Region-guided CycleGANs for Stain Transfer in Whole Slide Images

Joseph Boyd, Irène Villa, Marie-Christine Mathieu, Eric Deutsch, Nikos Paragios, Maria Vakalopoulou, Stergios Christodoulidis

MICCAI 2022

[arxiv] [code]

Abstract: In whole slide imaging, commonly used staining techniques based on hematoxylin and eosin (H&E) and immunohistochemistry (IHC) stains accentuate different aspects of the tissue landscape. In the case of detecting metastases, IHC provides a distinct readout that is readily interpretable by pathologists. IHC, however, is a more expensive option and not available at all medical centers. Virtually generating IHC images from H&E using deep neural networks becomes an attractive option. Deep generative models such as cycleGANs learn a semantically-consistent mapping between two image domains, while emulating the textural properties of each domain. They are therefore a suitable choice for stain transfer applications. However, they remain fully unsupervised, and possess no mechanism for injecting partial supervisory signals. In this paper, we propose an extension to cycleGANs in the form of a region of interest discriminator, yielding a type of conditional GAN. This allows the cycleGAN to learn from unpaired datasets where, in addition, there is a partial annotation of objects for which one wishes to enforce a consistency. We present a use case on whole slide images, where an IHC stain provides an experimentally-generated signal for metastatic cells. We show the superiority of our approach over prior art in stain transfer on histopathology tiles derived from two datasets.

@inproceedings{boyd2022region,
  title={Region-Guided CycleGANs for Stain Transfer in Whole Slide Images},
  author={Boyd, Joseph and Villa, Ir{\`e}ne and Mathieu, Marie-Christine and Deutsch, Eric and Paragios, Nikos and Vakalopoulou, Maria and Christodoulidis, Stergios},
  booktitle={Medical Image Computing and Computer Assisted Intervention--MICCAI 2022: 25th International Conference, Singapore, September 18--22, 2022, Proceedings, Part II},
  pages={356--365},
  year={2022},
  organization={Springer}
}