Cross-Modality Learning for Predicting IHC Biomarkers from H&E-Stained Whole-Slide Images

2025-06-18

AI Summary

To address the clinical bottlenecks of immunohistochemistry (IHC)—namely, high cost, lengthy processing time, and dependence on expert interpretation—this study proposes a novel unsupervised paradigm for predicting IHC biomarker expression directly from routine hematoxylin and eosin (H&E) whole-slide images (WSIs). We introduce HistoStainAlign, the first framework to align H&E and IHC embeddings across modalities via contrastive learning, without requiring image registration or pixel-/patch-level annotations, thereby effectively decoupling tissue morphology from molecular expression features. The method integrates multi-scale WSI modeling with deep contrastive representation learning. Evaluated on three critical biomarkers—p53, PD-L1, and Ki-67—it achieves weighted F1 scores of 0.735, 0.830, and 0.723, respectively, demonstrating clinical feasibility as an IHC pre-screening tool. This work establishes an interpretable, low-dependency technical pathway for AI-assisted digital pathology diagnosis.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Multi-instance/Multi-view Learning
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Hematoxylin and Eosin (H&E) staining is a cornerstone of pathological analysis, offering reliable visualization of cellular morphology and tissue architecture for cancer diagnosis, subtyping, and grading. Immunohistochemistry (IHC) staining provides molecular insights by detecting specific proteins within tissues, enhancing diagnostic accuracy, and improving treatment planning. However, IHC staining is costly, time-consuming, and resource-intensive, requiring specialized expertise. To address these limitations, this study proposes HistoStainAlign, a novel deep learning framework that predicts IHC staining patterns directly from H&E whole-slide images (WSIs) by learning joint representations of morphological and molecular features. The framework integrates paired H&E and IHC embeddings through a contrastive training strategy, capturing complementary features across staining modalities without patch-level annotations or tissue registration. The model was evaluated on gastrointestinal and lung tissue WSIs with three commonly used IHC stains: P53, PD-L1, and Ki-67. HistoStainAlign achieved weighted F1 scores of 0.735 [95% Confidence Interval (CI): 0.670-0.799], 0.830 [95% CI: 0.772-0.886], and 0.723 [95% CI: 0.607-0.836], respectively for these three IHC stains. Embedding analyses demonstrated the robustness of the contrastive alignment in capturing meaningful cross-stain relationships. Comparisons with a baseline model further highlight the advantage of incorporating contrastive learning for improved stain pattern prediction. This study demonstrates the potential of computational approaches to serve as a pre-screening tool, helping prioritize cases for IHC staining and improving workflow efficiency.

Problem

• Predicts IHC biomarkers from H&E images computationally
• Reduces cost and time of IHC staining process
• Improves diagnostic workflow efficiency via deep learning

Innovation

• Deep learning predicts IHC from H&E images
• Contrastive training aligns H&E and IHC features
• No patch annotations or registration required