A Three-Step Framework for Automatically Registering Immunohistochemical and H&E Stained Whole Slide Images Targeting Clinical Applications

Joint analysis of multiple biomarker images and tissue morphology plays an important role in disease diagnosis, treatment planning, and drug development. This necessitates precise cross-staining comparison among Whole Slide Images (WSIs) of immunohistochemical (IHC) and hematoxylin and eosin (H&E) stained microscopic slides. In this paper, we propose a novel three-step, feature-based, automatic cross-staining WSI alignment method to support clinical practice. The comparative and ablation experiments have shown the good performance of our method, suggesting that it can offer a simple and effective cross-staining WSIs alignment contributing to pathological diagnosis.