Studying Therapy Effects and Disease Outcomes in Silico using Artificial Counterfactual Tissue Samples

Counterfactual samples created by our generative method the CF-HistoGAN introduced in https://doi.org/10.48550/arXiv.2302.03120. This model was trained on and transformed data from 2 different datasets: the colorectal cancer (CRC) dataset by Schürch et al. https://doi.org/10.1016/j.cell. 2020.07.005 and the cutaneous T cell lymphoma (CTCL) by (Phillips et al https://doi.org/10.1038/s41467-021-26974-6.