RESSEG

Automatic segmentation of postoperative brain resection cavities from magnetic resonance images (MRI) using a convolutional neural network (CNN) trained with PyTorch 1.7.1.

Installation

It's recommended to use conda and install your desired PyTorch version before installing resseg. A 6-GB GPU is large enough to segment an image in the MNI space.

conda create -n resseg python=3.8 ipython -y && conda activate resseg  # recommended
pip install resseg

Usage

BITE

Example using an image from the Brain Images of Tumors for Evaluation database (BITE).

BITE=`resseg-download bite`
resseg $BITE -o bite_seg.nii.gz

EPISURG

Example using an image from the EPISURG dataset. Segmentation works best when images are in the MNI space, so resseg includes a tool for this purpose (requires ANTsPy).

pip install antspyx
EPISURG=`resseg-download episurg`
resseg-mni $EPISURG -t episurg_to_mni.tfm
resseg $EPISURG -o episurg_seg.nii.gz -t episurg_to_mni.tfm

Credit

If you use this library for your research, please cite our MICCAI 2020 paper:

F. Pérez-García, R. Rodionov, A. Alim-Marvasti, R. Sparks, J. S. Duncan and S. Ourselin. Simulation of Brain Resection for Cavity Segmentation Using Self-Supervised and Semi-Supervised Learning.

[Preprint on arXiv]

And the EPISURG dataset, which was used to train the model:

Pérez-García, Fernando; Rodionov, Roman; Alim-Marvasti, Ali; Sparks, Rachel; Duncan, John; Ourselin, Sebastien (2020): EPISURG: a dataset of postoperative magnetic resonance images (MRI) for quantitative analysis of resection neurosurgery for refractory epilepsy. University College London. Dataset. https://doi.org/10.5522/04/9996158.v1

See also

• resector was used to simulate brain resections during training
• TorchIO was also used extensively. Both resseg and resector require this library.