Skip to content

Latest commit

 

History

History
150 lines (97 loc) · 4.73 KB

README.adoc

File metadata and controls

150 lines (97 loc) · 4.73 KB
Raw

Adversarial Augmentation for Enhancing Classification of Mammography Images

Paper

  1. Department of Computer Science, ETH Zurich

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

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

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

In arXiv, 2019. (* joint contribution)

Correspondence to: Lukas Jendele and Ondrej Skopek

Citation

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

@article{AdvAugmentation2019,
  title={{Adversarial Augmentation for Enhancing Classification of Mammography Images}},
  author={Jendele, Lukas and Skopek, Ondrej and Becker, Anton S and Konukoglu, Ender},
  journal={arXiv preprint arXiv:1902.07762},
  year={2019}
}

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.

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

Requirements and versions:

  • Python 3.5

  • Git

  • Tensorflow 1.12.0

Important: When committing, 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 sourced into the virtual environment: source venv/bin/activate

Running the experiments

Image conversion

Put all data into the directories in data_in/. Supported are: 1_BCDR/, 2_INbreast/, 3_zrh/, cbis.

  1. ./local/convert_images_all.sh

  2. ./local/merge_images_all.sh

  3. ./local/split_images_all.sh

  4. ./local/treval_split.sh

GAN training

  1. ./local/run.sh. Wait 24 hours.

  2. ./local/infer.sh. Make sure to enter the correct checkpoint number here and below.

  3. ./local/to_png.sh. Make sure to change the paths in notebooks/inference_tfrecord_to_png.py.

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 ..

Directory structure

  • cluster/ — scripts for running the training/evaluation on the cluster

  • data_in/ — input data and associated scripts/configs

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

  • local/ — scripts for running the training/evaluation locally

  • 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

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

Licensed under the Apache License Version 2.0.

In: models/breast_cycle_gan

TensorPack

Licensed under the Apache License Version 2.0.

In: models/rcnn