Repository files navigation

ByHaofu Liao (liaohaofu@gmail.com), Spring, 2019

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

@inproceedings{adn2019_miccai,  title={Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction},  author={Haofu Liao, Wei-An Lin, Jianbo Yuan, S. Kevin Zhou, Jiebo Luo},  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)},  year={2019}}@article{adn2019_tmi,   author={H. {Liao} and W. {Lin} and S. K. {Zhou} and J. {Luo}},   journal={IEEE Transactions on Medical Imaging},   title={ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction},   year={2019},  doi={10.1109/TMI.2019.2933425}}

This repository is tested under the following system settings:

• Ubuntu 16.04
• Python 3.7 (Anaconda/Miniconda reconmmended)
• Pytorch 1.0.0 or above
• CUDA 9.0 or above
• Matlab R2018b (with Image Processing Toolbox, Parallel Computing Toolbox and Statistics and Machine Learning Toolbox)

For most of the users, you may consider install ADN locally on your machine with the following steps.

• Clone this repository from Github

git clone https://github.com/liaohaofu/adn.git

• InstallPytorch andAnaconda/Miniconda
  • Anaconda/Miniconda installation is optional. If not installed, you may have to install some dependent python packages manually.
• Install Python dependencies.

pip install -r requirements.txt

For Docker users, we provide a pre-built docker image as well as a Dockerfile.

• Installdocker-ce andnvidia-docker.
• Pull the ADN docker image from Docker Hub. This will install ADN as well as its dependencies automatically.

docker pull liaohaofu/adn

• [Optional] If you want a customized version of ADN docker image, you may modify the docker file atdocker/Dockerfile and then build a docker image.

cd docker/docker build -t liaohaofu/adn .

• Run the ADN docker image.

docker run -it --runtime=nvidia liaohaofu/adn

Two publicly available datasets (DeepLesion and Spineweb) are supported. As a courtesy, we also support training/testing with natural images.

• Download theDeepLesion dataset. We use the first 9.zip files (Images_png_01.zip to Images_png_09.zip) in our experiments. You may use thebatch_download_zips.py provided by DeepLesion to batch download the.zip files at once.
• Extract the downloaded.zip files. All the extracted images will be under the folderpath_to_DeepLesion/Images_png/. Herepath_to_DeepLesion is the folder path where you extract the.zip files.
• Create a softlink to DeepLesion.Replacepath_to_DeepLesion/Images_png to the actual path in your system before running the following command.

ln -s path_to_DeepLesion/Images_png data/deep_lesion/raw

• Prepare DeepLesion dataset for ADN (MATLAB required). The configuration file for preparing DeepLesion dataset can be found atconfig/dataset.yaml.

>>prepare_deep_lesion

• Download theSpineweb dataset.
• Extract thespine-*.zip files (i.e.,spine-1.zip,spine-2.zip, etc.). All the extracted images will be under the folderpath_to_Spineweb/spine-*/. Herepath_to_Spineweb is the folder path where you extract thespine-*.zip files.
• Create a softlink to Spineweb.Replacepath_to_Spineweb/ to the actual path to in your system before running the following command.

mkdir data/spinewebln -s path_to_Spineweb/ data/spineweb/raw

• Prepare Spineweb dataset for ADN. The configuration file for preparing Spineweb dataset can be found atconfig/dataset.yaml.

python prepare_spineweb.py

• Our code assumes you have prepared your natural image dataset as following.

your_dataset├── test│   ├── artifact # a folder containing all the testing images with artifact│   └── no_artifact # a folder containing all the testing images without artifact└── train    ├── artifact # a folder containing all the training images with artifact    └── no_artifact # a folder containing all the training images without artifact

• Create a softlink to your natural image dataset

ln -s path_to_your_dataset data/nature_image

• Note that our model is not tuned for natural images (e.g., choices of loss functions, hyperparameters, etc.) and its effectiveness may vary depending on the problems and datasets.

• We provide a demo code to demonstrate the effectiveness of ADN. The input sample images are located atsamples/ and the outputs of the demo can be found atresults/. To run the demo,

python demo.py deep_lesionpython demo.py spineweb

• [Optional] By default, the demo code will download pretrained models from google drive automatically. If the downloading fails, you may download them from google drive manually.

  • Download pretrained models from Google Drive (DeepLesion |Spineweb) orBitbucket.
  • Move the downloaded models toruns/.

  mv path_to_DeepLesion_model runs/deep_lesion/deep_lesion_49.ptmv path_to_Spineweb_model runs/spineweb/spineweb_39.pt

• Configure the training and testing. We use a two-stage configuration for ADN, one for the default settings and the other for the run settings.

  • The default settings of ADN can be found atconfig/adn.yaml which is not subject to be changed. When users do not provide the values for a specific setting, the default setting in this file will be used.
  • The run settings can be found atruns/adn.yaml. This is where the users provide specific settings for ADN's training and testing. Any provided settings in this file will override the default settings during the experiments.By default, the settings for training and testing ADN with DeepLesion, Spineweb and natural image datasets are provided inruns/adn.yaml.

• Train ADN with DeepLesion, Spineweb datasets or a natural image dataset. The training results (model checkpoints, configs, losses, training visualizations, etc.) can be found underruns/run_name/ whererun_name can be eitherdeep_lesion,spineweb ornature_image

python train.py deep_lesionpython train.py spinewebpython train.py nature_image

• Test ADN with DeepLesion, Spineweb datasets or a natural image dataset. The testing results (evaluation metrics and testing visualizations, etc.) can be found underruns/run_name/ whererun_name can be eitherdeep_lesion,spineweb ornature_image.

python test.py deep_lesionpython test.py spinewebpython test.py nature_image

The authors would like to thank Dr. Yanbo Zhang (yanbozhang007@gmail.com) and Dr. Hengyong Yu (hengyong_yu@uml.edu) for providing the artifact synthesis code used in this repository.