Synthetic whole-slide image tile generation with gene expression profile-infused deep generative models
Metadata
Show full item recordEditorial
Elsevier
Date
2023-08-28Referencia bibliográfica
Carrillo-Perez et al., 2023, Cell Reports Methods 3, 100534 August 28, 2023 ª 2023 The Author(s). [https://doi.org/10.1016/j.crmeth.2023.100534]
Sponsorship
Grants PID2021- 128317OB-I00; MCIN/AEI/10.13039/501100011033; Project P20-00163, funded by Consejerı´a de Universidad, Investigacio´ n e Innovacio; ERDF A way of making EuropeAbstract
In this work, we propose an approach to generate whole-slide image (WSI) tiles by using deep generative
models infused with matched gene expression profiles. First, we train a variational autoencoder (VAE) that
learns a latent, lower-dimensional representation of multi-tissue gene expression profiles. Then, we use
this representation to infuse generative adversarial networks (GANs) that generate lung and brain cortex
tissue tiles, resulting in a new model that we call RNA-GAN. Tiles generated by RNA-GAN were preferred
by expert pathologists compared with tiles generated using traditional GANs, and in addition, RNA-GAN
needs fewer training epochs to generate high-quality tiles. Finally, RNA-GAN was able to generalize to
gene expression profiles outside of the training set, showing imputation capabilities. A web-based quiz is
available for users to play a game distinguishing real and synthetic tiles: https://rna-gan.stanford.edu/,
and the code for RNA-GAN is available here: https://github.com/gevaertlab/RNA-GAN.