基于图论一致性的鲁棒且拓扑感知的半监督组织病理学分割
Graph-Theoretic Consistency for Robust and Topology-Aware Semi-Supervised Histopathology Segmentation
AI总结：
提出拓扑图一致性（TGC）框架，通过对齐预测图与参考图的拉普拉斯谱、组件计数和邻接统计，在仅5-10%标注下实现最先进的半监督分割性能。
摘要：
半监督语义分割（SSSS）在计算病理学中至关重要，因为密集标注成本高昂且有限。现有方法通常依赖像素级一致性，这会传播噪声伪标签并产生碎片化或拓扑无效的掩膜。我们提出拓扑图一致性（TGC），一个通过对齐预测图与参考图的拉普拉斯谱、组件计数和邻接统计来整合图论约束的框架。这强制执行全局拓扑并提高分割精度。在GlaS和CRAG上的实验表明，TGC在5-10%监督下实现了最先进的性能，并显著缩小了与全监督的差距。
英文摘要：
Semi-supervised semantic segmentation (SSSS) is vital in computational pathology, where dense annotations are costly and limited. Existing methods often rely on pixel-level consistency, which propagates noisy pseudo-labels and produces fragmented or topologically invalid masks. We propose Topology Graph Consistency (TGC), a framework that integrates graph-theoretic constraints by aligning Laplacian spectra, component counts, and adjacency statistics between prediction graphs and references. This enforces global topology and improves segmentation accuracy. Experiments on GlaS and CRAG demonstrate that TGC achieves state-of-the-art performance under 5-10% supervision and significantly narrows the gap to full supervision.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
