Skip to content

SCAN-NRAD/BrainRegressorCNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

About Brain Regressor CNN

A deep learning-based method to estimate brain morphometry directly from T1-weighted MRI.

Abstract

The code is related to the following publication publication (bibtex):

Rebsamen, M., Suter, Y., Wiest, R., Reyes, M., & Rummel, C. (2020) Brain morphometry estimation: From hours to seconds using deep learning. Frontiers in Neurology, 11, 244. https://doi.org/10.3389/fneur.2020.00244 

Quick start in three steps:

Create virtual environment (optional)

conda create -n DL python=3.6 source activate DL pip install -r Python/requirements.txt

Import FreeSurfer data into h5 dataset

Assuming FS_RESULTS_DIR points to subjects directory with FreeSurfer results (GT) to import.

cd Python ./create_ds.sh FS_RESULTS_DIR

Train model

export PYTHONPATH=../miapy:../Python python main.py config.json 

About

Brain Morphometry Estimation: From Hours to Seconds Using Deep Learning

Topics

Resources

License

Stars

Watchers

Forks

Contributors