cs.CVNov 5, 2026

TRiST: Topology-Reinforced Swin Transformer for Medical Image Analysis

Authors: Pengfei Gu, Huimin Li, Guangyu Meng, Hao Zheng, Haoteng Tang, Bin Fu, Danny Z. Chen

Organizations: Department of Computer Science, The University of Texas Rio Grande Valley · School of Mathematical and Statistical Sciences, The University of Texas Rio Grande Valley · Department of Computer Science and Engineering, University of Notre Dame · School of Computing and Informatics, University of Louisiana at Lafayette

Abstract

Medical images contain topological patterns, such as connected components and loops, at scales ranging from small lesions to organ boundaries. Although hierarchical Vision Transformers have advanced medical image analysis, they do not explicitly incorporate topology throughout their multiscale representations. We propose Topology-Reinforced Swin Transformer (TRiST), a framework that integrates topological information into feature construction, refinement, and attention. First, a Hierarchical Multi-Scale Topology Representation algorithm computes 2D persistent homology (H0 and H1) independently at four native Swin stages, producing descriptors aligned with each stage's token grid rather than downsampling fine-scale topology. Second, a Band-Aware H0/H1 Residual Refinement module uses gated residual networks to process short-, medium-, and long-persistence information separately. Third, a Persistence-Band Progressive Attention Bias converts stage-specific descriptors into learned key-saliency scores that directly modify shifted-window attention logits. We instantiate TRiST as Topo-SwinV2-B for classification and Topo-Swin-UNet for segmentation, preserving the underlying Swin-based backbones. Experiments on five medical image datasets show consistent improvements over Swin-based baselines and competitive performance relative to existing topology-augmented methods.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SwInception -- Local Attention Meets Convolutions

    May 28, 2026David Hagerman, Roman Naeem, Jakob Lindqvist +3Hybrid CNN-Transformer ArchitecturesEfficient ViTs

  2. VTRL-Med: Progressive Visual Refinement with Topology-Guided Regularization for Medical Image Clustering

    Oct 23, 2026Guangyu Meng, Pengfei Gu, Peixian Liang +3Deep ClusteringMedical Image Analysis

  3. TopoCL: Topological Contrastive Learning for Medical Imaging

    Mar 15, 2026Guangyu Meng, Pengfei Gu, Peixian Liang +3Medical Image Representation LearningContrastive Learning