def emit_registered(self, values):
id, image, classification = values
registered_image, _ = [image, None
] if id == 0 else afr.affine_registration(
image, self.reference_image)
features = skimage.filters.gaussian(registered_image -
self.reference_image,
sigma=2)[self.mask].flatten()
self.log("registered image {} {}".format(id, features))
self.emit([id, features, classification])
def _reg_prealign(row, force_recompute=False):
prealign_file = _get_fname(row, '_reg_prealign.npy')
if not op.exists(prealign_file) or force_recompute:
moving = nib.load(_b0(row, force_recompute=force_recompute))
static = dpd.read_mni_template()
moving_data = moving.get_data()
moving_affine = moving.affine
static_data = static.get_data()
static_affine = static.affine
_, aff = reg.affine_registration(moving_data, static_data,
moving_affine, static_affine)
np.save(prealign_file, aff)
return prealign_file
def _reg_prealign(self, row):
prealign_file = self._get_fname(row,
'_prealign_from-DWI_to-MNI_xfm.npy')
if self.force_recompute or not op.exists(prealign_file):
moving = nib.load(self._b0(row))
static = dpd.read_mni_template()
moving_data = moving.get_fdata()
moving_affine = moving.affine
static_data = static.get_fdata()
static_affine = static.affine
_, aff = reg.affine_registration(moving_data, static_data,
moving_affine, static_affine)
np.save(prealign_file, aff)
meta_fname = self._get_fname(row,
'_prealign_from-DWI_to-MNI_xfm.json')
meta = dict(type="rigid")
afd.write_json(meta_fname, meta)
return prealign_file
#
# .. note::
# To find the right place for the waypoint ROIs, we calculate a non-linear
# transformation between the individual's brain and the MNI T2 template.
# Before calculating this non-linear warping, we perform a pre-alignment
# using an affine transformation.
print("Registering to template...")
MNI_T2_img = afd.read_mni_template()
if not op.exists(op.join(working_dir, 'mapping.nii.gz')):
import dipy.core.gradients as dpg
gtab = dpg.gradient_table(hardi_fbval, hardi_fbvec)
b0 = np.mean(img.get_fdata()[..., gtab.b0s_mask], -1)
# Prealign using affine registration
_, prealign = reg.affine_registration(b0, MNI_T2_img.get_fdata(),
img.affine, MNI_T2_img.affine)
# Then register using a non-linear registration using the affine for
# prealignment
warped_hardi, mapping = reg.syn_register_dwi(hardi_fdata,
gtab,
prealign=prealign)
reg.write_mapping(mapping, op.join(working_dir, 'mapping.nii.gz'))
else:
mapping = reg.read_mapping(op.join(working_dir, 'mapping.nii.gz'), img,
MNI_T2_img)
mapping_img = nib.load(op.join(working_dir, 'mapping.nii.gz'))
mapping_img_data = mapping_img.get_fdata()
# Working with diffeomorphic map data
#
# To find the right place for the waypoint ROIs, we calculate a non-linear
# transformation between the individual's brain DWI measurement (the b0
# measurements) and the MNI T1 template.
# Before calculating this non-linear warping, we perform a pre-alignment
# using an affine transformation.
print("Registering to template...")
MNI_T1w_img = afd.read_mni_template(weight="T1w")
if not op.exists(op.join(working_dir, 'mapping.nii.gz')):
import dipy.core.gradients as dpg
gtab = dpg.gradient_table(hardi_fbval, hardi_fbvec)
# Prealign using affine registration
_, prealign = reg.affine_registration(apm, MNI_T1w_img.get_fdata(),
img.affine, MNI_T1w_img.affine)
# Then register using a non-linear registration using the affine for
# prealignment
warped_hardi, mapping = reg.syn_register_dwi(hardi_fdata,
gtab,
prealign=prealign)
reg.write_mapping(mapping, op.join(working_dir, 'mapping.nii.gz'))
else:
mapping = reg.read_mapping(op.join(working_dir, 'mapping.nii.gz'), img,
MNI_T1w_img)
##########################################################################
# Bundle specification
# -------------------------------------------
#