English

Graph-Theoretic Consistency for Robust and Topology-Aware Semi-Supervised Histopathology Segmentation

Image and Video Processing 2025-11-14 v3 Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@article{arxiv.2509.22689,
  title  = {Graph-Theoretic Consistency for Robust and Topology-Aware Semi-Supervised Histopathology Segmentation},
  author = {Ha-Hieu Pham and Minh Le and Han Huynh and Nguyen Quoc Khanh Le and Huy-Hieu Pham},
  journal= {arXiv preprint arXiv:2509.22689},
  year   = {2025}
}

Comments

Accepted to the AAAI 2026 Student Abstract and Poster Program

R2 v1 2026-07-01T05:59:27.743Z