All configs are located configs folder
For training the modeld section, simply run python3 main.py dataset=cam16. You may specifiy the dataset using dataset=[tcga|breakhis|cam16|cam17].
For testing the model, simply run python3 main.py dataset=cam16 run=test. You may specifiy the dataset using dataset=[tcga|breakhis|cam16|cam17].
For classifier training, simply run python3 classifier.py dataset=cam17 model=classifier run.opt_run.n_epoch=40. You may specifiy the dataset using dataset=[tcga|breakhis|cam17].
We provide several pretrained trained models. We also provide our train-test splits.
| method | Dataset | url |
|---|---|---|
| CAGAN | TCGA-IDH | model |
| CAGAN | BreakHis | model |
| CAGAN | CAMELYON16 | model |
Please cite following paper if these codes help your research
@article{cong2022colour, title={Colour adaptive generative networks for stain normalisation of histopathology images}, author={Cong, Cong and Liu, Sidong and Di Ieva, Antonio and Pagnucco, Maurice and Berkovsky, Shlomo and Song, Yang}, journal={Medical Image Analysis}, pages={102580}, year={2022}, publisher={Elsevier} }