用图论约束提升病理图像分割的拓扑一致性与鲁棒性
Graph-Theoretic Consistency for Robust and Topology-Aware Semi-Supervised Histopathology Segmentation
- 通过谱、连通分量和邻接统计对齐预测图与参考图
- 在5%-10%标注下达到当前最优，接近全监督性能
- 适合需要拓扑正确分割的医学图像分析场景
半监督语义分割（SSSS）在计算病理学中至关重要，因密集标注成本高且有限。现有方法常依赖像素级一致性，易传播噪声伪标签，导致分割结果碎片化或拓扑错误。本文提出拓扑图一致性（TGC）框架，通过对齐预测图与参考图之间的拉普拉斯谱、连通分量数和邻接统计，引入图论约束，强制全局拓扑结构，提升分割精度。在GlaS和CRAG数据集上的实验表明，TGC在5%-10%标注条件下达到当前最优性能，显著缩小与全监督方法的差距。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。