AGMDT: Virtual Staining of Renal Histology Images with Adjacency-Guided Multi-Domain Transfer

TL;DR

The paper introduces AGMDT, a novel framework for virtual staining of renal histology images that leverages correlations across serial tissue slices to improve multi-domain image translation without pixel-level alignment.

Contribution

AGMDT is the first method to utilize inter-slice correlations for multi-domain virtual staining, avoiding pixel-level alignment and enhancing structural detail fidelity.

Findings

AGMDT outperforms state-of-the-art methods in quantitative and morphological metrics.

The framework effectively balances pixel-level alignment with unpaired domain transfer.

A high-quality multi-domain renal histological dataset was constructed for training and evaluation.

Abstract

Renal pathology, as the gold standard of kidney disease diagnosis, requires doctors to analyze a series of tissue slices stained by H&E staining and special staining like Masson, PASM, and PAS, respectively. These special staining methods are costly, time-consuming, and hard to standardize for wide use especially in primary hospitals. Advances of supervised learning methods have enabled the virtually conversion of H&E images into special staining images, but achieving pixel-to-pixel alignment for training remains challenging. In contrast, unsupervised learning methods regarding different stains as different style transfer domains can utilize unpaired data, but they ignore the spatial inter-domain correlations and thus decrease the trustworthiness of structural details for diagnosis. In this paper, we propose a novel virtual staining framework AGMDT to translate images into other domains by avoiding pixel-level alignment and meanwhile utilizing the correlations among adjacent tissue slices. We first build a high-quality multi-domain renal histological dataset where each specimen case comprises a series of slices stained in various ways. Based on it, the proposed framework AGMDT discovers patch-level aligned pairs across the serial slices of multi-domains through glomerulus detection and bipartite graph matching, and utilizes such correlations to supervise the end-to-end model for multi-domain staining transformation. Experimental results show that the proposed AGMDT achieves a good balance between the precise pixel-level alignment and unpaired domain transfer by exploiting correlations across multi-domain serial pathological slices, and outperforms the state-of-the-art methods in both quantitative measure and morphological details.