Base

Common interface for transforms.

class nitransforms.base.ImageGrid(image)[source]

Class to represent spaces of gridded data (images).

property affine: Access the indexes-to-RAS affine.

property header: Access the original reference’s header.

index(x)[source]: Get the image array’s indexes corresponding to coordinates.

property inverse: Access the RAS-to-indexes affine.

property ndcoords: List the physical coordinates of this gridded space samples.

property ndindex: List the indexes corresponding to the space grid.

ras(ijk)[source]: Get RAS+ coordinates from input indexes.

class nitransforms.base.SampledSpatialData(dataset)[source]

Represent sampled spatial data: regularly gridded (images) and surfaces.

property ndcoords: List the physical coordinates of this sample.

property ndim: Access the number of dimensions.

property npoints: Access the total number of voxels.

property shape: Access the space’s size of each dimension.

class nitransforms.base.SpatialReference[source]

Factory to create spatial references.

static factory(dataset)[source]: Create a reference for spatial transforms.

class nitransforms.base.TransformBase(reference=None)[source]

Abstract image class to represent transforms.

apply(spatialimage, reference=None, order=3, mode='constant', cval=0.0, prefilter=True, output_dtype=None)[source]

Apply a transformation to an image, resampling on the reference spatial object.

Parameters

spatialimage (spatialimage) – The image object containing the data to be resampled in reference space
reference (spatial object, optional) – The image, surface, or combination thereof containing the coordinates of samples that will be sampled.
order (int, optional) – The order of the spline interpolation, default is 3. The order has to be in the range 0-5.
mode ({'constant', 'reflect', 'nearest', 'mirror', 'wrap'}, optional) – Determines how the input image is extended when the resamplings overflows a border. Default is ‘constant’.
cval (float, optional) – Constant value for mode='constant'. Default is 0.0.
prefilter (bool, optional) – Determines if the image’s data array is prefiltered with a spline filter before interpolation. The default is True, which will create a temporary float64 array of filtered values if order > 1. If setting this to False, the output will be slightly blurred if order > 1, unless the input is prefiltered, i.e. it is the result of calling the spline filter on the original input.
output_dtype (dtype specifier, optional) – The dtype of the returned array or image, if specified. If None, the default behavior is to use the effective dtype of the input image. If slope and/or intercept are defined, the effective dtype is float64, otherwise it is equivalent to the input image’s get_data_dtype() (on-disk type). If reference is defined, then the return value is an image, with a data array of the effective dtype but with the on-disk dtype set to the input image’s on-disk dtype.

Returns

resampled – The data imaged after resampling to reference space.

Return type

spatialimage or ndarray

map(x, inverse=False)[source]

Apply \(y = f(x)\).

TransformBase implements the identity transform.

Parameters

x (N x D numpy.ndarray) – Input RAS+ coordinates (i.e., physical coordinates).
inverse (bool) – If True, apply the inverse transform \(x = f^{-1}(y)\).

Returns

y – Transformed (mapped) RAS+ coordinates (i.e., physical coordinates).

Return type

N x D numpy.ndarray

property ndim: Access the dimensions of the reference space.

property reference: Access a reference space where data will be resampled onto.

to_filename(filename, fmt='X5')[source]: Store the transform in BIDS-Transforms HDF5 file format (.x5).

exception nitransforms.base.TransformError[source]: A custom exception for transforms.