mlsanityData to 14 Oct 2026

USIGAN: Unbalanced Self-Information Feature Transport for Weakly Paired Image IHC Virtual Staining

arXiv 2507.05843 ↗First posted 8 Jul 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Immunohistochemical (IHC) virtual staining is a task that generates virtual IHC images from H&E images while maintaining pathological semantic consistency with adjacent slices. This task aims to achieve cross-domain mapping between morphological structures and staining patterns through generative models, providing an efficient and cost-effective solution for pathological analysis. However, under weakly paired conditions, spatial heterogeneity between adjacent slices presents significant challenges. This can lead to inaccurate one-to-many mappings and generate results that are inconsistent with the pathological semantics of adjacent slices. To address this issue, we propose a novel unbalanced self-information feature transport for IHC virtual staining, named USIGAN, which extracts global morphological semantics without relying on positional correspondence.By removing weakly paired terms in the joint marginal distribution, we effectively mitigate the impact of weak pairing on joint distributions, thereby significantly improving the content consistency and pathological semantic consistency of the generated results. Moreover, we design the Unbalanced Optimal Transport Consistency (UOT-CTM) mechanism and the Pathology Self-Correspondence (PC-SCM) mechanism to construct correlation matrices between H&E and generated IHC in image-level and real IHC and generated IHC image sets in intra-group level.. Experiments conducted on two publicly available datasets demonstrate that our method achieves superior performance across multiple clinically significant metrics, such as IoD and Pearson-R correlation, demonstrating better clinical relevance.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 31 of its 60 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

31 of 60 references.

References · 31

  1. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  3. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  4. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 639
  5. 2023Denoising Diffusion Bridge Modelscited by 178
  6. 2023Unpaired Image-to-Image Translation via Neural Schr"odinger Bridgecited by 96
  7. 2018Deep learning-based virtual histology staining using auto-fluorescence of label-free tissuecited by 70
  8. 2021The Spatially-Correlative Loss for Various Image Translation Taskscited by 66
  9. 2022BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pixcited by 61
  10. 2020Deep learning-based transformation of the H&E stain into special stainscited by 55
  11. 2021Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translationcited by 45
  12. 2022Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Taskscited by 42
19 more
  1. 2021Unbalanced Feature Transport for Exemplar-based Image Translationcited by 41
  2. 2022QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translationcited by 39
  3. 2023Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairscited by 38
  4. 2016Scaling Algorithms for Unbalanced Transport Problemscited by 36
  5. 2021Contrastive Learning Improves Model Robustness Under Label Noisecited by 36
  6. 2022Modulated Contrast for Versatile Image Synthesiscited by 23
  7. 2021Label-free virtual HER2 immunohistochemical staining of breast tissue using deep learningcited by 22
  8. 2024Pathological Semantics-Preserving Learning for H&E-to-IHC Virtual Stainingcited by 21
  9. 2022Marginal Contrastive Correspondence for Guided Image Generationcited by 19
  10. 2023Predicting Ki67, ER, PR, and HER2 Statuses from H&E-stained Breast Cancer Imagescited by 14
  11. 2024Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruningcited by 10
  12. 2024VIMs: Virtual Immunohistochemistry Multiplex staining via Text-to-Stain Diffusion Trained on Uniplex Stainscited by 10
  13. 2025Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiencycited by 9
  14. 2022Rethinking the Paradigm of Content Constraints in Unpaired Image-to-Image Translationcited by 7
  15. 2024RegWSI: Whole Slide Image Registration using Combined Deep Feature- and Intensity-Based Methods: Winner of the ACROBAT 2023 Challengecited by 7
  16. 2025Hybrid Spiking Vision Transformer for Object Detection with Event Camerascited by 7
  17. 2024Unpaired Multi-Domain Histopathology Virtual Staining using Dual Path Prompted Inversioncited by 6
  18. 2025HistDiST: Histopathological Diffusion-based Stain Transfercited by 5
  19. 2025Efficient ANN-SNN Conversion with Error Compensation Learningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Topology-aware Pathological Consistency Matching for Weakly-Paired IHC Virtual Stainingcited by 1
  2. 2026ContiStain: Cross-Domain Relation-Preserving Distillation for Continual Multi-Domain Virtual IHC Stainingcited by 0
  3. 2026Towards Reliable Stain Transfer: An Iterative Data-Model Co-Optimization Framework Based on Multimodal Expert-Guided Assessmentcited by 0