headctools 0.21

A set of tools for preproccessing and performing brain segmentation and skull reconstruction on head CT images

This tool includes a bunch of algorithms for preprocessing CT images & PyTorch based models for performing brain segmentation or skull reconstruction on craniectomy images.

The implemented convolutional neural networks are based on the U-Net model, which was adapted to these particular problems.

Requirements

You should have Python 3.7+ installed in your system. If you are using the registrarion commands, you should manually install FSL

Package install

For installing the package using pip, run the following command:

pip install headctools

You can check some usage examples in the colab notebook and the readthedocs page.

Citing our work

If you have found this repo useful, please consider citing our work

@incollection{Matzkin2020,
  doi = {10.1007/978-3-030-59713-9_38},
  url = {https://doi.org/10.1007/978-3-030-59713-9_38},
  year = {2020},
  publisher = {Springer International Publishing},
  pages = {390--399},
  author = {Franco Matzkin and Virginia Newcombe and Susan Stevenson and Aneesh Khetani and Tom Newman and Richard Digby and Andrew Stevens and Ben Glocker and Enzo Ferrante},
  title = {Self-supervised Skull Reconstruction in Brain {CT} Images with Decompressive Craniectomy},
  booktitle = {Medical Image Computing and Computer Assisted Intervention {\textendash} {MICCAI} 2020}
}

Project logo icons made by Pixel perfect from www.flaticon.com