PGVMS: A Prompt-Guided Unified Framework for Virtual Multiplex IHC Staining With Pathological Semantic Learning
- 11 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (6) , 2866-2882
Abstract
Immunohistochemical (IHC) staining enables precise molecular profiling of protein expression, with over 200 clinically available antibody-based tests in modern pathology. However, comprehensive IHC analysis is frequently limited by insufficient tissue quantities in small biopsies. Therefore, virtual multiplex staining emerges as an innovative solution to digitally transform H&E images into multiple IHC representations, yet current methods still face three critical challenges: (1) inadequate semantic guidance for multi-staining, (2) inconsistent distribution of immunochemistry staining, and (3) spatial misalignment across different stain modalities. To overcome these limitations, we present a prompt-guided framework for virtual multiplex IHC staining using only uniplex training data (PGVMS). Our framework introduces three key innovations corresponding to each challenge: First, an adaptive prompt guidance mechanism employing a pathological visual language model dynamically adjusts staining prompts to resolve semantic guidance limitations (Challenge 1). Second, our protein-aware learning strategy (PALS) maintains precise protein expression patterns by direct quantification and constraint of protein distributions (Challenge 2). Third, the prototype-consistent learning strategy (PCLS) establishes cross-image semantic interaction to correct spatial misalignments (Challenge 3). Evaluated on two benchmark datasets, PGVMS demonstrates superior performance in pathological consistency. In general, PGVMS represents a paradigm shift from dedicated single-task models toward unified virtual staining systems.Keywords
All Related Versions
Funding Information
- Key Technologies Research and Development Program (2023YFF0723400)
- National Natural Science Foundation of China (62271475)
- Shenzhen–Hong Kong Joint Laboratory on Intelligence Computational Analysis for Tumor Imaging (E3G111)
- Guangdong Youth Talent Program (2024TQ08A386)
- Youth Innovation Promotion Association of the Chinese Academy of Sciences (2022365)
This publication has 24 references indexed in Scilit:
- A vision–language foundation model for precision oncologyNature, 2025
- VIMs: Virtual Immunohistochemistry Multiplex Staining via Text-to-Stain Diffusion Trained on Uniplex Stains2024
- Pathological Semantics-Preserving Learning for H&E-to-IHC Virtual Staining2024
- Advancing H&E-to-IHC Virtual Staining with Task-Specific Domain Knowledge for HER2 Scoring2024
- Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairs2023
- A visual–language foundation model for pathology image analysis using medical TwitterNature Medicine, 2023
- Multiplex Immunohistochemistry and Immunofluorescence: A Practical Update for PathologistsLaboratory Investigation, 2023
- Semi-supervised PR Virtual Staining for Breast Histopathological Images2022
- MVFStain: Multiple virtual functional stain histopathology images generation based on specific domain mappingMedical Image Analysis, 2022
- Contrastive Learning for Unpaired Image-to-Image Translation2020