DIRECT

DIRECT: Deep Image REConstruction Toolkit - Published in JOSS (2022)

https://github.com/nki-ai/direct

Keywords

Keywords from Contributors

Repository

Deep learning framework for MRI reconstruction

README.rst

.. raw:: html

   

     
     

     

   

.. raw:: html

   


   


   
   
   
   
   
   
   
   
   
   
   
   

   

   

       Installation •
       Quick Start •
       Documentation •
       Model Zoo 

   

   



``DIRECT`` is a Python, end-to-end pipeline for solving Inverse Problems emerging in Imaging Processing.
It is built with PyTorch and stores state-of-the-art Deep Learning imaging inverse problem solvers such as denoising, dealiasing and reconstruction.
By defining a base forward linear or non-linear operator, ``DIRECT`` can be used for training models for recovering images such as MRIs from partially observed or noisy input data.
``DIRECT`` stores inverse problem solvers such as the vSHARP, Learned Primal Dual algorithm, Recurrent Inference Machine and Recurrent Variational Network, which were part of the winning solutions in Facebook & NYUs FastMRI challenge in 2019, the Calgary-Campinas MRI reconstruction challenge at MIDL 2020 and the CMRxRecon challenge 2023.
For a full list of the baselines currently implemented in DIRECT see `here <#baselines-and-trained-models>`_.

.. raw:: html

   

     
     
   




Projects
--------
In the `projects `_ folder baseline model configurations are provided for each project.

Baselines and trained models
----------------------------

We provide a set of baseline results and trained models in the `DIRECT Model Zoo `_. Baselines and trained models include the `vSHARP `_, `Recurrent Variational Network (RecurrentVarNet) `_, the `Recurrent Inference Machine (RIM) `_, the `End-to-end Variational Network (VarNet) `_, the `Learned Primal Dual Network (LDPNet) `_, the `X-Primal Dual Network (XPDNet) `_, the `KIKI-Net `_, the `U-Net `_, the `Joint-ICNet `_, and the `AIRS Medical fastmri model (MultiDomainNet) `_.

License and usage
-----------------

DIRECT is not intended for clinical use. DIRECT is released under the `Apache 2.0 License `_.


Citing DIRECT
-------------

If you use DIRECT in your own research, or want to refer to baseline results published in the `DIRECT Model Zoo `_\ , please use the following BiBTeX entry:


.. code-block:: text

    @article{DIRECTTOOLKIT,
        doi = {10.21105/joss.04278},
        url = {https://doi.org/10.21105/joss.04278},
        year = {2022},
        publisher = {The Open Journal},
        volume = {7},
        number = {73},
        pages = {4278},
        author = {George Yiasemis and Nikita Moriakov and Dimitrios Karkalousos and Matthan Caan and Jonas Teuwen},
        title = {DIRECT: Deep Image REConstruction Toolkit},
        journal = {Journal of Open Source Software}
    }

Owner

JOSS Publication

DIRECT: Deep Image REConstruction Toolkit

Published

May 30, 2022

DOI

10.21105/joss.04278

Volume 7, Issue 73, Page 4278

Authors

George Yiasemis
Netherlands Cancer Institute, University of Amsterdam

Nikita Moriakov
Netherlands Cancer Institute, Radboud University Medical Center

Dimitrios Karkalousos
Amsterdam UMC, Biomedical Engineering and Physics

Matthan Caan
Amsterdam UMC, Biomedical Engineering and Physics

Jonas Teuwen
Netherlands Cancer Institute, University of Amsterdam, Radboud University Medical Center

Editor

Øystein Sørensen

Tags

Pytorch Deep Learning Inverse Problem Solver Image Processing Deep MRI reconstruction Accelerated MRI

View PDF Review Thread Software Archive

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - family-names: Yiasemis
    given-names: George
    email: g.yiasemis@nki.nl
    orcid:  https://orcid.org/0000-0002-1348-8987
  - family-names: Moriakov
    given-names: Nikita
    email: n.moriakov@nki.nl
    orcid:  https://orcid.org/0000-0002-7127-1006
  - family-names: Karkalousos
    given-names: Dimitrios
    email: d.karkalousos@amsterdamumc.nl
    orcid: https://orcid.org/0000-0001-5983-0322
  - family-names: Caan
    given-names: Matthan
    email: m.w.a.caan@amsterdamumc.nl
    orcid: https://orcid.org/0000-0002-5162-8880
  - family-names: Teuwen
    given-names: Jonas
    email: j.teuwen@nki.nl
    orcid:  https://orcid.org/0000-0002-1825-1428
title: "DIRECT: Deep Image REConstruction Toolkit"
doi: 10.21105/joss.04278
url: https://doi.org/10.21105/joss.04278
journal: Journal of Open Source Software
publisher: he Open Journal
volume: "7"
number: "73"
pages: "4278"
year: "2022"

GitHub Events

Committers

Last synced: 5 months ago

Issues and Pull Requests

Last synced: 4 months ago