def initialize(self, data_collection):
super(SkullStrip_Model, self).initialize(data_collection)
for label, data_group in data_collection.data_groups.iteritems():
reference_filename = data_group.data[data_collection.current_case][
self.reference_channel[0]]
self.mask_filename = self.generate_output_filename(
reference_filename, self.mask_string)
input_data = np.take(data_group.preprocessed_case,
self.reference_channel,
axis=-1)[np.newaxis, ...]
# Also Hacky
self.model.outputs[-1].model = self.model
self.model.outputs[-1].input_patch_shape = self.model.outputs[
-1].model.model.layers[0].input_shape
self.model.outputs[-1].process_case([input_data])
self.model.outputs[-1].postprocess()
save_numpy_2_nifti(
np.squeeze(self.model.outputs[-1].return_objects[-1]),
data_group.preprocessed_affine, self.mask_filename) # Hacky
self.mask_numpy = read_image_files(self.mask_filename,
return_affine=False)
def execute(self, data_collection):
if self.mask_numpy is None:
for label, data_group in list(data_collection.data_groups.items()):
input_data = np.take(data_group.preprocessed_case,
self.reference_channel,
axis=-1)[np.newaxis, ...]
# Hacky -- TODO: Revise.
self.model.outputs[-1].model = self.model
self.model.outputs[-1].input_patch_shape = self.model.outputs[
-1].model.model.layers[0].input_shape
self.model.outputs[-1].process_case(input_data)
self.model.outputs[-1].postprocess(input_data)
reference_filename = data_group.data[
data_collection.current_case][self.reference_channel[0]]
self.mask_filename = self.generate_output_filename(
reference_filename, self.mask_string)
save_numpy_2_nifti(
np.squeeze(self.model.outputs[-1].return_objects[-1]),
self.mask_filename,
data_group.preprocessed_affine) # Hacky
self.mask_numpy = read_image_files(self.mask_filename,
return_affine=False)
super(SkullStrip_Model, self).execute(data_collection)
def save_to_file(self, data_group):
""" No idea how this will work if the amount of output files is changed in a preprocessing step
Also missing affines is a problem.
"""
if type(self.output_data) is not list:
for file_idx, output_filename in enumerate(self.output_filenames):
if self.overwrite or not os.path.exists(output_filename):
save_numpy_2_nifti(np.squeeze(self.output_data[..., file_idx]), data_group.preprocessed_affine, output_filename)
return
def initialize(self, data_collection):
super(SkullStrip, self).initialize(data_collection)
for label, data_group in data_collection.data_groups.iteritems():
reference_filename = data_group.data[data_collection.current_case][
self.reference_channel]
self.mask_filename = self.generate_output_filename(
reference_filename, self.mask_string)
if type(data_group.preprocessed_case) is list:
input_file = data_group.preprocessed_case[
self.reference_channel]
else:
# What to do about affines here... Also, reroute this file to a temporary directory.
input_file = save_numpy_2_nifti(
data_group.preprocessed_case[..., self.reference_channel],
data_group.preprocessed_affine,
self.generate_output_filename(reference_filename))
specific_command = self.command + [
quotes(input_file),
quotes(self.mask_filename), '-f',
str(self.bet2_f), '-g',
str(self.bet2_g), '-m'
]
subprocess.call(' '.join(specific_command), shell=True)
os.rename(self.mask_filename + '_mask.nii.gz', self.mask_filename)
self.mask_numpy = read_image_files(self.mask_filename,
return_affine=False)
def save_output(self, postprocessor=None):
# Currently assumes Nifti output. TODO: Make automatically detect output or determine with a class variable.
# Ideally, split also this out into a saving.py function in utils.
# Case naming is a little wild here, TODO: make more simple.
for input_data in self.return_objects:
casename = self.data_collection.data_groups[self.inputs[0]].base_casename
input_affine = self.data_collection.data_groups[self.inputs[0]].base_affine
augmentation_string = self.data_collection.data_groups[self.inputs[0]].augmentation_strings[-1]
if self.output_directory is None:
output_directory = casename
else:
output_directory = self.output_directory
if postprocessor is None:
output_filepath = os.path.join(output_directory, replace_suffix(self.output_filename, '', augmentation_string + self.postprocessor_string))
else:
output_filepath = os.path.join(output_directory, replace_suffix(self.output_filename, '', augmentation_string + postprocessor.postprocessor_string))
# If prediction already exists, skip it. Useful if process is interrupted.
if os.path.exists(output_filepath) and not self.replace_existing:
return
# Squeezing is a little cagey. Maybe explicitly remove batch dimension instead.
output_shape = input_data.shape
input_data = np.squeeze(input_data)
return_filenames = []
# If there is only one channel, only save one file.
if output_shape[-1] == 1 or self.stack_outputs:
self.return_filenames += [save_numpy_2_nifti(input_data, input_affine, output_filepath=output_filepath)]
else:
for channel in xrange(output_shape[-1]):
return_filenames += [save_numpy_2_nifti(input_data[..., channel], input_affine, output_filepath=replace_suffix(output_filepath, input_suffix='', output_suffix='_channel_' + str(channel)))]
self.return_filenames += [return_filenames]
return
def initialize(self, data_collection):
super(SkullStrip, self).initialize(data_collection)
for label, data_group in data_collection.data_groups.iteritems():
if type(data_group.preprocessed_case) is list:
input_file = data_group.preprocessed_case[
self.reference_channel]
else:
# What to do about affines here...
input_file = save_numpy_2_nifti(
data_group.preprocessed_case[..., self.reference_channel],
data_group.preprocessed_affine,
'DEEPNEURO_TEMP_FILE.nii.gz')
base_filename = data_group.data[data_collection.current_case][
self.reference_channel]
self.mask_filename = self.generate_output_filename(
base_filename, self.mask_string)
specific_command = self.command + [
input_file, self.mask_filename, '-f',
str(self.bet2_f), '-g',
str(self.bet2_g), '-m'
]
subprocess.call(' '.join(specific_command),
shell=True,
stdout=FNULL,
stderr=subprocess.STDOUT)
os.rename(self.mask_filename + '_mask.nii.gz', self.mask_filename)
self.mask_numpy = read_image_files(self.mask_filename,
return_affine=False)