def make_matcher():
I = load_image(example_data.get_filename('neurospin',
'sulcal2000',
'nobias_ammon.nii.gz'))
J = load_image(example_data.get_filename('neurospin',
'sulcal2000',
'nobias_anubis.nii.gz'))
# Create a registration instance
R = IconicRegistration(I, J)
R.set_source_fov(fixed_npoints=64**3)
R.similarity = 'llr_cc'
return R
def load_ppm():
# Read input files
for i in range(ntissues):
fname = os.path.join(datadir, tissues[i]+'_1000Prior.img')
if i == 0:
im = load_image(fname)
affine = im.affine
data = np.zeros(list(im.shape)+[ntissues])
data[:,:,:,0] = im.data
else:
data[:,:,:,i] = load_image(fname).data
#ppm = Image(data, affine)
# Normalize and mask ppms
psum = data.sum(3)
X,Y,Z = np.where(psum>0)
for i in range(ntissues):
data[X,Y,Z,i] /= psum[X,Y,Z]
mask = (X.astype('uint'), Y.astype('uint'), Z.astype('uint'))
return data, mask, affine
pylab.pink()
array = im.data
if threshold==None:
pylab.imshow(array[:,slice,:])
else:
pylab.imshow(array[:,slice,:]>threshold)
"""
Main
"""
# Load images
I = load_image(example_data.get_filename('neurospin',
'sulcal2000',
'nobias_ammon.nii.gz'))
J = load_image(example_data.get_filename('neurospin',
'sulcal2000',
'nobias_anubis.nii.gz'))
# Create a registration instance
R = IconicRegistration(I, J)
R.set_source_fov(fixed_npoints=64**3)
R.similarity = 'llr_mi'
T = np.eye(4)
#T[0:3,3] = [4,5,6]
print R.eval(T)
def load_mri():
fname = os.path.join(datadir, 'BiasCorIm.img')
return load_image(fname)
def load_mri():
fname = os.path.join(datadir, subjects[s_idx]+'.nii')
print(fname)
return load_image(fname)
