Sequence Adaptive Multimodal SEGmentation (SAMSEG) is a tool to robustly segment dozens of brain structures from head MRI scans without preprocessing. The characteristic property of SAMSEG is that it accepts multi-contrast MRI data without prior assumptions on the specific type of scanner or pulse sequences used.
license:
url: https://gitlab.com/flywheel-io/flywheel-apps/
cite:
Fast and sequence-adaptive whole-brain segmentation using parametric Bayesian modeling. O. Puonti, J.E. Iglesias, K. Van Leemput. NeuroImage, 143, 235-249, 2016.
Category: analysis
Gear Level:
- Project
- Subject
- Session
- Acquisition
- Analysis
- api-key
- Name: api-key
- Type: object
- Optional: true
- Classification: api-key
- Description: Flywheel API key.
-
debug
- Name: debug
- Type: boolean
- Description: Log debug messages
- Default: false
-
input
- Base: file
- Description: input file (usually isotropic reconstruction)
- Optional: false
-
output
- Base: file
- Description: segmentated file
- Optional: false
-
parcelation
- Base: file
- Description: parcelation file
- Optional: true
-
vol
- Base: file
- Description: volume estimation file (csv)
- Optional: true
-
QC
- Base: file
- Description: QC file (csv)
- Optional: true
No metadata currently created by this gear
- Three dimensional structural image
This gear runs on BIDS-organized data. To have your data BIDS-ified, it is recommended that you run, in the following order:
- dcm2niix
- Level: Any
- file-metadata-importer
- Level: Any
- file-classifier
- Level: Any
This section provides a more detailed description of the gear, including not just WHAT it does, but HOW it works in flywheel
This gear is run at either the Subject
or the Session
level. It downloads the data
for that subject/session into the /flwyhweel/v0/work/bids
folder and then runs the
synthseg
pipeline on it.
After the pipeline is run, the output folder is zipped and saved into the analysis container.
This section contains specifications on any input files that the gear may need
A picture and description of the workflow
graph LR;
A[T1w]:::input --> FW;
FW[FW] --> FMI;
FMI((file-metadata-importer)):::gear --> FC;
FC((file-classifier)):::gear --> D2N;
D2N((dcm2niix)):::gear --> CB;
CB((curate-bids)):::gear --> CISO;
CISO((ciso)):::gear --> SS;
SS((synthseg)):::gear --> ANA;
ANA[Analysis]:::container;
classDef container fill:#57d,color:#fff
classDef input fill:#7a9,color:#fff
classDef gear fill:#659,color:#fff
Description of workflow
- Upload data to container
- Prepare data by running the following gears:
- file metadata importer
- file classifier
- dcm2niix
- MRIQC (optional)
- curate bids
- Select either a subject or a session.
- Run the ciso gear (Hyperfine triplane aquisitions)
- Run the synthseg gear
- Gear places output in Analysis
[For more information about how to get started contributing to that gear, checkout CONTRIBUTING.md.]