def test_masking_biascorrection():
"""Test the masking function using bias correction."""
with tempfile.TemporaryDirectory() as test_dir:
test_in_file = np.ones((63, 96, 48))
test_in_file = nib.Nifti1Image(test_in_file, np.eye(4))
test_in_file_path = Path(test_dir) / 'test_in_file.nii.gz'
nib.save(test_in_file, test_in_file_path)
# for input_type in ['anat', 'func']:
for input_type in ['anat']:
config = {
"masking_config": {
F"masking_config_{input_type}": {
"bias_field_correction": {
"shrink_factor": 2
},
"testing": True
}
}
}
config_path = Path(test_dir) / 'test_config.json'
with open(config_path, 'w') as jsonfile:
json.dump(config, jsonfile, indent=4)
nii_path_masked, [resampled_mask_path
], resampled_mask_path = predict_mask(
in_file=test_in_file_path,
input_type=input_type,
masking_config_path=config_path)
assert Path(nii_path_masked).exists(
), f'nii_path_masked "{nii_path_masked}" does not exist, but should exist.'
assert Path(
resampled_mask_path).exists(), f'resampled_mask_path "{resampled_mask_path}" does not exist, ' \
f'but should exist.'
def tester(data_dir, studies, save_dir, model_path, data_type='anat'):
if not os.path.exists(save_dir):
os.makedirs(save_dir)
visualisation = {
'bool': True,
'path': save_dir,
}
if data_type == 'anat':
data_paths = data_loader.load_bidsdata(data_dir, studies=studies)
for path in data_paths:
print(path)
masked_path = \
predict_mask(path, visualisation_bool=visualisation['bool'], visualisation_path=visualisation['path'],
bias_correct_bool=True, anat_model_path=model_path)[0]
command = 'mv {a} {b}'.format(
a=masked_path,
b=os.path.join(save_dir, 'masked_' + os.path.basename(path)))
print(command)
os.system(command)
if data_type == 'func':
data_paths = data_loader.load_bidsdata(data_dir,
studies=['irsabi_bidsdata'],
input_type='func')
if not os.path.exists(save_dir):
os.makedirs(save_dir)
for path in data_paths:
print(path)
masked_path = predict_mask(
path,
input_type='func',
visualisation_bool=visualisation['bool'],
visualisation_path=visualisation['path'],
bias_correct_bool=True,
func_model_path=model_path)[0]
command = 'mv {a} {b}'.format(
a=masked_path,
b=os.path.join(save_dir, 'masked_' + os.path.basename(path)))
print(command)
os.system(command)
command = 'rm *.nii.gz'
os.system(command)
def test_masker():
test_dir = os.path.join(os.path.dirname(mlebe.__file__),
'masking/tests/temp/')
os.makedirs(test_dir, exist_ok=True)
test_config = json_to_dict('configs/test_config.json')
with open(os.path.join(test_dir, 'test_config.json'), 'w') as jsonfile:
json.dump(test_config, jsonfile, indent=4)
test_in_file = np.ones((63, 96, 48))
test_in_file = nib.Nifti1Image(test_in_file, np.eye(4))
test_in_file_dir = os.path.join(test_dir, 'test_in_file.nii.gz')
nib.save(test_in_file, test_in_file_dir)
_, _, _ = predict_mask(test_in_file_dir,
os.path.join(test_dir, 'test_config.json'))
shutil.rmtree(test_dir)
def tester(data_dir,
studies,
save_dir,
data_type='anat',
visualisation_format='pdf',
bias_correct=True,
with_bids_cropping=False,
model_config_path=''):
config_path = 'visualisation/vis_config.json'
config = json_file_to_pyobj(config_path)
if not os.path.exists(save_dir):
os.makedirs(save_dir)
if data_type == 'anat':
write_to_jsonfile(
config_path,
[('masking_config.masking_config_anat.model_config_path',
model_config_path),
('masking_config.masking_config_anat.bias_correct_bool',
bias_correct),
('masking_config.masking_config_anat.visualisation_format',
visualisation_format),
('masking_config.masking_config_anat.visualisation_bool', True),
('masking_config.masking_config_anat.visualisation_path',
save_dir),
('masking_config.masking_config_anat.with_bids_cropping',
with_bids_cropping)])
data_paths = data_loader.load_bidsdata(data_dir, studies=studies)
for path in tqdm(data_paths):
print(path)
masked_path = \
predict_mask(path, config_path)[
0]
command = 'mv {a} {b}'.format(
a=masked_path,
b=os.path.join(save_dir, 'masked_' + os.path.basename(path)))
print(command)
os.system(command)
if data_type == 'func':
write_to_jsonfile(
config_path,
[('masking_config.masking_config_func.model_config_path',
model_config_path),
('masking_config.masking_config_func.bias_correct_bool',
bias_correct),
('masking_config.masking_config_func.visualisation_format',
visualisation_format),
('masking_config.masking_config_func.visualisation_bool', True),
('masking_config.masking_config_func.visualisation_path',
save_dir),
('masking_config.masking_config_func.with_bids_cropping',
with_bids_cropping)])
data_paths = data_loader.load_bidsdata(data_dir,
studies=['irsabi_bidsdata'],
input_type='func')
if not os.path.exists(save_dir):
os.makedirs(save_dir)
for path in tqdm(data_paths):
print(path)
masked_path = predict_mask(path, config_path, input_type='func')[0]
command = 'mv {a} {b}'.format(
a=masked_path,
b=os.path.join(save_dir, 'masked_' + os.path.basename(path)))
print(command)
os.system(command)
command = 'rm *.nii.gz'
os.system(command)