def analyze_roi(p, delta, mod1, ss_mod1, mod1_name, mod2, ss_mod2, mod2_name, residuals, check_function):
px = p[0]
py = p[1]
pz = p[2]
roi = np.zeros_like(residuals)
roi[(px - delta) : (px + delta + 1), (py - delta) : (py + delta + 1), (pz - delta) : (pz + delta + 1)] = 1
rt.plot_slices(residuals_nb, cmap=None)
rt.plot_slices((roi + 0.1) * residuals_nb, cmap=None)
samples = roi * residuals_nb
samples = samples[roi != 0].reshape(-1)
x = mod1[roi != 0].reshape(-1)
y = mod2[roi != 0].reshape(-1)
check_function(x, y, mod1_name, mod2_name, 0)
check_function(x, y, mod1_name, mod2_name, 1)
x_ss_t1 = mod1[roi != 0].reshape(-1)
y_ss_t1 = ss_mod1[roi != 0].reshape(-1)
check_function(x_ss_t1, y_ss_t1, mod1_name, "F[" + mod2_name + "]", 0)
check_function(x_ss_t1, y_ss_t1, mod1_name, "F[" + mod2_name + "]", 1)
x_ss_t2 = mod2[roi != 0].reshape(-1)
y_ss_t2 = ss_mod2[roi != 0].reshape(-1)
check_function(x_ss_t2, y_ss_t2, mod2_name, "F[" + mod1_name + "]", 0)
check_function(x_ss_t2, y_ss_t2, mod2_name, "F[" + mod1_name + "]", 1)
def analyze_roi(p, delta, mod1, ss_mod1, mod1_name, mod2, ss_mod2, mod2_name, residuals, check_function):
px = p[0]
py = p[1]
pz = p[2]
roi = np.zeros_like(residuals)
roi[(px-delta):(px+delta+1), (py-delta):(py+delta+1), (pz-delta):(pz+delta+1)] = 1
rt.plot_slices(residuals_nb, cmap=None)
rt.plot_slices((roi+0.1)*residuals_nb, cmap=None)
samples = roi*residuals_nb
samples = samples[roi!=0].reshape(-1)
x = mod1[roi!=0].reshape(-1)
y = mod2[roi!=0].reshape(-1)
check_function(x, y, mod1_name, mod2_name, 0)
check_function(x, y, mod1_name, mod2_name, 1)
x_ss_t1 = mod1[roi!=0].reshape(-1)
y_ss_t1 = ss_mod1[roi!=0].reshape(-1)
check_function(x_ss_t1, y_ss_t1, mod1_name, "F["+mod2_name+"]", 0)
check_function(x_ss_t1, y_ss_t1, mod1_name, "F["+mod2_name+"]", 1)
x_ss_t2 = mod2[roi!=0].reshape(-1)
y_ss_t2 = ss_mod2[roi!=0].reshape(-1)
check_function(x_ss_t2, y_ss_t2, mod2_name, "F["+mod1_name+"]", 0)
check_function(x_ss_t2, y_ss_t2, mod2_name, "F["+mod1_name+"]", 1)
def quick_check():
img1_fname = "/home/omar/data/DATA_NeoBrainS12/T1.nii.gz"
img2_fname = "/home/omar/data/DATA_NeoBrainS12/set2_i1_t1.nii.gz"
img1_nib = nib.load(img1_fname)
img1 = img1_nib.get_data().squeeze()
img1_affine = img1_nib.get_affine()
img2_nib = nib.load(img2_fname)
img2 = img2_nib.get_data().squeeze()
img2_affine = img2_nib.get_affine()
# nib.aff2axcodes(img1_affine)
#aff = AffineMap(None, img1.shape, img1_affine, img2.shape, img2_affine)
#aff = transform_centers_of_mass(img1, img1_affine, img2, img2_affine)
aff = dipy_align(img1, img1_affine, img2, img2_affine, np.eye(4))
img2_resampled = aff.transform(img2)
rt.overlay_slices(img1, img2_resampled, slice_type=0)
rt.overlay_slices(img1, img2_resampled, slice_type=1)
rt.overlay_slices(img1, img2_resampled, slice_type=2)
# Verify that original and RAS versions of neo1 describe the same object
# Load original data
neo1_fname = get_neobrain('train', 1, 'T1')
neo1_old, neo1_old_affine, neo1_old_spacing, neo1_old_ori = load_from_raw(neo1_fname)
# Load RAS version
neo1_nib = nib.load(neo1_fname)
neo1 = neo1_nib.get_data()
neo1_affine = neo1_nib.get_affine()
# Resample RAS on top of original
aff = AffineMap(None, neo1_old.shape, neo1_old_affine, neo1.shape, neo1_affine)
neo1_resampled = aff.transform(neo1)
rt.overlay_slices(neo1_old, neo1_resampled, slice_type=0)
rt.overlay_slices(neo1_old, neo1_resampled, slice_type=1)
rt.overlay_slices(neo1_old, neo1_resampled, slice_type=2)
# Attempt to resample a test volume on top of training
neo2_fname = get_neobrain('test', 1, 'i1_t1')
neo2_nib = nib.load(neo2_fname)
neo2 = neo2_nib.get_data()
neo2_affine = neo2_nib.get_affine()
aff = transform_centers_of_mass(neo1, neo1_affine, neo2, neo2_affine)
#aff = dipy_align(neo1, neo1_affine, neo2, neo2_affine)
neo2_resampled = aff.transform(neo2)
rt.overlay_slices(neo1, neo2_resampled, slice_type=0)
rt.overlay_slices(neo1, neo2_resampled, slice_type=1)
rt.overlay_slices(neo1, neo2_resampled, slice_type=2)
# Load atlas
atlas_fname = get_neobrain('atlas', 'neo-withSkull', None)
atlas_nib = nib.load(atlas_fname)
atlas_affine = atlas_nib.get_affine()
atlas = atlas_nib.get_data()
rt.plot_slices(atlas)
# Resample atlas on top of neo1
aff = AffineMap(None, neo1.shape, neo1_affine, atlas.shape, atlas_affine)
atlas_resampled = aff.transform(atlas)
rt.overlay_slices(neo1, atlas_resampled)
ibsr1 = ibsr1_nib.get_data().squeeze()
ibsr1_affine = ibsr1_nib.get_affine()
# Load brainweb (and match ibsr axes)
brainweb_strip_name = info.get_brainweb("t1", "strip")
brainweb_strip_nib = nib.load(brainweb_strip_name)
brainweb_strip = brainweb_strip_nib.get_data().squeeze()
brainweb_strip = brainweb_strip.transpose([0, 2, 1])[::-1, :, :]
brainweb_mask = brainweb_strip > 0
brainweb_name = info.get_brainweb("t1", "raw")
brainweb_nib = nib.load(brainweb_name)
brainweb = brainweb_nib.get_data().squeeze()
brainweb_affine = brainweb_nib.get_affine()
brainweb = brainweb.transpose([0, 2, 1])[::-1, :, :]
rt.plot_slices(brainweb)
brainweb_affine = ibsr1_affine.copy()
brainweb_affine[brainweb_affine != 0] = 1
brainweb_affine[0, 0] = -1
# Reslice Brainweb on IBSR1
ibsr_to_bw = AffineMap(None, ibsr1.shape, ibsr1_affine, brainweb.shape, brainweb_affine)
bw_on_ibsr1 = ibsr_to_bw.transform(brainweb)
rt.overlay_slices(ibsr1, bw_on_ibsr1) # misaligned
c_of_mass = transform_centers_of_mass(ibsr1, ibsr1_affine, brainweb, brainweb_affine)
bw_on_ibsr1 = c_of_mass.transform(brainweb)
rt.overlay_slices(ibsr1, bw_on_ibsr1) # roughly aligned
# Start affine alignment
ibsr1 = ibsr1_nib.get_data().squeeze()
ibsr1_affine = ibsr1_nib.get_affine()
# Load brainweb (and match ibsr axes)
brainweb_strip_name = info.get_brainweb('t1', 'strip')
brainweb_strip_nib = nib.load(brainweb_strip_name)
brainweb_strip = brainweb_strip_nib.get_data().squeeze()
brainweb_strip = brainweb_strip.transpose([0, 2, 1])[::-1, :, :]
brainweb_mask = brainweb_strip > 0
brainweb_name = info.get_brainweb('t1', 'raw')
brainweb_nib = nib.load(brainweb_name)
brainweb = brainweb_nib.get_data().squeeze()
brainweb_affine = brainweb_nib.get_affine()
brainweb = brainweb.transpose([0, 2, 1])[::-1, :, :]
rt.plot_slices(brainweb)
brainweb_affine = ibsr1_affine.copy()
brainweb_affine[brainweb_affine != 0] = 1
brainweb_affine[0, 0] = -1
# Reslice Brainweb on IBSR1
ibsr_to_bw = AffineMap(None, ibsr1.shape, ibsr1_affine, brainweb.shape,
brainweb_affine)
bw_on_ibsr1 = ibsr_to_bw.transform(brainweb)
rt.overlay_slices(ibsr1, bw_on_ibsr1) # misaligned
c_of_mass = transform_centers_of_mass(ibsr1, ibsr1_affine, brainweb,
brainweb_affine)
bw_on_ibsr1 = c_of_mass.transform(brainweb)
rt.overlay_slices(ibsr1, bw_on_ibsr1) # roughly aligned
w_path_nib = nib.Nifti1Image(w_path, dwi_nib.get_affine())
w_path_nib.to_filename("w_path.nii.gz")
P = np.random.permutation(range(1, 33))
for i in range(32):
s = w_path.shape[2] // 2
figure(facecolor="white")
subplot(1, 2, 1)
imshow(w_path[:, :, s, P[i]].T)
subplot(1, 2, 2)
imshow(dwi[:, :, s, P[i]].T)
for i in range(2, 4):
rt.plot_slices(dwi[..., i])
def optimal_vs_average_experiment():
# Compute transfer for optimal local-linearity
radius = 5
init_from_mean = True
nlabels_t1 = 1 + np.max(t1_lab)
nlabels_t2 = 1 + np.max(t2_lab)
means_t1t2, vars_t1t2 = get_mean_transfer(t1_lab, t2)
fmean_t1lab = np.array(means_t1t2)
means_t2t1, vars_t2t1 = get_mean_transfer(t2_lab, t1)
fmean_t2lab = np.array(means_t2t1)
def quick_check():
img1_fname = "/home/omar/data/DATA_NeoBrainS12/T1.nii.gz"
img2_fname = "/home/omar/data/DATA_NeoBrainS12/set2_i1_t1.nii.gz"
img1_nib = nib.load(img1_fname)
img1 = img1_nib.get_data().squeeze()
img1_affine = img1_nib.get_affine()
img2_nib = nib.load(img2_fname)
img2 = img2_nib.get_data().squeeze()
img2_affine = img2_nib.get_affine()
# nib.aff2axcodes(img1_affine)
#aff = AffineMap(None, img1.shape, img1_affine, img2.shape, img2_affine)
#aff = transform_centers_of_mass(img1, img1_affine, img2, img2_affine)
aff = dipy_align(img1, img1_affine, img2, img2_affine, np.eye(4))
img2_resampled = aff.transform(img2)
rt.overlay_slices(img1, img2_resampled, slice_type=0)
rt.overlay_slices(img1, img2_resampled, slice_type=1)
rt.overlay_slices(img1, img2_resampled, slice_type=2)
# Verify that original and RAS versions of neo1 describe the same object
# Load original data
neo1_fname = get_neobrain('train', 1, 'T1')
neo1_old, neo1_old_affine, neo1_old_spacing, neo1_old_ori = load_from_raw(
neo1_fname)
# Load RAS version
neo1_nib = nib.load(neo1_fname)
neo1 = neo1_nib.get_data()
neo1_affine = neo1_nib.get_affine()
# Resample RAS on top of original
aff = AffineMap(None, neo1_old.shape, neo1_old_affine, neo1.shape,
neo1_affine)
neo1_resampled = aff.transform(neo1)
rt.overlay_slices(neo1_old, neo1_resampled, slice_type=0)
rt.overlay_slices(neo1_old, neo1_resampled, slice_type=1)
rt.overlay_slices(neo1_old, neo1_resampled, slice_type=2)
# Attempt to resample a test volume on top of training
neo2_fname = get_neobrain('test', 1, 'i1_t1')
neo2_nib = nib.load(neo2_fname)
neo2 = neo2_nib.get_data()
neo2_affine = neo2_nib.get_affine()
aff = transform_centers_of_mass(neo1, neo1_affine, neo2, neo2_affine)
#aff = dipy_align(neo1, neo1_affine, neo2, neo2_affine)
neo2_resampled = aff.transform(neo2)
rt.overlay_slices(neo1, neo2_resampled, slice_type=0)
rt.overlay_slices(neo1, neo2_resampled, slice_type=1)
rt.overlay_slices(neo1, neo2_resampled, slice_type=2)
# Load atlas
atlas_fname = get_neobrain('atlas', 'neo-withSkull', None)
atlas_nib = nib.load(atlas_fname)
atlas_affine = atlas_nib.get_affine()
atlas = atlas_nib.get_data()
rt.plot_slices(atlas)
# Resample atlas on top of neo1
aff = AffineMap(None, neo1.shape, neo1_affine, atlas.shape, atlas_affine)
atlas_resampled = aff.transform(atlas)
rt.overlay_slices(neo1, atlas_resampled)
