NIPY logo
Home · Quickstart · Documentation · Citation · NiPy
Loading

Table Of Contents

Versions

ReleaseDevel
0.6.0pre-0.7
Download Github

Links

interfaces.nipy.utils

Similarity

Code: file:///build/buildd/nipype-0.6.0/nipype/interfaces/nipy/utils.py#L42

Calculates similarity between two 3D volumes. Both volumes have to be in the same coordinate system, same space within that coordinate system and with the same voxel dimensions.

Example

>>> from nipype.interfaces.nipy.utils import Similarity
>>> similarity = Similarity()
>>> similarity.inputs.volume1 = 'rc1s1.nii'
>>> similarity.inputs.volume2 = 'rc1s2.nii'
>>> similarity.inputs.metric = 'cr'
>>> res = similarity.run() 

Inputs:

[Mandatory]
mask1: (an existing file name)
        3D volume
mask2: (an existing file name)
        3D volume
volume1: (an existing file name)
        3D volume
volume2: (an existing file name)
        3D volume

[Optional]
ignore_exception: (a boolean, nipype default value: False)
        Print an error message instead of throwing an exception in case the interface fails to
        run
metric
        str or callable
        Cost-function for assessing image similarity. If a string,
        one of 'cc': correlation coefficient, 'cr': correlation
        ratio, 'crl1': L1-norm based correlation ratio, 'mi': mutual
        information, 'nmi': normalized mutual information, 'slr':
        supervised log-likelihood ratio. If a callable, it should
        take a two-dimensional array representing the image joint
        histogram as an input and return a float.

Outputs:

similarity: (a float)
        Similarity between volume 1 and 2