SynthSeg

This functionality is available in FreeSurfer development versions newer than December 2023

Author: Pablo Laso

E-mail: plaso [at] kth.se

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

If you use WMH-SynthSeg in your analysis, please cite:

Quantifying white matter hyperintensity and brain volumes in heterogeneous clinical and low-field portable MRI. Laso P, Cerri S, Sorby-Adams A, Guo J, Matteen F, Goebl P, Wu J, Li H, Young SI, Billot B, Puonti O, Rosen MS, Kirsch J, Strisciuglio N, Wolterink JM, Eshaghi A, Barkhof F, Kimberly WT, and Iglesias JE. Under review.

General Description
Usage
Frequently asked questions (FAQ)

1. General Description

This tool is a version of SynthSeg that, in addition to segmeting anatomy, also provides segmentations for white matter hyperintensity (WMH) - or hypointensities, in T1-like modalities. As the original SynthSeg, WMH-SynthSeg works out of the box and can handle brain MRI scans of any contrast and resolution. Unlike SynthSeg, WMH-SynthSeg is designed to adapt to low-field MRI scans with low resolution and signal-to-noise ratio (which makes it potentially a bit less accurate on high-resolution data acquired at high field).

As for SynthSeg, the output segmentations are returned at high resolution (1mm isotropic), regardless of the resolution of the input scans. The code can run on the GPU (3s per scan) as well as the CPU (1 minute per scan). The list of segmented structures is the same as for SynthSeg 2.0 (plus the WMH label, which is FreeSurfer label 77). Below are some examples of segmentations given by SynthSeg.

2. Usage

You can use WMH-SynthSeg with the following command:

mri_WMHsynthseg --i <input> --o <output> --csv_vols <CSV file> --device <device>  --threads <threads>

where:

<input>: path to a scan to segment, or to a folder.
<output>: path where the output segmentations will be saved. This must be the same type as --i (i.e., the path to a file or a folder).
<CSV file>: (optional) path to a CSV file where volumes for all segmented regions will be saved.
<threads>: (optional) number of threads to be used by PyTorch in CPU mode (see blow). Default is 1. Set it to -1 to use all possible cores.
<device>: (optional) device used by PyTorch. Default is 'cpu'. Set it to 'cuda' to use the GPU, if available. If there are multiple GPUs available, use 'cuda:0', 'cuda:1', etc to index them.

Important: If you wish to process several scans, we highly recommend that you put them in a single folder, rather than calling mri_WMHsynthseg individually on each scan. This will save the time required to set up the software for each scan.

3. Frequently asked questions (FAQ)

Does running this tool require preprocessing of the input scans?

No! Because we applied aggressive augmentation during training (see paper), this tool is able to segment both processed and unprocessed data. So there is no need to apply bias field correction, skull stripping, or intensity normalisation.

The sum of the number of voxels of a given structure multiplied by the volume of a voxel is not equal to the volume reported in the output volume file.

This is because the volumes are computed upon a soft segmentation, rather than the discrete segmentation. The same happens with the main recon-all stream: if you compute volumes by counting voxels in aseg.mgz, you don't get the values reported in aseg.stats.

What formats are supported ?

This tool can be run on Nifti (.nii/.nii.gz) and FreeSurfer (.mgz) scans.

How can I increase the speed of the CPU version without using a GPU?

The first solution is to use the --fast flag, which will half the processing time if you're not using the "--robust" flag (gains in speed are much smaller if you are). Next, if you have a multi-core machine, you can increase the number of threads with the --threads flag (up to the number of cores). Additionally you can also try to decrease the cropping value, but this will also decrease the field of view of the image.

Why are the inputs automatically resampled to 1mm resolution ?

Simply because, in order to output segmentations at 1mm resolution, the network needs the input images to be at this particular resolution! We actually do not resample images with resolution in the range [0.95, 1.05], which is close enough. We highlight that the resampling is performed internally to avoid the dependence on any external tool.

Why aren't the segmentations perfectly aligned with their corresponding images?

This may happens with viewers other than FreeSurfer's Freeview, if they do not handle headers properly. We recommend using Freeview but, if you want to use another viewer, you may have to use the --resample flag to save the resampled images, which any viewer will correctly align with the segmentations.

6. Matlab implementation

Matlab added the non-robust version of SynthSeg to their Medical Imaging Toolbox in version R2022b. They have a fully documented example on how to use it here.

Alternatively, you can download our Matlab script, which you can call with a single line of code: Download. Uncompress the code and type: "help SynthSeg" for instructions.

7. List of segmented structures

Please note that the label values follow the FreeSurfer classification. We emphasise that the structures are given in the same order as they appear in the posteriors, i.e. the first map of the posteriors corresponds to the background, then the second map is associated to the left cerebral white matter, etc.