Progressive Translation of H&E to IHC with Enhanced Structural Fidelity

2025-11-03

AI Summary

Hematoxylin and eosin (H&E) stained slides lack cost-effective means to infer spatial protein distribution, necessitating immunohistochemistry (IHC) staining. Method: This paper proposes a progressive generative network that decouples modeling of tissue structure, color appearance, and cellular boundaries—overcoming fidelity bottlenecks in existing stain translation methods regarding structural preservation and diaminobenzidine (DAB) chromogen accuracy. Built upon the ASP framework, it integrates PatchNCE contrastive learning and introduces two novel losses: DAB concentration loss and image gradient loss, enabling stage-wise optimization of multi-modal visual features. Results: Evaluated on HER2 and ER datasets, the method significantly improves detail fidelity and photorealism of generated IHC-equivalent images. It achieves superior nuclear/membranous localization clarity, structural continuity, and staining specificity compared to state-of-the-art approaches, offering a high-cost-benefit alternative for computational pathology protein expression analysis.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Compared to hematoxylin-eosin (H&E) staining, immunohistochemistry (IHC) not only maintains the structural features of tissue samples, but also provides high-resolution protein localization, which is essential for aiding in pathology diagnosis. Despite its diagnostic value, IHC remains a costly and labor-intensive technique. Its limited scalability and constraints in multiplexing further hinder widespread adoption, especially in resource-limited settings. Consequently, researchers are increasingly exploring computational stain translation techniques to synthesize IHC-equivalent images from H&E-stained slides, aiming to extract protein-level information more efficiently and cost-effectively. However, most existing stain translation techniques rely on a linearly weighted summation of multiple loss terms within a single objective function, strategy that often overlooks the interdepedence among these components-resulting in suboptimal image quality and an inability to simultaneously preserve structural authenticity and color fidelity. To address this limitation, we propose a novel network architecture that follows a progressive structure, incorporating color and cell border generation logic, which enables each visual aspect to be optimized in a stage-wise and decoupled manner. To validate the effectiveness of our proposed network architecture, we build upon the Adaptive Supervised PatchNCE (ASP) framework as our baseline. We introduce additional loss functions based on 3,3'-diaminobenzidine (DAB) chromogen concentration and image gradient, enhancing color fidelity and cell boundary clarity in the generated IHC images. By reconstructing the generation pipeline using our structure-color-cell boundary progressive mechanism, experiments on HER2 and ER datasets demonstrated that the model significantly improved visual quality and achieved finer structural details.

Problem

• Synthesizing IHC images from H&E slides computationally to reduce costs
• Overcoming suboptimal quality in stain translation techniques
• Preserving structural authenticity and color fidelity simultaneously

Innovation

• Progressive network architecture for stage-wise optimization
• Color and cell border generation logic integration
• Enhanced loss functions for structural and color fidelity