From Pixels to Pathology: Restoration Diffusion for Diagnostic-Consistent Virtual IHC

TL;DR

This paper introduces Star-Diff, a diffusion model for virtual IHC staining from H&E images that preserves tissue structure and biomarker variability, with a new evaluation metric for diagnostic consistency.

Contribution

The work presents a novel structure-aware diffusion model and a semantic fidelity score for more accurate and clinically relevant virtual IHC synthesis.

Findings

Star-Diff outperforms existing methods in visual quality and diagnostic accuracy.

The Semantic Fidelity Score effectively evaluates diagnostic relevance under misalignment.

Rapid inference makes the method suitable for intraoperative applications.

Abstract

Hematoxylin and eosin (H&E) staining is the clinical standard for assessing tissue morphology, but it lacks molecular-level diagnostic information. In contrast, immunohistochemistry (IHC) provides crucial insights into biomarker expression, such as HER2 status for breast cancer grading, but remains costly and time-consuming, limiting its use in time-sensitive clinical workflows. To address this gap, virtual staining from H&E to IHC has emerged as a promising alternative, yet faces two core challenges: (1) Lack of fair evaluation of synthetic images against misaligned IHC ground truths, and (2) preserving structural integrity and biological variability during translation. To this end, we present an end-to-end framework encompassing both generation and evaluation in this work. We introduce Star-Diff, a structure-aware staining restoration diffusion model that reformulates virtual staining as an image restoration task. By combining residual and noise-based generation pathways, Star-Diff maintains tissue structure while modeling realistic biomarker variability. To evaluate the diagnostic consistency of the generated IHC patches, we propose the Semantic Fidelity Score (SFS), a clinical-grading-task-driven metric that quantifies class-wise semantic degradation based on biomarker classification accuracy. Unlike pixel-level metrics such as SSIM and PSNR, SFS remains robust under spatial misalignment and classifier uncertainty. Experiments on the BCI dataset demonstrate that Star-Diff achieves state-of-the-art (SOTA) performance in both visual fidelity and diagnostic relevance. With rapid inference and strong clinical alignment,it presents a practical solution for applications such as intraoperative virtual IHC synthesis.