This is the repository for the manuscript entitled: "Preliminary Evaluation of the Utility of Deep Generative Histopathology Image Translation at a Mid-Sized NCI Cancer Center" https://www.biorxiv.org/content/10.1101/2020.01.07.897801v2
Presented at BIOSTEC 2020 and awarded best paper in workshop Comp2Clinic: Biomedical Researchers & Clinicians Closing The Gap Between Translational Research And Healthcare Practice
In this repository, we have included a few sample images for the generation of nucleus and cytoplasmic masks from urine cytology images. We will continue to update the code base and dataset of this repository, feel free to make a GitHub Issue to request changes to the repository. Our recommendation for testing the translation would be to train the attached dataset using the training scripts featured in this repository: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix