Towards Histopathological Stain Invariance by Unsupervised Domain Augmentation using Generative Adversarial Networks

TL;DR

This paper introduces an unsupervised adversarial image translation method to train stain-invariant neural networks for digital pathology, improving segmentation across multiple staining protocols without extensive labeled data.

Contribution

It presents a novel unsupervised domain augmentation approach using GANs to achieve stain invariance in deep learning models for pathology.

Findings

Significant improvement in glomeruli segmentation across seven staining modalities.

Demonstrated stain invariance in learned representations.

Effective training on one stain and application to others.

Abstract

The application of supervised deep learning methods in digital pathology is limited due to their sensitivity to domain shift. Digital Pathology is an area prone to high variability due to many sources, including the common practice of evaluating several consecutive tissue sections stained with different staining protocols. Obtaining labels for each stain is very expensive and time consuming as it requires a high level of domain knowledge. In this article, we propose an unsupervised augmentation approach based on adversarial image-to-image translation, which facilitates the training of stain invariant supervised convolutional neural networks. By training the network on one commonly used staining modality and applying it to images that include corresponding, but differently stained, tissue structures, the presented method demonstrates significant improvements over other approaches. These benefits are illustrated in the problem of glomeruli segmentation in seven different staining modalities (PAS, Jones H&E, CD68, Sirius Red, CD34, H&E and CD3) and analysis of the learned representations demonstrate their stain invariance.