CEREBRUM-7T

Visit the Project page.

Description

Implementation of the paper "CEREBRUM 7T: Fast and Fully-volumetric Brain Segmentation of 7 Tesla MR Volumes" (link).

In the paper, we tackle the problem of automatic 7T MRI segmentation. The generated model is able to produce accurate multi-structure segmentation masks on six different classes, in only few seconds. Classes are: gray matter (GM), white matter (WM), cerebrospinal fluid (CSF), ventricles, cerebellum, brainstem, and basal ganglia.

Usage

Visit the relative page to learn how to use CEREBRUM-7T from source code, docker, or singularity.

Data

Visit the relative page for all the information needed about the data.

Authors

Michele Svanera & Dennis Bontempi

Citation

If you find this code useful in your research, please consider citing our paper:

@article{SvaneraHBM21Cerebrum7T,
	author = {Svanera, Michele and Benini, Sergio and Bontempi, Dennis and Muckli, Lars},
	title = {CEREBRUM-7T: Fast and Fully Volumetric Brain Segmentation of 7 Tesla MR Volumes},
	journal = {Human Brain Mapping},
	volume = {n/a},
	number = {n/a},
	pages = {},
	keywords = {3D image analysis, brain MRI segmentation, convolutional neural networks, weakly supervised learning},
	doi = {https://doi.org/10.1002/hbm.25636},
	url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/hbm.25636},
	eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1002/hbm.25636},
}