TorchIO

PyPI downloads PyPI version Google Colab notebook Documentation status Build status Coverage status Code quality Maintainability Slack

TorchIO is a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of 3D medical images in deep learning, following the design of PyTorch.

It includes multiple intensity and spatial transforms for data augmentation and preprocessing. These 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 or k-space motion artifacts.

The code is available on GitHub.

Credits

If you use this library for your research, please cite the paper: Pérez-García et al., 2020, TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning.

This package has been greatly inspired by NiftyNet.

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 Pérez-García and Rachel Sparks and Sebastien Ourselin},
   year={2020},
   eprint={2003.04696},
   archivePrefix={arXiv},
   primaryClass={eess.IV}
}