Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

ENH: Threshold mask in images_to_matrix #646

Merged
merged 1 commit into from
May 20, 2024
Merged

ENH: Threshold mask in images_to_matrix #646

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 7 additions & 5 deletions ants/utils/matrix_image.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,13 +123,14 @@ def images_to_matrix(image_list, mask=None, sigma=None, epsilon=0.5):
images to convert to ndarray

mask : ANTsImage (optional)
image containing binary mask. voxels in the mask are placed in the matrix
Mask image, voxels in the mask (>= epsilon) are placed in the matrix. If None,
the first image in image_list is thresholded at its mean value to create a mask.

sigma : scaler (optional)
smoothing factor

epsilon : scalar
threshold for mask
threshold for mask, values >= epsilon are included in the mask.

Returns
-------
Expand All @@ -149,6 +150,7 @@ def images_to_matrix(image_list, mask=None, sigma=None, epsilon=0.5):
mask = ants.get_mask(image_list[0])

num_images = len(image_list)
mask_thresh = mask.clone() >= epsilon
mask_arr = mask.numpy() >= epsilon
num_voxels = np.sum(mask_arr)

Expand All @@ -157,9 +159,9 @@ def images_to_matrix(image_list, mask=None, sigma=None, epsilon=0.5):
for i, img in enumerate(image_list):
if do_smooth:
img = ants.smooth_image(img, sigma, sigma_in_physical_coordinates=True)
if np.sum(np.array(img.shape) - np.array(mask.shape)) != 0:
img = ants.resample_image_to_target(img, mask, 2)
data_matrix[i, :] = img[mask]
if np.sum(np.array(img.shape) - np.array(mask_thresh.shape)) != 0:
img = ants.resample_image_to_target(img, mask_thresh, 2)
data_matrix[i, :] = img[mask_thresh]
return data_matrix


Expand Down
15 changes: 11 additions & 4 deletions tests/test_core_ants_image_io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,6 +164,7 @@ def test_images_to_matrix(self):
imgmat = ants.images_to_matrix(imglist, mask=mask)
self.assertTrue(imgmat.shape[0] == len(imglist))
self.assertTrue(imgmat.shape[1] == (mask>0).sum())
self.assertTrue(np.allclose(img[mask], imgmat[0,:]))

# go back to images
imglist2 = ants.matrix_to_images(imgmat, mask)
Expand All @@ -178,20 +179,26 @@ def test_images_to_matrix(self):
imgmat = ants.images_to_matrix(imglist, mask=mask, sigma=2.)

# with no mask
mask = ants.image_clone( img > img.mean(), pixeltype = 'float' )
imglist = [img.clone(),img.clone(),img.clone()]
imgmat = ants.images_to_matrix(imglist)

# Mask not binary
mask = ants.image_clone( img / img.mean(), pixeltype = 'float' )
imgmat = ants.images_to_matrix(imglist, mask=mask, epsilon=1)

# with mask of different shape
s = [65]*img.dimension
mask2 = ants.from_numpy(np.random.randn(*s))
mask2 = ants.from_numpy(np.random.randn(*s), spacing=[4.0, 4.0])
mask2 = mask2 > mask2.mean()
imgmat = ants.images_to_matrix(imglist, mask=mask2)
self.assertTrue(imgmat.shape[0] == len(imglist))
self.assertTrue(imgmat.shape[1] == (mask2>0).sum())



def timeseries_to_matrix(self):
img = ants.make_image( (10,10,10,5 ) )
mat = ants.timeseries_to_matrix( img )

img = ants.make_image( (10,10,10,5 ) )
mask = ants.ndimage_to_list( img )[0] * 0
mask[ 4:8, 4:8, 4:8 ] = 1
Expand Down
15 changes: 8 additions & 7 deletions tests/test_registration.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -292,7 +292,7 @@ def test_resample_image_example(self):
fi = ants.image_read(ants.get_ants_data("r16"))
finn = ants.resample_image(fi, (50, 60), True, 0)
filin = ants.resample_image(fi, (1.5, 1.5), False, 1)

def test_resample_channels(self):
img = ants.image_read( ants.get_ants_data("r16"))
img = ants.merge_channels([img, img])
Expand All @@ -304,6 +304,7 @@ def test_resample_image_to_target_example(self):
fi = ants.image_read(ants.get_ants_data("r16"))
fi2mm = ants.resample_image(fi, (2, 2), use_voxels=0, interp_type=1)
resampled = ants.resample_image_to_target(fi2mm, fi, verbose=True)
self.assertTrue(ants.image_physical_space_consistency(fi, resampled, 0.0001, datatype=True))


class TestModule_symmetrize_image(unittest.TestCase):
Expand Down Expand Up @@ -365,7 +366,7 @@ def setUp(self):

def tearDown(self):
pass

def test_landmark_transforms(self):
fixed = np.array([[50.0,50.0],[200.0,50.0],[200.0,200.0]])
moving = np.array([[50.0,50.0],[50.0,200.0],[200.0,200.0]])
Expand All @@ -381,27 +382,27 @@ def test_landmark_transforms(self):
xfrm = ants.fit_transform_to_paired_points(moving, fixed, transform_type="bspline", domain_image=domain_image, number_of_fitting_levels=5)
xfrm = ants.fit_transform_to_paired_points(moving, fixed, transform_type="diffeo", domain_image=domain_image, number_of_fitting_levels=6)

res = ants.fit_time_varying_transform_to_point_sets([fixed, moving, moving],
res = ants.fit_time_varying_transform_to_point_sets([fixed, moving, moving],
domain_image=ants.image_read(ants.get_data('r16')),
verbose=True)

def test_deformation_gradient(self):
fi = ants.image_read( ants.get_ants_data('r16'))
mi = ants.image_read( ants.get_ants_data('r64'))
fi = ants.resample_image(fi,(128,128),1,0)
mi = ants.resample_image(mi,(128,128),1,0)
mytx = ants.registration(fixed=fi , moving=mi, type_of_transform = ('SyN') )
dg = ants.deformation_gradient( ants.image_read( mytx['fwdtransforms'][0] ) )

dg = ants.deformation_gradient( ants.image_read( mytx['fwdtransforms'][0] ),
py_based=True)

dg = ants.deformation_gradient( ants.image_read( mytx['fwdtransforms'][0] ),
to_rotation=True)

dg = ants.deformation_gradient( ants.image_read( mytx['fwdtransforms'][0] ),
to_rotation=True, py_based=True)

def test_jacobian(self):
fi = ants.image_read( ants.get_ants_data('r16'))
mi = ants.image_read( ants.get_ants_data('r64'))
Expand Down