interfaces.fsl.fix¶
Classifier¶
Classify ICA components using a specific training dataset (<thresh> is in the range 0-100, typically 5-20).
Inputs:
[Mandatory]
trained_wts_file: (an existing file name)
trained-weights file
argument: ``%s``, position: 2
thresh: (an integer (int or long))
Threshold for cleanup.
argument: ``%d``, position: -1
[Optional]
mel_ica: (an existing directory name)
Melodic output directory or directories
argument: ``%s``, position: 1
artifacts_list_file: (a file name)
Text file listing which ICs are artifacts; can be the output from
classification or can be created manually
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
environ: (a dictionary with keys which are a bytes or None or a value
of class 'str' and with values which are a bytes or None or a
value of class 'str', nipype default value: {})
Environment variables
Outputs:
artifacts_list_file: (a file name)
Text file listing which ICs are artifacts; can be the output from
classification or can be created manually
Cleaner¶
Extract features (for later training and/or classifying)
Inputs:
[Mandatory]
artifacts_list_file: (an existing file name)
Text file listing which ICs are artifacts; can be the output from
classification or can be created manually
argument: ``%s``, position: 1
[Optional]
cleanup_motion: (a boolean)
cleanup motion confounds, looks for design.fsf for highpass filter
cut-off
argument: ``-m``, position: 2
highpass: (a float, nipype default value: 100)
cleanup motion confounds
argument: ``-m -h %f``, position: 2
aggressive: (a boolean)
Apply aggressive (full variance) cleanup, instead of the default
less-aggressive (unique variance) cleanup.
argument: ``-A``, position: 3
confound_file: (a file name)
Include additional confound file.
argument: ``-x %s``, position: 4
confound_file_1: (a file name)
Include additional confound file.
argument: ``-x %s``, position: 5
confound_file_2: (a file name)
Include additional confound file.
argument: ``-x %s``, position: 6
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
environ: (a dictionary with keys which are a bytes or None or a value
of class 'str' and with values which are a bytes or None or a
value of class 'str', nipype default value: {})
Environment variables
Outputs:
cleaned_functional_file: (an existing file name)
Cleaned session data
FeatureExtractor¶
Extract features (for later training and/or classifying)
Inputs:
[Optional]
mel_ica: (an existing directory name)
Melodic output directory or directories
argument: ``%s``, position: -1
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
environ: (a dictionary with keys which are a bytes or None or a value
of class 'str' and with values which are a bytes or None or a
value of class 'str', nipype default value: {})
Environment variables
Outputs:
mel_ica: (an existing directory name)
Melodic output directory or directories
argument: ``%s``, position: -1
Training¶
Train the classifier based on your own FEAT/MELODIC output directory.
Inputs:
[Optional]
mel_icas: (a list of items which are an existing directory name)
Melodic output directories
argument: ``%s``, position: -1
trained_wts_filestem: (a unicode string)
trained-weights filestem, used for trained_wts_file and output
directories
argument: ``%s``, position: 1
loo: (a boolean)
full leave-one-out test with classifier training
argument: ``-l``, position: 2
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
environ: (a dictionary with keys which are a bytes or None or a value
of class 'str' and with values which are a bytes or None or a
value of class 'str', nipype default value: {})
Environment variables
Outputs:
trained_wts_file: (an existing file name)
Trained-weights file
TrainingSetCreator¶
Goes through set of provided melodic output directories, to find all the ones that have a hand_labels_noise.txt file in them.
This is outsourced as a separate class, so that the pipeline is rerun everytime a handlabeled file has been changed, or a new one created.
Inputs:
[Optional]
mel_icas_in: (a list of items which are an existing directory name)
Melodic output directories
argument: ``%s``, position: -1
Outputs:
mel_icas_out: (a list of items which are an existing directory name)
Hand labels for noise vs signal
argument: ``%s``, position: -1