复相同分支，但构建不同的树。恢复分支与保持分支连通性是可分离的属性，因此建议分别报告这两种度量。
英文摘要
Fractional flow reserve derived from CT angiography (FFR-CT) simulates flow through a patient-specific vessel model, so its accuracy depends on the connectedness of the segmented tree, not only on volumetric overlap: a segmentation can reach high Dice yet sever a bifurcation, dropping the downstream subtree and reversing the treatment decision. Topology-aware losses such as clDice and Skeleton Recall act on the global centreline and can miss localised breaks. We study the Bifurcation Connectedness Score (BCS), which scores connectedness at each ground-truth bifurcation, and soft-BCS, its differentiable training surrogate. BCS captures a property of segmentation quality the standard metrics miss: it responds strongly to breaks in connectedness while staying largely unchanged under connectedness-preserving narrowing. Higher BCS accompanies closer agreement between the FFR-CT decisions a solver makes on predicted versus ground-truth geometry, most clearly in severe disease (OR 2.16, CI [1.23, 4.18]). Both decisions come from the same solver, so this reflects geometric, not clinical, fidelity. In training, soft-BCS and Skeleton Recall recover the same branches but build different trees. Recovering branches and keeping them connected are separable properties, so we recommend reporting a measure of each.
CommentsAccepted at STACOM 2026 (MICCAI workshop). 11 pages, 3 figures, 2 tables
