SynthSeg

This functionality is only available in the development version of FreeSurfer.

Author: Benjamin Billot

E-mail: benjamin.billot.18 [at] ucl.ac.uk

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 SynthSeg in your analysis, please cite:

• SynthSeg: Domain Randomisation for Segmentation of Brain MRI Scans of any Contrast and Resolution. B Billot, DN Greve, O Puonti, A Thielscher, K Van Leemput, B Fischl, AV Dalca, JE Iglesias. Under revision.

For the robust mode, please cite also:

• Robust Segmentation of Brain MRI in the Wild with Hierarchical CNNs and no Retraining. B Billot, C Magdamo, SE Arnold, S Das, JE Iglesias. Under revision.

Contents

1. General Description
2. Installation
3. Usage
4. Frequently asked questions (FAQ)
5. List of segmented structures

1. General Description

This tool implements SynthSeg, the first convolutional neural network for segmentation of brain MRI scans of any contrast and resolution that works out of the box, without retraining or fine-tuning. SynthSeg relies on a single model, which we distribute here. This model is robust to:

• a wide array of subject populations: from young and healthy to aging and diseased subjects with strong atrophy,
• white matter lesions (see green arrows in image below),
• scans with or without preprocessing (bias field corruption, skull stripping, intensity normalisztion, registration to template).

The output segmentations are generated at high resolution (1mm isotropic), regardless of the resolution of the input scans. The code can run on the GPU (6s per scan) as well as the CPU (1 min per scan). The list of segmented structures can be found at the bottom of this page.

Important: While SynthSeg is quite robust, it sometimes falter on scans with low signal-to-noise ratio, or with low tissue contrast (see figure below). For this reason, we developed a new architecture for increased robustness, which can be selected with the --robust flag (details in Section 3 below). You can use this mode when SynthSeg gives results like those in the the third column of the figure below:

2. Installation

The first time you run this module, it will prompt you to install Tensorflow. Simply follow the instructions in the screen to install the CPU or GPU version.

If you have a compatible GPU, you can install the GPU version for faster processing, but this requires installing libraries (GPU driver, Cuda, CuDNN). These libraries are generally required for a GPU, and are not specific for this tool. In fact you may have already installed them. In this case you can directly use this tool without taking any further actions, as the code will automatically run on your GPU.

3. Usage

You can use SynthSeg with the following command:

mri_synthseg --i <input> --o <output> [--post <post> --resample <resample> --vol <vol> --cpu --threads <threads> --crop <crop> --fast --robust]

where:

• <input>: path to a scan to segment, or to a folder. This can also be the path to a text file, where each line is the path of an image to segment.

• <output>: is the path where the output segmentation will be saved. This must be a folder if --i designates is a folder, or a text file (where each line is a path of an output segmentation) if --i designates is a text file.

• --robust: (optional) use the new network for increased robustness (e.g., when analyzing clinical data with large space spacing).

• --fast: (optional) use this flag to disable some postprocessing operations for faster prediction (approximately twice as fast, but less accurate).

• <post>: (optional) path where 3D images with posterior probabilities will be saved. This must be the same type as --i (i.e., a folder or a text file).

• <resample>: (optional) path where 3D images resampled at 1mm resolution will be saved. This must be the same type as --i (i.e., a folder or a text file).

• <vol>: (optional) path to CSV files where ROI volumes will be saved. If --i designates an image or a folder, <vol> must be the path to a single CSV file where all volumes will be saved. Otherwise, <vol>' must be a text file, where each line is the path to a different csv file where the volumes of the corresponding subject will be saved.

• --cpu: (optional) use this flag to run code on the CPU rather than the GPU.

• <threads>: (optional) number of threads to be used by Tensorflow (default uses one core). Increase it to decrease the runtime when using the CPU version.

• <crop>: (optional) to crop the inputs to a given shape before segmentation. This must be divisible by 32. It can be given as a single (i.e., --crop 160) or several integers (i.e, --crop 160 128 192, ordered in RAS coordinates). This value defaults to 192, decreased it for faster analysis or to fit in your GPU. Increase if needed it for images with large field of view.

We note that --robust and --fast are only available on development versions from March 17th 2022 onwards.

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

4. Frequently asked questions (FAQ)

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.

5. List of segmented structures