# Self supervised contrastive learning for digital histopathology

We release larger pretrained models (resnet34, resnet50, and resnet101) trained for the original work, which can be found in the **.ckpt** files in the following link:

https://github.com/martellab-sri/self-supervised-histopathology/releases/tag/largermodels

To view the training code and access the resnet18 pretrained weights, the original codebase can be found [here](https://github.com/ozanciga/self-supervised-histopathology). 

# Citation
Please use below to cite this paper if you find this repository useful or if you use pretrained models shared here in your research.

```
@article{SelfSupervisedHisto,
title = {Self supervised contrastive learning for digital histopathology},
journal = {Machine Learning with Applications},
volume = {7},
pages = {100198},
year = {2022},
issn = {2666-8270},
doi = {https://doi.org/10.1016/j.mlwa.2021.100198},
url = {https://www.sciencedirect.com/science/article/pii/S2666827021000992},
author = {Ozan Ciga and Tony Xu and Anne Louise Martel}
}
```