Automatic Multi-Stain Registration of Whole Slide Images in Histopathology

TL;DR

This paper introduces an automatic, two-step feature-based method for aligning gigapixel whole slide images across different stains, enabling precise cross-staining tissue comparison crucial for disease diagnosis.

Contribution

The proposed method automates multi-stain WSI registration using SIFT and FSC, achieving high accuracy and efficiency for large histopathology images.

Findings

Average Jaccard similarity index of 0.942 with manual registration

Automatic alignment handles translation, rotation, and scaling

Facilitates localization of tiny metastatic foci

Abstract

Joint analysis of multiple biomarker images and tissue morphology is important for disease diagnosis, treatment planning and drug development. It requires cross-staining comparison among Whole Slide Images (WSIs) of immuno-histochemical and hematoxylin and eosin (H&E) microscopic slides. However, automatic, and fast cross-staining alignment of enormous gigapixel WSIs at single-cell precision is challenging. In addition to morphological deformations introduced during slide preparation, there are large variations in cell appearance and tissue morphology across different staining. In this paper, we propose a two-step automatic feature-based cross-staining WSI alignment to assist localization of even tiny metastatic foci in the assessment of lymph node. Image pairs were aligned allowing for translation, rotation, and scaling. The registration was performed automatically by first detecting landmarks in both images, using the scale-invariant image transform (SIFT), followed by the fast sample consensus (FSC) protocol for finding point correspondences and finally aligned the images. The Registration results were evaluated using both visual and quantitative criteria using the Jaccard index. The average Jaccard similarity index of the results produced by the proposed system is 0.942 when compared with the manual registration.