def test__extrapolate_out_mask():
# Input data:
initial_data = np.zeros((5, 5, 5))
initial_data[1, 2, 2] = 1
initial_data[2, 1, 2] = 2
initial_data[2, 2, 1] = 3
initial_data[3, 2, 2] = 4
initial_data[2, 3, 2] = 5
initial_data[2, 2, 3] = 6
initial_mask = initial_data.copy() != 0
# Expected result
target_data = np.array([[[0., 0., 0., 0., 0.], [0., 0., 0., 0., 0.],
[0., 0., 1., 0., 0.], [0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.]],
[[0., 0., 0., 0., 0.], [0., 0., 1.5, 0., 0.],
[0., 2., 1., 3.5, 0.], [0., 0., 3., 0., 0.],
[0., 0., 0., 0., 0.]],
[[0., 0., 2., 0., 0.], [0., 2.5, 2., 4., 0.],
[3., 3., 3.5, 6., 6.], [0., 4., 5., 5.5, 0.],
[0., 0., 5., 0., 0.]],
[[0., 0., 0., 0., 0.], [0., 0., 3., 0., 0.],
[0., 3.5, 4., 5., 0.], [0., 0., 4.5, 0., 0.],
[0., 0., 0., 0., 0.]],
[[0., 0., 0., 0., 0.], [0., 0., 0., 0., 0.],
[0., 0., 4., 0., 0.], [0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.]]])
target_mask = np.array([[[False, False, False, False, False],
[False, False, False, False, False],
[False, False, True, False, False],
[False, False, False, False, False],
[False, False, False, False, False]],
[[False, False, False, False, False],
[False, False, True, False, False],
[False, True, True, True, False],
[False, False, True, False, False],
[False, False, False, False, False]],
[[False, False, True, False, False],
[False, True, True, True, False],
[True, True, True, True, True],
[False, True, True, True, False],
[False, False, True, False, False]],
[[False, False, False, False, False],
[False, False, True, False, False],
[False, True, True, True, False],
[False, False, True, False, False],
[False, False, False, False, False]],
[[False, False, False, False, False],
[False, False, False, False, False],
[False, False, True, False, False],
[False, False, False, False, False],
[False, False, False, False, False]]])
# Test:
extrapolated_data, extrapolated_mask = _extrapolate_out_mask(initial_data,
initial_mask,
iterations=1)
assert_array_equal(extrapolated_data, target_data)
assert_array_equal(extrapolated_mask, target_mask)
def _resample_image(self, image_file, output_file, target_nii):
# Compute the background and extrapolate outside of the mask
log.info("Extrapolating %s", image_file)
niimg = nb.load(image_file)
affine = niimg.get_affine()
data = niimg.get_data().squeeze()
niimg = nb.Nifti1Image(data, affine, header=niimg.get_header())
bg_mask = compute_background_mask(niimg).get_data()
# Test if the image has been masked:
out_of_mask = data[np.logical_not(bg_mask)]
if np.all(np.isnan(out_of_mask)) or len(np.unique(out_of_mask)) == 1:
# Need to extrapolate
data = _extrapolate_out_mask(data.astype(np.float),
bg_mask, iterations=3)[0]
niimg = nb.Nifti1Image(data, affine, header=niimg.get_header())
del out_of_mask, bg_mask
log.info("Resampling %s", image_file)
resampled_nii = resample_img(
niimg, target_nii.get_affine(), target_nii.shape)
resampled_nii = nb.Nifti1Image(resampled_nii.get_data().squeeze(),
resampled_nii.get_affine(),
header=niimg.get_header())
if len(resampled_nii.shape) == 3:
resampled_nii.to_filename(output_file)
else:
# We have a 4D file
raise Exception('4D File.')
# assert len(resampled_nii.shape) == 4
# resampled_data = resampled_nii.get_data()
# affine = resampled_nii.get_affine()
# for index in range(resampled_nii.shape[-1]):
# # First save the files separately
# this_nii = nb.Nifti1Image(resampled_data[..., index], affine)
# this_id = int("%i%i" % (-row[1]['image_id'], index))
# this_file = os.path.join(output_dir, "%06d%s" % (this_id, ext))
# this_nii.to_filename(this_file)
# # Second, fix the dataframe
# out_df = out_df[out_df.image_id != row[1]['image_id']]
# this_row = row[1].copy()
# this_row.image_id = this_id
# out_df = out_df.append(this_row)
return output_file
def download_images(dest_dir,images_df=None,target=None,resample=True):
"""Downloads images dataframe and resamples them to a common space"""
orig_path = os.path.join(dest_dir, "original")
mkdir_p(orig_path)
if resample == True:
if not target:
print "To resample you must specify a target!"
return
resampled_path = os.path.join(dest_dir, "resampled")
mkdir_p(resampled_path)
target_nii = nb.load(target)
if not isinstance(images_df,pandas.DataFrame):
images_df = get_images()
out_df = images_df.copy()
for row in images_df.iterrows():
# Downloading the file to the "original" subfolder
_, _, ext = split_filename(row[1]['file'])
orig_file = os.path.join(orig_path, "%04d%s" % (row[1]['image_id'], ext))
if not os.path.exists(orig_file):
try:
print "Downloading %s" % orig_file
urllib.urlretrieve(row[1]['file'], orig_file)
if resample == True:
# Compute the background and extrapolate outside of the mask
print "Extrapolating %s" % orig_file
niimg = nb.load(orig_file)
affine = niimg.get_affine()
data = niimg.get_data().squeeze()
niimg = nb.Nifti1Image(data, affine,header=niimg.get_header())
bg_mask = compute_background_mask(niimg).get_data()
# Test if the image has been masked:
out_of_mask = data[np.logical_not(bg_mask)]
if np.all(np.isnan(out_of_mask)) or len(np.unique(out_of_mask)) == 1:
# Need to extrapolate
data = _extrapolate_out_mask(data.astype(np.float), bg_mask,iterations=3)[0]
niimg = nb.Nifti1Image(data, affine,header=niimg.get_header())
del out_of_mask, bg_mask
# Resampling the file to target and saving the output in the "resampled" folder
resampled_file = os.path.join(resampled_path,"%06d%s" % (row[1]['image_id'], ext))
print "Resampling %s" % orig_file
resampled_nii = resample_img(niimg, target_nii.get_affine(),target_nii.shape)
resampled_nii = nb.Nifti1Image(resampled_nii.get_data().squeeze(),
resampled_nii.get_affine(),
header=niimg.get_header())
if len(resampled_nii.shape) == 3:
resampled_nii.to_filename(resampled_file)
else:
# We have a 4D file
assert len(resampled_nii.shape) == 4
resampled_data = resampled_nii.get_data()
affine = resampled_nii.get_affine()
for index in range(resampled_nii.shape[-1]):
# First save the files separately
this_nii = nb.Nifti1Image(resampled_data[..., index],affine)
this_id = int("%i%i" % (-row[1]['image_id'], index))
this_file = os.path.join(resampled_path,"%06d%s" % (this_id, ext))
this_nii.to_filename(this_file)
# Second, fix the dataframe
out_df = out_df[out_df.image_id != row[1]['image_id']]
this_row = row[1].copy()
this_row.image_id = this_id
out_df = out_df.append(this_row)
except:
print "Error downloading image id %s, retry this image." %(row[1]["image_id"])
return out_df
def download_and_resample(self, dest_dir, target,collection_ids=None,image_ids=None):
"""Downloads all stat maps and resamples them to a common space"""
target_nii = nb.load(target)
orig_path = os.path.join(dest_dir, "original")
mkdir_p(orig_path)
resampled_path = os.path.join(dest_dir, "resampled")
mkdir_p(resampled_path)
combined_df = self.get_images_with_collections_df()
# If the user has specified specific images
if image_ids:
combined_df = combined_df.loc[combined_df.image_id.isin(image_ids)]
# If the user wants to subset to a set of collections
if collection_ids:
if isinstance(collection_ids,str): collection_ids = [collection_ids]
combined_df = combined_df[combined_df['collection_id'].isin(collection_ids)]
out_df = combined_df.copy()
for row in combined_df.iterrows():
# Downloading the file to the "original" subfolder
_, _, ext = split_filename(row[1]['file'])
orig_file = os.path.join(orig_path, "%04d%s" % (row[1]['image_id'], ext))
if not os.path.exists(orig_file):
try:
print "Downloading %s" % orig_file
urllib.urlretrieve(row[1]['file'], orig_file)
# Compute the background and extrapolate outside of the mask
print "Extrapolating %s" % orig_file
niimg = nb.load(orig_file)
affine = niimg.get_affine()
data = niimg.get_data().squeeze()
niimg = nb.Nifti1Image(data, affine,header=niimg.get_header())
bg_mask = compute_background_mask(niimg).get_data()
# Test if the image has been masked:
out_of_mask = data[np.logical_not(bg_mask)]
if np.all(np.isnan(out_of_mask)) or len(np.unique(out_of_mask)) == 1:
# Need to extrapolate
data = _extrapolate_out_mask(data.astype(np.float), bg_mask,iterations=3)[0]
niimg = nb.Nifti1Image(data, affine,header=niimg.get_header())
del out_of_mask, bg_mask
# Resampling the file to target and saving the output in the "resampled" folder
resampled_file = os.path.join(resampled_path,"%06d%s" % (row[1]['image_id'], ext))
print "Resampling %s" % orig_file
resampled_nii = resample_img(niimg, target_nii.get_affine(),target_nii.shape)
resampled_nii = nb.Nifti1Image(resampled_nii.get_data().squeeze(),
resampled_nii.get_affine(),
header=niimg.get_header())
if len(resampled_nii.shape) == 3:
resampled_nii.to_filename(resampled_file)
else:
# We have a 4D file
assert len(resampled_nii.shape) == 4
resampled_data = resampled_nii.get_data()
affine = resampled_nii.get_affine()
for index in range(resampled_nii.shape[-1]):
# First save the files separately
this_nii = nb.Nifti1Image(resampled_data[..., index],affine)
this_id = int("%i%i" % (-row[1]['image_id'], index))
this_file = os.path.join(resampled_path,"%06d%s" % (this_id, ext))
this_nii.to_filename(this_file)
# Second, fix the dataframe
out_df = out_df[out_df.image_id != row[1]['image_id']]
this_row = row[1].copy()
this_row.image_id = this_id
out_df = out_df.append(this_row)
except:
print "Error downloading image id %s, retry this image." %(row[1]["image_id"])
return out_df
def download_images(dest_dir, images_df=None, target=None, resample=True):
"""Downloads images dataframe and resamples them to a common space"""
orig_path = os.path.join(dest_dir, "original")
mkdir_p(orig_path)
if resample == True:
if not target:
print("To resample you must specify a target!")
return
resampled_path = os.path.join(dest_dir, "resampled")
mkdir_p(resampled_path)
target_nii = nb.load(target)
if not isinstance(images_df, pandas.DataFrame):
images_df = get_images()
out_df = images_df.copy()
for row in images_df.iterrows():
# Downloading the file to the "original" subfolder
_, _, ext = split_filename(row[1]['file'])
orig_file = os.path.join(orig_path,
"%04d%s" % (row[1]['image_id'], ext))
if not os.path.exists(orig_file):
try:
print("Downloading %s" % orig_file)
urlretrieve(row[1]['file'], orig_file)
if resample == True:
# Compute the background and extrapolate outside of the mask
print("Extrapolating %s" % orig_file)
niimg = nb.load(orig_file)
affine = niimg.get_affine()
data = niimg.get_data().squeeze()
niimg = nb.Nifti1Image(data,
affine,
header=niimg.get_header())
bg_mask = compute_background_mask(niimg).get_data()
# Test if the image has been masked:
out_of_mask = data[np.logical_not(bg_mask)]
if np.all(np.isnan(out_of_mask)) or len(
np.unique(out_of_mask)) == 1:
# Need to extrapolate
data = _extrapolate_out_mask(data.astype(np.float),
bg_mask,
iterations=3)[0]
niimg = nb.Nifti1Image(data,
affine,
header=niimg.get_header())
del out_of_mask, bg_mask
# Resampling the file to target and saving the output in the "resampled" folder
resampled_file = os.path.join(
resampled_path, "%06d%s" % (row[1]['image_id'], ext))
print("Resampling %s" % orig_file)
resampled_nii = resample_img(niimg,
target_nii.get_affine(),
target_nii.shape)
resampled_nii = nb.Nifti1Image(
resampled_nii.get_data().squeeze(),
resampled_nii.get_affine(),
header=niimg.get_header())
if len(resampled_nii.shape) == 3:
resampled_nii.to_filename(resampled_file)
else:
# We have a 4D file
assert len(resampled_nii.shape) == 4
resampled_data = resampled_nii.get_data()
affine = resampled_nii.get_affine()
for index in range(resampled_nii.shape[-1]):
# First save the files separately
this_nii = nb.Nifti1Image(
resampled_data[..., index], affine)
this_id = int("%i%i" %
(-row[1]['image_id'], index))
this_file = os.path.join(resampled_path,
"%06d%s" % (this_id, ext))
this_nii.to_filename(this_file)
# Second, fix the dataframe
out_df = out_df[
out_df.image_id != row[1]['image_id']]
this_row = row[1].copy()
this_row.image_id = this_id
out_df = out_df.append(this_row)
except:
print("Error downloading image id %s, retry this image." %
(row[1]["image_id"]))
return out_df
def test__extrapolate_out_mask():
# Input data:
initial_data = np.zeros((5,5,5))
initial_data[1,2,2] = 1
initial_data[2,1,2] = 2
initial_data[2,2,1] = 3
initial_data[3,2,2] = 4
initial_data[2,3,2] = 5
initial_data[2,2,3] = 6
initial_mask = initial_data.copy() != 0
# Expected result
target_data = np.array([[[0. , 0. , 0. , 0. , 0. ],
[0. , 0. , 0. , 0. , 0. ],
[0. , 0. , 1. , 0. , 0. ],
[0. , 0. , 0. , 0. , 0. ],
[0. , 0. , 0. , 0. , 0. ]],
[[0. , 0. , 0. , 0. , 0. ],
[0. , 0. , 1.5, 0. , 0. ],
[0. , 2. , 1. , 3.5, 0. ],
[0. , 0. , 3. , 0. , 0. ],
[0. , 0. , 0. , 0. , 0. ]],
[[0. , 0. , 2. , 0. , 0. ],
[0. , 2.5, 2. , 4. , 0. ],
[3. , 3. , 3.5, 6. , 6. ],
[0. , 4. , 5. , 5.5, 0. ],
[0. , 0. , 5. , 0. , 0. ]],
[[0. , 0. , 0. , 0. , 0. ],
[0. , 0. , 3. , 0. , 0. ],
[0. , 3.5, 4. , 5. , 0. ],
[0. , 0. , 4.5, 0. , 0. ],
[0. , 0. , 0. , 0. , 0. ]],
[[0. , 0. , 0. , 0. , 0. ],
[0. , 0. , 0. , 0. , 0. ],
[0. , 0. , 4. , 0. , 0. ],
[0. , 0. , 0. , 0. , 0. ],
[0. , 0. , 0. , 0. , 0. ]]])
target_mask = np.array([[[False, False, False, False, False],
[False, False, False, False, False],
[False, False, True, False, False],
[False, False, False, False, False],
[False, False, False, False, False]],
[[False, False, False, False, False],
[False, False, True, False, False],
[False, True, True, True, False],
[False, False, True, False, False],
[False, False, False, False, False]],
[[False, False, True, False, False],
[False, True, True, True, False],
[ True, True, True, True, True],
[False, True, True, True, False],
[False, False, True, False, False]],
[[False, False, False, False, False],
[False, False, True, False, False],
[False, True, True, True, False],
[False, False, True, False, False],
[False, False, False, False, False]],
[[False, False, False, False, False],
[False, False, False, False, False],
[False, False, True, False, False],
[False, False, False, False, False],
[False, False, False, False, False]]])
# Test:
extrapolated_data, extrapolated_mask = _extrapolate_out_mask(initial_data,
initial_mask,
iterations=1)
assert_array_equal(extrapolated_data, target_data)
assert_array_equal(extrapolated_mask, target_mask)