= Bayesian Segmentation with Histological Atlas "NextBrain" =
<
>
'''''Visit [[https://github-pages.ucl.ac.uk/NextBrain|the homepage of the NextBrain project]] for further information on this atlas. '''''
<
>
<
>
''Author: Juan Eugenio Iglesias''
<
>
''E-mail: jiglesiasgonzalez [at] mgh.harvard.edu''
<
>
<
>
''Rather than directly contacting the author, please post your questions on this module to the FreeSurfer mailing list at freesurfer [at] nmr.mgh.harvard.edu''
<
>
<
>
A preprint of the manuscript describing the atlas and segmentation method used in this module can be found [[https://www.biorxiv.org/content/10.1101/2024.02.05.579016v1|on bioRxiv.]]
<
>
=== Contents ===
1. General Description
2. Installation
3. Usage
4. Usage ('full' Bayesian version, '''not recommended''')
5. Frequently asked questions (FAQ)
<
>
=== 1. General Description ===
This module uses our new probabilistic atlas of the human brain to segment 333 distinct ROIs per hemisphere on in vivo scans. Segmentation relies on a Bayesian algorithm and is thus robust against changes in MRIi pulse sequence (e.g., T1-weighted, T2-weighted, FLAIR, etc). Sample slices of the atlas and the segmentation of the sample subject "bert" are shown below:
<
><
> {{attachment:examples.png||height="320"}} <
>
=== 2. Installation ===
The first time you run this module, it will prompt you to download the atlas. Follow the instructions on the screen to obtain the files.
<
>
=== 3. Usage (faster versions) ===
'''We just released these, so please bear with us (and definitely let us know!) if the code is buggy or crashes.'''
Our original implementation (still available for compatibility and reproducibility, see Section 4 below) used
a "proper" Bayesian inference algorithm that makes segmentation incredibly slow (tens of hours) unless a GPU
with pretty large RAM is available.
Since December 2024, we distribute two faster versions, where the atlas deformation is pre-computed
and then kept constant during the optimization, such that we only need to run the EM algorithm once for
the Gaussian parameters. Segmentation of 1mm isotropic scans takes about 20 minutes on a CPU with 8 cores
(and just a few minutes on a GPU). Segmentation of ex vivo scans with 0.25mm isotropic resolution takes
about 2 hours on the same CPU.
There are two such fast versions. One uses [[https://arxiv.org/abs/2404.01249|FireANTs (Jena et al)]]
to register to the target scan a synthetic cartoon derived from the atlas. This version actively tries to fit smaller structures and
subregions. The command line is:
{{{
mri_histo_atlas_segment_fireants INPUT_SCAN OUTPUT_DIRECTORY GPU THREADS [BF_MODE]
}}}
''INPUT_SCAN'': scan to process, in mgz or nii(.gz) format.
''OUTPUT_DIRECTORY'': directory where segmentations, volume files, etc, will be created (more on this below).
''GPU'': set to 1 to use the GPU (faster, but you many run out of memory!).
''THREADS'': number of CPU threads used by the code (set to -1 to use all available threads).
''BF_MODE'' (optional): bias field mode: dct (default), polynomial, or hybrid (try polynomial/hybrid if default doesn't do well)
For example, you can segment bert with a GPU and 8 CPU threads with:
{{{
mri_histo_atlas_segment $SUBJECTS_DIR/bert/mri/orig.mgz /path/to/output/bert_histo_atlas_segmentation/ 1 8
}}}
In the output directory, you will find:
''seg.[left/right].mgz'': NextBrain segmentation of the left and right hemisphere, respectively.
''vols.[left/right].csv'': CSV spreadsheet with the volumes of the different ROIs, computed from the posteriors (soft segmentations).
''seg.[left/right].rgb.mgz'': color version of the soft segmentation (use "Display as RBG map" option in Freeview).
''synthseg.mgz'': [[https://surfer.nmr.mgh.harvard.edu/fswiki/SynthSeg|SynthSeg]] segmentation of the input (used in preprocessing, to make cartoon, and to initialize GMM parameters).
''SynthSeg_volumes.csv'': coarse volumes [[https://surfer.nmr.mgh.harvard.edu/fswiki/SynthSeg|SynthSeg]] segmentation of the input (used in preprocessing, to make cartoon, and to initialize GMM parameters).
''atlas_reg.nii.gz'': [[https://surfer.nmr.mgh.harvard.edu/fswiki/EasyReg|EasyReg]] registration to MNI space, used in preprocessing.
''lut.txt'': FreeSurfer lookup table mapping label indices to brain anatomy. You need it when visualizing the NextBrain segmentations with Freeview.
''atlas_nonlinear_reg.[left/right].nii.gz'': registered cartoon images. Useful for debugging, if the segmentation fails.
The other fast version uses
[[https://arxiv.org/abs/2404.01249|SynthMorph (Hoffmann et al., Imaging Neuroscience, 2024)]],
a neural network for image registration. This version is even faster (because of SynthMorph and because
it runs both hemispheres in one go) and does OK for 1mm isotropic scans. However, SynthMorph
relies heavily on fitting the boundaries of whole structures and does not the map smaller regions
as well (e.g., thalamic nuclei). Therefore, we do not recommend it for images with resolution better
than 1mm isotropic (e.g., ex vivo scans).
{{{
mri_histo_atlas_segment_fast INPUT_SCAN OUTPUT_DIRECTORY GPU THREADS [BF_MODE]
}}}
The outputs are very similar to that of mri_histo_atlas_segment_fireants.
<
>
=== 4. Usage ('full' Bayesian version; not recommended as it is very slow) ===
We discourage users from using this version, which we only keep for compatibility and reproducibility.
To segment a brain MRI scan,
{{{
mri_histo_atlas_segment INPUT_SCAN OUTPUT_DIRECTORY ATLAS_MODE GPU THREADS [BF_MODE] [GMM_MODE]
}}}
where:
''INPUT_SCAN'': scan to process, in mgz or nii(.gz) format.
''OUTPUT_DIRECTORY'': directory where segmentations, volume files, etc, will be created (more on this below).
''ATLAS_MODE'' : full (atlas with all 333 labels) or simplified (simpler brainstem protocol used by fast versions; recommended)
''GPU'': set to 1 to use the GPU ('''we highly recommend using a GPU to run this module; without a GPU, running this module on a single scan can take tens of hours'''). The GPU requirements depend on the image but are about 24GB of memory.
''THREADS'': number of CPU threads used by the code (set to -1 to use all available threads).
''BF_MODE'' (optional): bias field mode: dct (default), polynomial, or hybrid.
''GMM_MODE'' (optional): gaussian mixture model (GMM) mode: must be 1mm unless you define your own (see FAQ below).
In the output directory, you will find:
''bf_corrected.mgz'': a bias field corrected version of the input scan.
''SynthSeg.mgz'': [[https://surfer.nmr.mgh.harvard.edu/fswiki/SynthSeg|SynthSeg]] segmentation of the input (which we use in preprocessing and to initialize Gaussian parameters).
''MNI_registration.mgz'': [[https://surfer.nmr.mgh.harvard.edu/fswiki/EasyReg|EasyReg]] registration to MNI space, use in preprocessing.
''seg_[left/right].mgz'': segmentation into 333 ROIs of the left and right hemisphere, respectively.
''vols_[left/right].csv'': CSV spreadsheet with the volumes of the different ROIs, computed from the posteriors (soft segmentations).
''lookup_table.txt'': FreeSurfer lookup table mapping label indices to brain anatomy. You need it when visualizing the segmentations with Freeview.
<
>
=== 5. Frequently asked questions (FAQ) ===
* '''The output of mri_histo_atlas_segment_fireants looks generally OK but is off in some areas; can I do something about it?'''
This is particularly important for high-resolution ex vivo brains. There is still hope! If you open the SynthSeg segmentation in the results directory and it is off in the offending area, you can manually edit it (which doesn't take long since it is always at 1mm resolution) and re-run mri_histo_atlas_segment_fireants with the same output directory.
* '''Do I really need a GPU for the 'full' Bayesian version?'''
Technically, no. In practice, yes. On a modern GPU, the code runs in an hour or less. On the CPU, it depends on the number of threads, but it can easily take a whole day or more.
* '''Do I need a GPU for the faster versions?'''
Certainly no! The code should run in less than half an hour on any semi-modern workstation, if you allocate enough threads (or about two hours for an ex vivo scan at 0.25mm resolution).
* '''What do the BF_MODE and GMM_MODE arguments do in the full Bayesian version?'''
You should not need to touch these, but the BF_MODE changes the set of basis functions for bias field correction and you could potentially try tinkering with it if the bias field correction fails (i.e., if bf_corrected.mgz has noticeable bias). GMM_MODE allows you to change the grouping of ROIs into tissue classes (advanced mode!).
The GMM model is crucial as it determines how different brain regions are grouped into tissue types for the purpose of
image intensity modeling. This is specified though a set of files that should be found under 'data' in the atlas directory:
''data/gmm_components_[GMM_MODE].yaml'': defines tissue classes and specificies the number of components of the corresponding GMM
''data/combined_aseg_labels_[GMM_MODE].yaml'' defines the labels that belong to each tissue class
''data/combined_atlas_labels_[GMM_MODE].yaml'' defines FreeSurfer ('aseg') labels that are used to initialize the parameters of each class.
Note that, in in dev versions newer than August 23 2024, these files are located under data_full and data_simplified (one directory per atlas / protocol).
We distribute a GMM_MODE named "1mm" that we have used in our experiments, and which is the default mode of the code. If you
want to use your own model, you will need to create another triplet of files of your own (use the 1mm version as template).
<
>