Score-based Diffusion Model for Unpaired Virtual Histology Staining

TL;DR

This paper introduces a novel score-based diffusion model guided by mutual information for unpaired virtual histology staining, effectively translating H&E images into IHC images while preserving tissue structure and enabling controllable staining.

Contribution

It presents a new MI-guided diffusion framework with a global energy function, a customized reverse diffusion process, and local contrastive learning for unpaired virtual staining.

Findings

Outperforms state-of-the-art virtual staining methods

Achieves high structural fidelity at cellular level

Demonstrates strong biomedical potential

Abstract

Hematoxylin and eosin (H&E) staining visualizes histology but lacks specificity for diagnostic markers. Immunohistochemistry (IHC) staining provides protein-targeted staining but is restricted by tissue availability and antibody specificity. Virtual staining, i.e., computationally translating the H&E image to its IHC counterpart while preserving the tissue structure, is promising for efficient IHC generation. Existing virtual staining methods still face key challenges: 1) effective decomposition of staining style and tissue structure, 2) controllable staining process adaptable to diverse tissue and proteins, and 3) rigorous structural consistency modelling to handle the non-pixel-aligned nature of paired H&E and IHC images. This study proposes a mutual-information (MI)-guided score-based diffusion model for unpaired virtual staining. Specifically, we design 1) a global MI-guided energy function that disentangles the tissue structure and staining characteristics across modalities, 2) a novel timestep-customized reverse diffusion process for precise control of the staining intensity and structural reconstruction, and 3) a local MI-driven contrastive learning strategy to ensure the cellular level structural consistency between H&E-IHC images. Extensive experiments demonstrate the our superiority over state-of-the-art approaches, highlighting its biomedical potential. Codes will be open-sourced upon acceptance.