Multimarginal Wasserstein Barycenter for Stain Normalization and Augmentation

TL;DR

This paper introduces a multimarginal Wasserstein barycenter method for stain normalization and augmentation in histopathology images, improving diagnostic accuracy and robustness by effectively handling variations in H&E stained images.

Contribution

The paper proposes a novel mathematically robust approach using multimarginal Wasserstein barycenters for simultaneous stain normalization and augmentation with multiple references.

Findings

Outperforms state-of-the-art methods in stain normalization.

Achieves superior nuclei segmentation results.

Validated on a public dataset with improved accuracy.

Abstract

Variations in hematoxylin and eosin (H&E) stained images (due to clinical lab protocols, scanners, etc) directly impact the quality and accuracy of clinical diagnosis, and hence it is important to control for these variations for a reliable diagnosis. In this work, we present a new approach based on the multimarginal Wasserstein barycenter to normalize and augment H&E stained images given one or more references. Specifically, we provide a mathematically robust way of naturally incorporating additional images as intermediate references to drive stain normalization and augmentation simultaneously. The presented approach showed superior results quantitatively and qualitatively as compared to state-of-the-art methods for stain normalization. We further validated our stain normalization and augmentations in the nuclei segmentation task on a publicly available dataset, achieving state-of-the-art results against competing approaches.