RestainNet: a self-supervised digital re-stainer for stain normalization

TL;DR

RestainNet is a self-supervised digital re-staining model for stain normalization in pathology images, improving color consistency and supporting various staining styles without paired data, leading to better analysis and classification results.

Contribution

The paper introduces RestainNet, a flexible self-supervised model for stain normalization that does not require paired training data and effectively re-stains grayscale images to match target stain styles.

Findings

Outperforms existing stain normalization methods in color accuracy

Achieves state-of-the-art results in pathology image segmentation and classification

Demonstrates high flexibility in learning different staining styles without extra effort.

Abstract

Color inconsistency is an inevitable challenge in computational pathology, which generally happens because of stain intensity variations or sections scanned by different scanners. It harms the pathological image analysis methods, especially the learning-based models. A series of approaches have been proposed for stain normalization. However, most of them are lack flexibility in practice. In this paper, we formulated stain normalization as a digital re-staining process and proposed a self-supervised learning model, which is called RestainNet. Our network is regarded as a digital restainer which learns how to re-stain an unstained (grayscale) image. Two digital stains, Hematoxylin (H) and Eosin (E) were extracted from the original image by Beer-Lambert's Law. We proposed a staining loss to maintain the correctness of stain intensity during the restaining process. Thanks to the self-supervised nature, paired training samples are no longer necessary, which demonstrates great flexibility in practical usage. Our RestainNet outperforms existing approaches and achieves state-of-the-art performance with regard to color correctness and structure preservation. We further conducted experiments on the segmentation and classification tasks and the proposed RestainNet achieved outstanding performance compared with SOTA methods. The self-supervised design allows the network to learn any staining style with no extra effort.