Skip to main content

Automatic Removal of Facial Features from MRI Images

Project description

DeepDefacer: Automatic Removal of Facial Features via Deep Learning.

-------->

DeepDefacer is a MRI anonymization tool written in Python, on top of Tensorflow and Keras, that was developed in partnership with the Poldrack Lab at Stanford University. It can be used to quickly deface 3D MRI images of any resolution and size on commercial CPUs and GPUs. Its goal is to provide the community with an easy to use and efficient tool for defacing medical images that require anonymization for compliance with federal privacy laws (e.g HIPAA).

Referencing and citing DeepDefacer

If you use DeepDefacer in your work, please refer to this citation for the current version:

@article{khazane2019state,
  title={DeepDefacer: Automatic Removal of Facial Features from MR Scans Via Deep Learning},
  author={Anish Khazane, Julien Hoachuck, Dr. Chris Gorgowelski, Dr. Russell Poldrack},
  journal={in proceedings, arXiv preprint},
  year={2019}
}

If you use any of the architecture code from the ARFF-CNN, please also use the citation above to comply with its authors' instructions on referencing.

Requirements

  • Any Python version between 2.7 and 3.6.
  • If you are using the GPU version of this library, please ensure that your GPU drivers are correctly installed and up to date. Please reference GPU Support for Tensorflow-GPU for further details on GPU setup.
  • Input MRI images must have 3D structure and be saved in either .nii or .nii.gz format.

Installation

Deepdefacer can be easily installed on any operating system via Pypi. There are two versions of this package; CPU or GPU support. Please enter one of the following commands into your terminal window to begin installation, depending on your system specifications and desired python version.

CPU Support

pip install deepdefacer[tf_cpu] / pip3 install deepdefacer[tf_cpu]

GPU Support

pip install deepdefacer[tf_gpu] / pip3 install deepdefacer[tf_gpu]

Note: If you are using a ZSH-type shell, you may need to wrap the package name in quotations in order to successfully initiate the Pip installation. (e.g pip install "deepdefacer[...]").

Usage and Documentation

Once installed, please enter deepdefacer --help into your terminal window to see a list of available options for this program. Defacing a 3D MRI image is extremely simple, and can be done with the following command:

deepdefacer --input_file <input filename>

The program will output a defaced image in the same directory as the input file, unless --defaced_output_path is specified.

You can also save the predicted mask for any MRI image by specifying the desired output filename and directory with the --mask_output_path option.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for deepdefacer, version 2.1.2
Filename, size File type Python version Upload date Hashes
Filename, size deepdefacer-2.1.2.tar.gz (5.3 MB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page