BreastGAN

BreastGAN, first experiment.

Paper

Injecting and removing malignant features in mammography with CycleGAN: Investigation of an automated adversarial attack using neural networks

Anton S. Becker 1,2), Lukas Jendele* 3), Ondrej Skopek* 3), Nicole Berger 1), Soleen Ghafoor 1,4), Magda Marcon 1), Ender Konukoglu 5)

1. Institute of Diagnostic and Interventional Radiology, University Hospital of Zurich; Zurich, Switzerland

2. Department of Health Sciences and Technology, ETH Zurich; Zurich, Switzerland

3. Department of Computer Science, ETH Zurich

4. Department of Radiology, Memorial Sloan Kettering Cancer Center, New York City, USA

5. Computer Vision Laboratory, Department of Information Technology and Electrical Engineering, ETH Zurich

In arXiv, 2018. (* joint contribution)

Correspondence to: Anton S. Becker, Institute of Diagnostic and Interventional Radiology, UniversitätsSpital Zürich, Raemistrasse 100, CH-8091 Zürich

E-Mail: [email protected]

Citation

If you use this code for your research, please cite our paper:

@article{BreastGAN2018,
  title={{Injecting and removing malignant features in mammography with CycleGAN: Investigation of an automated adversarial attack using neural networks}},
  author={Becker, Anton S and Jendele, Lukas and Skopek, Ondrej and Berger, Nicole and Ghafoor, Soleen and Marcon, Magda and Konukoglu, Ender},
  journal={arXiv preprint arXiv:1811.07767},
  year={2018}
}

Related Projects

CycleGAN: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Requirements and versions:

• Python 3.5

• Git

• Tensorflow 1.5

Important: When commiting, remember to be in the virtual environment, for hooks to work.

NOTE: All code in Jupyter Notebooks is purely experimental. Use at your own risk.

Setup

Make sure there is no venv/ directory in your repository. If there is, remove it. Run the following commands:

./setup/create_venv.sh
source venv/bin/activate

Important: For all commands here, we assume you are source into the virtual environment: source venv/bin/activate

Jupyter notebooks

NOTE: All code in Jupyter Notebooks is purely experimental. Use at your own risk.

Save notebooks in the notebooks/ directory. These can also be worked on locally using Jupyter. In the project root directory, you can run either:

• jupyter notebook,

• or jupyter lab.

Add the following cell to your notebook, ideally in a "section":

# noqa
import os
wd = %pwd
print('Current directory:', wd)
if wd.endswith('notebooks'):
    %cd ..

Docker / Custom runner

After you have build a Docker image using: make build-cpu or make build-gpu (or pulling one from the remote Docker hub), you can use the Docker wrapper:

• Jupyter on Docker: ./run_docker.sh PASSWORD jupyter.

  • To execute a specific notebook and print its output to stdout, use: ./run_docker.sh PASSWORD notebook NOTEBOOK_FILE

    • Do note that NOTEBOOK_FILE is a path relative to the repository root and must also be present in the image!

  • For both of these commands, PASSWORD is the password you want to set for the Jupyter web interface.

  • You can access it at http://localhost:8888/.

  • Same applies to ./run_docker.sh PASSWORD lab.

• Python models on Docker: ./run_docker.sh PASSWORD model MODEL_MODULE FLAG_FILE

  • For example: ./run_docker.sh PASSWORD model models.breast_cycle_gan_graph flags/cyclegan.json

  • Do note that MODEL_MODULE and FLAG_FILE are paths relative to the repository root and must also be present in the image!

  • This will automatically run Tensorboard on http://localhost:6006/

Without the wrapper:

docker run IMG jupyter # runs Jupyter
docker run IMG lab # runs JupyterLab
docker run IMG notebook notebooks/test.ipynb # Runs the notebook
docker run IMG model models.breast_cycle_gan_graph flags/cyclegan.json # Runs the MNIST GAN graph model with flags from the specified file

Using the run script without Docker

You can also use the above commands without using Docker, by invoking the run script directly:

./docker/run.sh jupyter # runs Jupyter
./docker/run.sh lab # runs JupyterLab
./docker/run.sh notebook notebooks/test.ipynb # Runs the notebook
./docker/run.sh model models.mnist_gan_graph flags/gan.json # Runs the MNIST GAN graph model with flags from the specified file

Directory structure

• data_in/ — input data and associated scripts/configs

• data_out/ — output data and logs + associated scripts/configs

• docker/ — setup and configs for running stuff inside and outside of Docker

• flags/ — command line flags, model parameters, etc.

• models/ — scripts defining the models + hyperparameters

• notebooks/ — data exploration and other rapid development notebooks

  • Models from here should eventually be promoted into models/

• resources/ — Python utilities

• setup/ — environment setup and verification scripts in Python/Bash

• venv/ — the (local) Python virtual environment

Formatting

Run: ./setup/clean.sh. A Git hook will tell you if any files are misformatted before committing.

Third Party code used in this project

ICNR

https://github.com/kostyaev/ICNR by Dmitry Kostyaev

Licensed under the MIT Licence.

In: models/utils/icnr.py

Tensor2Tensor

https://github.com/tensorflow/tensor2tensor by The Tensor2Tensor Authors.

Licensed under the Apache License Version 2.0.

In: models/breast_cycle_gan

TensorFlow, TensorFlow Models

https://github.com/tensorflow/tensorflow, https://github.com/tensorflow/models by The TensorFlow Authors.

Licensed under the Apache License Version 2.0.

In: models/breast_cycle_gan