Newer
Older
.. image:: https://img.shields.io/badge/PyTorch-ee4c2c?logo=pytorch&logoColor=white
:alt: PyTorch
:target: https://pytorch.org/get-started/locally/
.. image:: https://img.shields.io/badge/-Albumentations-017F2F?style=flat&logo=github&labelColor=gray
:alt: Albumentations
:target: https://github.com/albumentations-team/albumentations
.. image:: https://img.shields.io/badge/-Pyscaffold-017F2F?style=flat&logo=github&labelColor=gray
:alt: Pyscaffold
A collection of data transformations for 3D-PLI images with available implementations for data augmentation in machine-learning pipelines.
.. image:: img/example.png
:alt: Alternative text for the image
:scale: 80%
https://arxiv.org/abs/2401.17207 Example 3D-PLI data augmentations using the provided transformations of 3D-PLI paramter maps. Original and transformed parameter maps are visualized as transmttance, retardation and fiber orientation map (FOM).
pip install git+https://jugit.fz-juelich.de/inm-1/bda/software/data_processing/pli-transforms.git
To access some data augmentations under ``pli_transforms.augmentations.pytorch`` a running installation of `PyTorch <https://pytorch.org/>`_ is required.
TBD
-----------
How to Cite
-----------
If you use this work in your research, please cite it as follows:
.. code-block:: latex
@article{oberstrass2024,
title = {Self-{{Supervised Representation Learning}} for {{Nerve Fiber Distribution Patterns}} in {{3D-PLI}}},
author = {Oberstrass, A. and others},
year = {2024},
journal = {arXiv preprint arXiv:2401.17207},
eprint = {2401.17207},
archiveprefix = {arxiv}
}