Fast, Unsupervised Framework for Registration Quality Assessment of Multi-stain Histological Whole Slide Pairs

TL;DR

This paper introduces a fast, unsupervised method for assessing the quality of registration between multi-stain histological whole slide images, enabling reliable, real-time quality control without ground-truth annotations.

Contribution

The study presents a novel, computationally efficient framework combining tissue masks and deformation metrics for registration quality assessment of histopathological images.

Findings

Strong correlation with human evaluations across multiple markers

Reliable real-time assessment without ground-truth annotations

Suitable for large-scale digital pathology quality control

Abstract

High-fidelity registration of histopathological whole slide images (WSIs), such as hematoxylin & eosin (H&E) and immunohistochemistry (IHC), is vital for integrated molecular analysis but challenging to evaluate without ground-truth (GT) annotations. Existing WSI-level assessments -- using annotated landmarks or intensity-based similarity metrics -- are often time-consuming, unreliable, and computationally intensive, limiting large-scale applicability. This study proposes a fast, unsupervised framework that jointly employs down-sampled tissue masks- and deformations-based metrics for registration quality assessment (RQA) of registered H&E and IHC WSI pairs. The masks-based metrics measure global structural correspondence, while the deformations-based metrics evaluate local smoothness, continuity, and transformation realism. Validation across multiple IHC markers and multi-expert assessments demonstrate a strong correlation between automated metrics and human evaluations. In the absence of GT, this framework offers reliable, real-time RQA with high fidelity and minimal computational resources, making it suitable for large-scale quality control in digital pathology.