ants.core.ants_transform

Functions

apply_ants_transform(transform, data[, ...])	Apply ANTsTransform to data
apply_ants_transform_to_image(transform, ...)	Apply transform to an image
apply_ants_transform_to_point(transform, point)	Apply transform to a point
apply_ants_transform_to_vector(transform, vector)	Apply transform to a vector
compose_ants_transforms(transform_list)	Compose multiple ANTsTransform's together
get_ants_transform_fixed_parameters(transform)	Get fixed parameters of an ANTsTransform
get_ants_transform_parameters(transform)	Get parameters of an ANTsTransform
invert_ants_transform(transform)	Invert ANTsTransform
set_ants_transform_fixed_parameters(...)	Set fixed parameters of an ANTsTransform
set_ants_transform_parameters(transform, ...)	Set parameters of an ANTsTransform
transform_index_to_physical_point(image, index)	Get spatial point from index of an image.
transform_physical_point_to_index(image, point)	Get index from spatial point of an image.

Classes

ANTsTransform([precision, dimension, ...])

class ANTsTransform(precision='float', dimension=3, transform_type='AffineTransform', pointer=None)

Bases: object

apply(data, data_type='point', reference=None, **kwargs)

Apply transform to data

apply_to_image(image, reference=None, interpolation='linear')

Apply transform to an image

Parameters:

• image (ants.core.ANTsImage) – image to which the transform will be applied

• reference (ants.core.ANTsImage) – target space for transforming image

• interpolation (str) –

  type of interpolation to use. Options are:

  linear nearestneighbor multilabel gaussian bspline cosinewindowedsinc welchwindowedsinc hammingwindoweddinc lanczoswindowedsinc genericlabel

Returns:

list

Return type:

transformed vector

apply_to_point(point)

Apply transform to a point

Parameters:

point (list/tuple) – point to which the transform will be applied

Returns:

list

Return type:

transformed point

Example

>>> import ants
>>> tx = ants.new_ants_transform()
>>> params = tx.parameters
>>> tx.set_parameters(params*2)
>>> pt2 = tx.apply_to_point((1,2,3)) # should be (2,4,6)

apply_to_vector(vector)

Apply transform to a vector

Parameters:

vector (list/tuple) – vector to which the transform will be applied

Returns:

list

Return type:

transformed vector

property fixed_parameters

Get parameters of transform

invert()

Invert the transform

property parameters

Get parameters of transform

set_fixed_parameters(parameters)

Set parameters of transform

set_parameters(parameters)

Set parameters of transform

apply_ants_transform(transform, data, data_type='point', reference=None, **kwargs)

Apply ANTsTransform to data

ANTsR function: applyAntsrTransform

Parameters:

• transform (ANTsTransform) – transform to apply to image

• data (ndarray/list/tuple) – data to which transform will be applied

• data_type (str) –

  type of data Options :

  ’point’ ‘vector’ ‘image’

• reference (ants.core.ANTsImage) – target space for transforming image

• kwargs (kwargs) – additional options passed to apply_ants_transform_to_image

Returns:

• ANTsImage if data_type == 'image'

• OR

• tuple if data_type == 'point' or data_type == 'vector'

apply_ants_transform_to_image(transform, image, reference, interpolation='linear')

Apply transform to an image

ANTsR function: applyAntsrTransformToImage

Parameters:

• image (ants.core.ANTsImage) – image to which the transform will be applied

• reference (ants.core.ANTsImage) – reference image

• interpolation (str) – type of interpolation to use. Options are: linear nearestneighbor multilabel gaussian bspline cosinewindowedsinc welchwindowedsinc hammingwindoweddinc lanczoswindowedsinc genericlabel

Returns:

list

Return type:

transformed vector

Example

>>> import ants
>>> img = ants.image_read(ants.get_ants_data("r16")).clone('float')
>>> tx = ants.new_ants_transform(dimension=2)
>>> tx.set_parameters((0.9,0,0,1.1,10,11))
>>> img2 = tx.apply_to_image(img, img)

apply_ants_transform_to_point(transform, point)

Apply transform to a point

ANTsR function: applyAntsrTransformToPoint

Parameters:

point (list/tuple) – point to which the transform will be applied

Returns:

tuple

Return type:

transformed point

Example

>>> import ants
>>> tx = ants.new_ants_transform()
>>> params = tx.parameters
>>> tx.set_parameters(params*2)
>>> pt2 = tx.apply_to_point((1,2,3)) # should be (2,4,6)

apply_ants_transform_to_vector(transform, vector)

Apply transform to a vector

ANTsR function: applyAntsrTransformToVector

Parameters:

vector (list/tuple) – vector to which the transform will be applied

Returns:

tuple

Return type:

transformed vector

compose_ants_transforms(transform_list)

Compose multiple ANTsTransform’s together

ANTsR function: composeAntsrTransforms

Parameters:

transform_list (list/tuple of ANTsTransform object) – list of transforms to compose together

Returns:

one transform that contains all given transforms

Return type:

ANTsTransform

Example

>>> import ants
>>> img = ants.image_read(ants.get_ants_data("r16")).clone('float')
>>> tx = ants.new_ants_transform(dimension=2)
>>> tx.set_parameters((0.9,0,0,1.1,10,11))
>>> inv_tx = tx.invert()
>>> single_tx = ants.compose_ants_transforms([tx, inv_tx])
>>> img_orig = single_tx.apply_to_image(img, img)
>>> rRotGenerator = ants.contrib.RandomRotate2D( ( 0, 40 ), reference=img )
>>> rShearGenerator=ants.contrib.RandomShear2D( (0,50), reference=img )
>>> tx1 = rRotGenerator.transform()
>>> tx2 = rShearGenerator.transform()
>>> rSrR = ants.compose_ants_transforms([tx1, tx2])
>>> rSrR.apply_to_image( img )

get_ants_transform_fixed_parameters(transform)

Get fixed parameters of an ANTsTransform

ANTsR function: getAntsrTransformFixedParameters

get_ants_transform_parameters(transform)

Get parameters of an ANTsTransform

ANTsR function: getAntsrTransformParameters

invert_ants_transform(transform)

Invert ANTsTransform

ANTsR function: invertAntsrTransform

Example

>>> import ants
>>> img = ants.image_read(ants.get_ants_data("r16")).clone('float')
>>> tx = ants.new_ants_transform(dimension=2)
>>> tx.set_parameters((0.9,0,0,1.1,10,11))
>>> img_transformed = tx.apply_to_image(img, img)
>>> inv_tx = tx.invert()
>>> img_orig = inv_tx.apply_to_image(img_transformed, img_transformed)

set_ants_transform_fixed_parameters(transform, parameters)

Set fixed parameters of an ANTsTransform

ANTsR function: setAntsrTransformFixedParameters

set_ants_transform_parameters(transform, parameters)

Set parameters of an ANTsTransform

ANTsR function: setAntsrTransformParameters

transform_index_to_physical_point(image, index)

Get spatial point from index of an image.

ANTsR function: antsTransformIndexToPhysicalPoint

Parameters:

• img (ants.core.ANTsImage) – image to get values from

• index (list or tuple or numpy.ndarray) – location in image

Return type:

tuple

Example

>>> import ants
>>> import numpy as np
>>> img = ants.make_image((10,10),np.random.randn(100))
>>> pt = ants.transform_index_to_physical_point(img, (2,2))

transform_physical_point_to_index(image, point)

Get index from spatial point of an image.

ANTsR function: antsTransformPhysicalPointToIndex

Parameters:

• image (ants.core.ANTsImage) – image to get values from

• point (list or tuple or numpy.ndarray) – point in image

Return type:

tuple

Example

>>> import ants
>>> import numpy as np
>>> img = ants.make_image((10,10),np.random.randn(100))
>>> idx = ants.transform_physical_point_to_index(img, (2,2))
>>> img.set_spacing((2,2))
>>> idx2 = ants.transform_physical_point_to_index(img, (4,4))