https://github.com/animesh/torchio

Tools for medical image processing in deep learning.

https://github.com/animesh/torchio

Repository

Tools for medical image processing in deep learning.

https://github.com/animesh/torchio/blob/master/

# [TorchIO](http://torchio.rtfd.io/)

> *Tools like TorchIO are a symptom of the maturation of medical AI research using deep learning techniques*.

Jack Clark, Policy Director
at [OpenAI](https://openai.com/) ([link](https://jack-clark.net/2020/03/17/)).

---

[![PyPI downloads](https://img.shields.io/pypi/dm/torchio.svg?label=PyPI%20downloads&logo=python&logoColor=white)](https://pypi.org/project/torchio/)
[![PyPI version](https://img.shields.io/pypi/v/torchio?label=PyPI%20version&logo=python&logoColor=white)](https://pypi.org/project/torchio/)
[![Google Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/112NTL8uJXzcMw4PQbUvMQN-WHlVwQS3i)
[![Documentation status](https://img.shields.io/readthedocs/torchio?label=Docs&logo=Read%20the%20Docs)](http://torchio.rtfd.io/?badge=latest)
[![Build status](https://img.shields.io/travis/fepegar/torchio/master.svg?label=Travis%20CI%20build&logo=travis)](https://travis-ci.org/fepegar/torchio)
[![Coverage status](https://codecov.io/gh/fepegar/torchio/branch/master/graphs/badge.svg)](https://codecov.io/github/fepegar/torchio)
[![Code quality](https://img.shields.io/scrutinizer/g/fepegar/torchio.svg?label=Code%20quality&logo=scrutinizer)](https://scrutinizer-ci.com/g/fepegar/torchio/?branch=master)
[![Code maintainability](https://api.codeclimate.com/v1/badges/518673e49a472dd5714d/maintainability)](https://codeclimate.com/github/fepegar/torchio/maintainability)
[![Slack](https://img.shields.io/badge/TorchIO-Join%20on%20Slack-blueviolet?style=flat&logo=slack)](https://join.slack.com/t/torchioworkspace/shared_invite/enQtOTY1NTgwNDI4NzA1LTEzMjIwZTczMGRmM2ZlMzBkZDg3YmQwY2E4OTIyYjFhZDVkZmIwOWZkNTQzYTFmYzdiNGEwZWQ4YjgwMTczZmE)
[![All Contributors](https://img.shields.io/badge/all_contributors-12-orange.svg)](#contributors-)

---

###  News: the paper is out! 

See the [Credits](#credits) section below for more information.

---


    

        
Original
        

            Random blur
        
    
    

        

        

            
                
            
        
    
    

        

            Random flip
        
        

            Random noise
        
    
    

        

            
                
            
        
        

            
                
            
        
    
    

        

            Random affine transformation
        
        

            Random elastic transformation
        
    
    

        

            
                
            
        
        

            
                
            
        
    
    

        

            Random bias field artifact
        
        

            Random motion artifact
        
    
    

        

            
                
            
        
        

            
                
            
        
    
    

        

            Random spike artifact
        
        

            Random ghosting artifact
        
    
    

        

            
                
            
        
        

            
                
            
        
    


---




    


([Queue](https://torchio.readthedocs.io/data/patch_training.html#queue)
for [patch-based training](https://torchio.readthedocs.io/data/patch_based.html))

---

TorchIO is a Python package containing a set of tools to efficiently
read, preprocess, sample, augment, and write 3D medical images in deep learning applications
written in [PyTorch](https://pytorch.org/),
including intensity and spatial transforms
for data augmentation and preprocessing.
Transforms include typical computer vision operations
such as random affine transformations and also domain-specific ones such as
simulation of intensity artifacts due to
[MRI magnetic field inhomogeneity](http://mriquestions.com/why-homogeneity.html)
or [k-space motion artifacts](http://proceedings.mlr.press/v102/shaw19a.html).

This package has been greatly inspired by NiftyNet,
[which is not actively maintained anymore](https://github.com/NifTK/NiftyNet/commit/935bf4334cd00fa9f9d50f6a95ddcbfdde4031e0).


## [Documentation](http://torchio.rtfd.io/)

The documentation is hosted on
[Read the Docs](http://torchio.rtfd.io/).

Please [create a new issue](https://github.com/fepegar/torchio/issues/new)
if you think something is missing.


## Credits

If you like this repository, please click on Star!

If you use this package for your research, please cite the paper:

[Prez-Garca et al., 2020, *TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning*](https://arxiv.org/abs/2003.04696).


BibTeX entry:

```bibtex
@misc{fern2020torchio,
    title={TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning},
    author={Fernando Prez-Garca and Rachel Sparks and Sebastien Ourselin},
    year={2020},
    eprint={2003.04696},
    archivePrefix={arXiv},
    primaryClass={eess.IV}
}
```

## Contributors 

Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)):





  

    

Fernando Prez-Garca
 
    

valabregue
  
    

GFabien

    

G.Reguig

    

Niels Schurink

    

Ibrahim Hadzic

    

ReubenDo

  
  

    

Julian Klug

    

David Vlgyes

    

Jean-Christophe Fillion-Robin

    

Suraj Pai

    

Ben Darwin

  






This project follows the [all-contributors](https://github.com/all-contributors/all-contributors) specification. Contributions of any kind welcome!

Owner

GitHub Events