segmentation_fastsurfer

Perform whole brain segmentation and surface reconstruction using deep-learning through FastSurfer.

Keywords : segmentation, fastsurfer, deepmi, cnn, deep-learning

Inputs

Format : tuple val(meta), path(anat), path(fs_license)

	Type	Description	Mandatory	Pattern
meta	map	Groovy Map containing sample information e.g. `[ id:'sample1', single_end:false ]`	True
anat	file	An anatomy (ex, .nii.gz).	True	`*.{nii,nii.gz,mgz}`
fs_license	file	The path to your FreeSurfer license. To get one, go to https://surfer.nmr.mgh.harvard.edu/registration.html. Optional. If you have already set your license as prescribed by Freesurfer (copied to a .license file in your $FREESURFER_HOME), this is not required.	True	`*.txt`

Format : tuple val(meta), path(*_fastsurfer)

	Type	Description	Mandatory	Pattern
meta	map	Groovy Map containing sample information e.g. `[ id:'sample1', single_end:false ]`	True
*_fastsurfer	directory	Fastsurfer segmentation outputs.	True	`*_fastsurfer`

Format : path(versions.yml)

	Type	Description	Mandatory	Pattern
versions.yml	file	File containing software versions	True	`versions.yml`

	Type	Description	Default
acq3T	boolean	Use this flag if the input T1w image was acquired at 3T.	False
cerebnet	boolean	Use this flag to enable cerebellum sub-segmentation with CerebNet.	False
hypvinn	boolean	Use this flag to enable hypothalamus sub-segmentation with HypVinn.	False
seg_only	boolean	Use this flag to only run the segmentation part of FastSurfer. If false, will also run the surface reconstruction part (recon-surf).	True

	Description	DOI
Fastsurfer	The FastSurfer pipeline consists of two main parts for segmentation and surface reconstruction.

Last updated : 2025-10-30