HistoStarGAN: A Unified Approach to Stain Normalisation, Stain Transfer and Stain Invariant Segmentation in Renal Histopathology

TL;DR

HistoStarGAN is a unified deep learning framework that enables stain transfer, normalization, and invariant segmentation in renal histopathology, demonstrating generalization to unseen stainings and generating synthetic data for improved model training.

Contribution

The paper introduces HistoStarGAN, the first unified model capable of multiple stain transfer and segmentation tasks with generalization to unseen stainings in histopathology.

Findings

Effective stain transfer and normalization across multiple stainings.

Accurate stain invariant segmentation on unseen stainings.

Generation of a synthetic annotated dataset for renal pathology.

Abstract

Virtual stain transfer is a promising area of research in Computational Pathology, which has a great potential to alleviate important limitations when applying deeplearningbased solutions such as lack of annotations and sensitivity to a domain shift. However, in the literature, the majority of virtual staining approaches are trained for a specific staining or stain combination, and their extension to unseen stainings requires the acquisition of additional data and training. In this paper, we propose HistoStarGAN, a unified framework that performs stain transfer between multiple stainings, stain normalisation and stain invariant segmentation, all in one inference of the model. We demonstrate the generalisation abilities of the proposed solution to perform diverse stain transfer and accurate stain invariant segmentation over numerous unseen stainings, which is the first such demonstration in the field. Moreover, the pre-trained HistoStar-GAN model can serve as a synthetic data generator, which paves the way for the use of fully annotated synthetic image data to improve the training of deep learning-based algorithms. To illustrate the capabilities of our approach, as well as the potential risks in the microscopy domain, inspired by applications in natural images, we generated KidneyArtPathology, a fully annotated artificial image dataset for renal pathology.