This is an attempt to do image segmentation using machine learning and FreeSurfer. The brain tumor segmentation (or BraTS) dataset was used. The model is based on a volume-to-volume Generative Adversarial Network (GAN). Part 2 will be about how to train a GAN model based on a paper by Cirillo et al.
Input
Predicted
Before we can even do any of the above, we need to use proper tooling to get the images ready. This installation of FreeSurfer was done on Ubuntu 22.04. The easiest way to go about it is to use the *.deb package.
1
sudo dpkg -i freesurfer_ubuntu22-7.4.1_amd64.deb
If there are missing depdencies, the following is needed:
1
sudo apt update && sudo apt -y upgrade
1
sudo apt update && sudo apt -y upgrade
1
sudo apt --fix-broken install
Test with this:
1
2
3
4
5
6
freeview -v $SUBJECTS_DIR/bert/mri/brainmask.mgz \
-v $SUBJECTS_DIR/bert/mri/aseg.mgz:colormap=lut:opacity=0.2 \
-f $SUBJECTS_DIR/bert/surf/lh.white:edgecolor=yellow \
-f $SUBJECTS_DIR/bert/surf/rh.white:edgecolor=yellow \
-f $SUBJECTS_DIR/bert/surf/lh.pial:annot=aparc:edgecolor=red \
-f $SUBJECTS_DIR/bert/surf/rh.pial:annot=aparc:edgecolor=red
Freesurfer