Cross-channel Perception Learning for H&E-to-IHC Virtual Staining

TL;DR

This paper introduces a novel cross-channel perception learning strategy for H&E-to-IHC virtual staining, improving the preservation of pathological features and image quality by leveraging dual-channel feature extraction and correlation analysis.

Contribution

The study proposes CCPL, a new method that decomposes immunohistochemical staining into dual channels and enhances virtual staining through cross-channel correlation and feature distillation, addressing limitations of existing approaches.

Findings

CCPL effectively preserves pathological features in virtual stained images.

The method achieves superior quantitative metrics like PSNR, SSIM, PCC, and FID.

Pathologists' evaluations confirm high-quality and diagnostically useful virtual staining.

Abstract

With the rapid development of digital pathology, virtual staining has become a key technology in multimedia medical information systems, offering new possibilities for the analysis and diagnosis of pathological images. However, existing H&E-to-IHC studies often overlook the cross-channel correlations between cell nuclei and cell membranes. To address this issue, we propose a novel Cross-Channel Perception Learning (CCPL) strategy. Specifically, CCPL first decomposes HER2 immunohistochemical staining into Hematoxylin and DAB staining channels, corresponding to cell nuclei and cell membranes, respectively. Using the pathology foundation model Gigapath's Tile Encoder, CCPL extracts dual-channel features from both the generated and real images and measures cross-channel correlations between nuclei and membranes. The features of the generated and real stained images, obtained through the Tile Encoder, are also used to calculate feature distillation loss, enhancing the model's feature extraction capabilities without increasing the inference burden. Additionally, CCPL performs statistical analysis on the focal optical density maps of both single channels to ensure consistency in staining distribution and intensity. Experimental results, based on quantitative metrics such as PSNR, SSIM, PCC, and FID, along with professional evaluations from pathologists, demonstrate that CCPL effectively preserves pathological features, generates high-quality virtual stained images, and provides robust support for automated pathological diagnosis using multimedia medical data.