TopoFuse：面向三维冷冻电子断层扫描分割的拓扑感知三平面融合
TopoFuse: Topology-Aware Tri-Planar Fusion for 3D Cryo-Electron Tomography Segmentation
- Virginia Tech（弗吉尼亚理工大学）
- National Institute of Technology, Kurukshetra（国立理工学院库鲁克谢特拉分校）
- Carnegie Mellon University（卡内基梅隆大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
TopoFuse通过可微投影算子结构性地强制拓扑约束，在冷冻电子断层扫描分割中减少拓扑错误，较软损失基线降低54%贝蒂数误差并提升Dice 4.6点。
AI中文摘要：
冷冻电子断层扫描的自动化分割通常会产生体素精确但拓扑破损的掩膜：膜发生断裂，细胞器相互融合，封闭腔体塌陷。现有的拓扑感知损失函数能减少这些违规，但无法消除它们，因为拓扑是通过梯度压力而非结构强制来鼓励的。我们提出TopoFuse，将拓扑重新定义为可微投影算子而非损失惩罚。在每次前向传播中，投影算子$\mathrm{Proj}_T$（一种PH引导的稀疏编辑）通过瓶颈匹配识别导致拓扑违规的关键体素，并应用稀疏编辑以满足维度$d \in \{0,2\}$的指定拓扑目标（图表特征计数和寿命预算）。若投影收敛，输出在降采样网格（$s=2$）上满足这些约束；若不收敛，修复证书明确暴露此情况，支持下游过滤。拓扑先验头直接从输入特征预测修正目标，在推理时消除对真实拓扑的依赖。在三个冷冻电子断层扫描基准上，TopoFuse将贝蒂数误差比最强软损失基线降低54%（$p < 0.001$），Dice提高4.6个百分点，且仅编辑3.1%的体素即可实现此效果。
英文摘要：
Automated segmentation of cryo-electron tomograms routinely produces masks that are voxel-accurate but topologically broken: membranes fragment, organelles merge into one another, and enclosed cavities collapse. Existing topology-aware losses reduce these violations but cannot eliminate them, because topology is encouraged through gradient pressure rather than structurally enforced. We introduce TopoFuse, which reframes topology as a differentiable projection operator rather than a loss penalty. At each forward pass, the projection operator $\mathrm{Proj}_T$ (a PH-guided sparse edit) identifies the critical voxels responsible for topological violations via bottleneck matching and applies sparse edits to satisfy a specified topology target (diagram feature counts and lifetime budgets) for dimensions $d \in \{0,2\}$. If the projection converges, the output satisfies those constraints on the downsampled grid ($s=2$); when it does not, a repair certificate exposes this explicitly, enabling downstream filtering. A topology prior head predicts the correction target directly from input features, removing any dependence on ground-truth topology at inference. Across three cryo-ET benchmarks, TopoFuse reduces Betti number error by 54% over the strongest soft-loss baseline ($p < 0.001$), improves Dice by 4.6 points, and edits only 3.1% of voxels to achieve this.
