def test_get_displacement_norm_between_images(self):
shapes = {
2: (100, 200),
3: (100, 200, 50),
}
origin = {
2: (-100, 10),
3: (-100, 10, 33.3),
}
direction = {
2: (0, -1, 1, 0),
3: (0, 1, 0, 1, 0, 0, 0, 0, -1),
}
spacing = {
2: (1.1, 2.5),
3: (1.1, 2.5, 5),
}
parameters = {
2: (-1.7, -10.23, 12),
3: (0.3, -1.3, 2.1, -10.23, 12, 4),
}
center = {
2: (-10, 15),
3: (-10, 15, 17.3),
}
for dim in [2, 3]:
print("Dimension: %d" % dim)
transform_sitk = getattr(sitk, "Euler%dDTransform" % dim)()
transform_sitk.SetParameters(parameters[dim])
transform_sitk.SetCenter(center[dim])
image_sitk = sitk.Image(shapes[dim], sitk.sitkFloat32)
image_sitk.SetOrigin(origin[dim])
image_sitk.SetDirection(direction[dim])
image_sitk.SetSpacing(spacing[dim])
# -------------------Compute mean displacements-------------------
t0 = ph.start_timing()
norm_disp = utils.get_voxel_displacements(image_sitk,
transform_sitk)
print("Time method: %s" % ph.stop_timing(t0))
# -----------------------Compute ref result-----------------------
disp_shape = sitk.GetArrayFromImage(image_sitk).shape
t0 = ph.start_timing()
disp = np.zeros(disp_shape + (dim, ))
for index in np.ndindex(shapes[dim]):
point = image_sitk.TransformIndexToPhysicalPoint(index)
point_ref = transform_sitk.TransformPoint(point)
disp[index[::-1]] = point - np.array(point_ref)
norm_disp_ref = np.sqrt(np.sum(np.square(disp), axis=-1))
print("Time reference: %s" % ph.stop_timing(t0))
self.assertAlmostEqual(np.linalg.norm(norm_disp - norm_disp_ref),
0,
places=self.precision)
def main():
pid = "49"
method = "manual" #auto, manual
input_dir = "{0:}/input".format(pid)
mask_dir = "{0:}/mask_{1:}/mask".format(pid, method)
output_dir = "{0:}/input_preprocess".format(pid)
# get input stack names
files = os.listdir(input_dir)
input_files = []
mask_files = []
for file in files:
if (("nii.gz" in file)):
input_files.append("{0:}/{1:}".format(input_dir, file))
mask_name = "{0:}/{1:}".format(mask_dir, file)
assert(os.path.isfile(mask_name))
mask_files.append(mask_name)
cmd_args = []
cmd_args.append("--filenames %s" % (" ").join(input_files))
cmd_args.append("--filenames-masks %s" % (" ").join(mask_files))
cmd_args.append("--dir-output %s" % output_dir)
cmd_args.append("--prefix-output ''")
cmd = "niftymic_correct_bias_field %s" % (" ").join(cmd_args)
time_start_bias = ph.start_timing()
exit_code = ph.execute_command(cmd)
elapsed_time_bias = ph.stop_timing(time_start_bias)
print("Computational Time for Bias Field Correction: %s" %
elapsed_time_bias)
if exit_code != 0:
raise RuntimeError("Bias field correction failed")
return 0
def run_dilation(self):
time_start = ph.start_timing()
dilater = sitk.BinaryDilateImageFilter()
dilater.SetKernelType(eval("sitk.sitk" + self._dilation_kernel))
dilater.SetKernelRadius(self._dilation_radius)
if self._use_dilation_in_plane_only:
shape = self._mask_sitk.GetSize()
N_slices = shape[2]
nda_mask = np.zeros(shape[::-1], dtype=np.uint8)
for i in range(0, N_slices):
slice_mask_sitk = self._mask_sitk[:, :, i:i + 1]
mask_sitk = dilater.Execute(slice_mask_sitk)
nda_mask[i, :, :] = sitk.GetArrayFromImage(mask_sitk)
mask_sitk = sitk.GetImageFromArray(nda_mask)
mask_sitk.CopyInformation(self._mask_sitk)
self._mask_sitk = mask_sitk
else:
self._mask_sitk = dilater.Execute(self._mask_sitk)
if self._stack is not None:
self._stack = st.Stack.from_sitk_image(
self._stack.sitk,
image_sitk_mask=self._mask_sitk,
filename=self._stack.get_filename())
self._computational_time = ph.stop_timing(time_start)
def run_bias_field_correction(self):
time_start = ph.start_timing()
bias_field_corrector = sitk.N4BiasFieldCorrectionImageFilter()
bias_field_corrector.SetBiasFieldFullWidthAtHalfMaximum(
self._bias_field_fwhm)
bias_field_corrector.SetConvergenceThreshold(
self._convergence_threshold)
bias_field_corrector.SetSplineOrder(self._spline_order)
bias_field_corrector.SetWienerFilterNoise(self._wiener_filter_noise)
if self._use_mask:
image_sitk = bias_field_corrector.Execute(self._stack.sitk,
self._stack.sitk_mask)
else:
image_sitk = bias_field_corrector.Execute(self._stack.sitk)
# Reading of image might lead to slight differences
stack_corrected_sitk_mask = sitk.Resample(
self._stack.sitk_mask, image_sitk,
sitk.Euler3DTransform(), sitk.sitkNearestNeighbor, 0,
self._stack.sitk_mask.GetPixelIDValue())
self._stack_corrected = st.Stack.from_sitk_image(
image_sitk=image_sitk,
image_sitk_mask=stack_corrected_sitk_mask,
filename=self._prefix_corrected + self._stack.get_filename(),
)
# Get computational time
self._computational_time = ph.stop_timing(time_start)
def run(self):
if not isinstance(self._fixed_itk, self._image_type):
raise ValueError("Fixed image must be of type itk.Image")
if not isinstance(self._moving_itk, self._image_type):
raise ValueError("Moving image must be of type itk.Image")
if self._fixed_itk_mask is not None and \
not isinstance(self._fixed_itk_mask, self._image_type):
raise ValueError(
"Fixed image mask must be of type itk.Image")
if self._moving_itk_mask is not None and \
not isinstance(self._moving_itk_mask, self._image_type):
raise ValueError(
"Moving image mask must be of type itk.Image")
time_start = ph.start_timing()
# Execute registration method
self._run_v3()
# self._run_v4()
# Get computational time
self._computational_time = ph.stop_timing(time_start)
def from_volume(cls, file_paths_masks):
t0 = ph.start_timing()
target_stack_estimator = cls()
volumes = np.array([
TargetStackEstimator._compute_volume(f) for f in file_paths_masks
])
# find index to smallest "valid" volume, i.e. volume > q * median
index = np.argmax(
volumes[np.argsort(volumes)] > 0.7 * np.median(volumes))
index = np.argsort(volumes)[index]
# Get index corresponding to maximum volume stack mask
# index = np.argmax(volumes)
# index = np.argmin(volumes)
# Get index corresponding to median volume stack mask
# index = np.argsort(volumes)[len(volumes)//2]
target_stack_estimator._target_stack_index = index
# computational time
target_stack_estimator._computational_time = ph.stop_timing(t0)
return target_stack_estimator
def test_translation_registration_of_slices(self):
filename_prefix = "TranslationOnly_"
# filename_prefix = "RigidTransform_"
filename_HRVolume = "HRVolume"
filename_StackSim = filename_prefix + "StackSimulated"
filename_transforms_prefix = filename_prefix + "TransformGroundTruth_slice"
stack_sim = st.Stack.from_filename(
os.path.join(self.dir_test_data, filename_StackSim + ".nii.gz"))
HR_volume = st.Stack.from_filename(
os.path.join(self.dir_test_data, filename_HRVolume + ".nii.gz"))
slices_sim = stack_sim.get_slices()
N_slices = len(slices_sim)
scale = np.array(
[180. / np.pi, 180. / np.pi, 180. / np.pi, 1., 1., 1.])
time_start = ph.start_timing()
for j in range(0, N_slices):
# for j in range(20, N_slices):
rigid_transform_groundtruth_sitk = sitk.ReadTransform(
self.dir_test_data + filename_transforms_prefix + str(j) +
".tfm")
parameters_gd = np.array(
rigid_transform_groundtruth_sitk.GetParameters())
angle_max = 5. * np.pi / 180.
t_max = 5.
registration = myreg.Registration(
fixed=slices_sim[j],
moving=HR_volume,
# initializer_type="SelfGEOMETRY",
use_verbose=0,
# data_loss="soft_l1",
# x_scale=[angle_max, angle_max, angle_max, t_max, t_max, t_max],
)
registration.run_registration()
# registration.print_statistics()
# Check parameters
transform_sitk = registration.get_registration_transform_sitk()
parameters = np.array(transform_sitk.GetParameters())
norm_diff = np.linalg.norm(parameters - parameters_gd)
params = parameters * scale
params_gt = parameters_gd * scale
print("Slice %s/%s: |parameters-parameters_gd| = %s" %
(j, N_slices - 1, str(norm_diff)))
print("\tEst: " + str(params) + " (deg/mmm)")
print("\tGT: " + str(params_gt) + " (deg/mmm)")
print("\tDiff: " + str(params - params_gt) + " (deg/mmm)")
self.assertEqual(np.round(norm_diff, decimals=self.accuracy), 0)
# Set elapsed time
print("Translation: " + str(ph.stop_timing(time_start)))
def run(self):
time_start = ph.start_timing()
self._run()
self._computational_time = ph.stop_timing(time_start)
if self._verbose:
ph.print_info("Required computational time: %s" %
(self.get_computational_time()))
def run(self):
ph.print_info("Chosen SDA approach: " + self._sda_approach)
ph.print_info("Smoothing parameter sigma = " + str(self._sigma_array))
time_start = ph.start_timing()
self._run[self._sda_approach]()
# Get computational time
self._computational_time = ph.stop_timing(time_start)
if self._verbose:
ph.print_info("Required computational time: %s" %
(self.get_computational_time()))
def run(self):
if not isinstance(self._fixed_points_nda, np.ndarray):
raise IOError("Fixed points must be of type np.array")
if not isinstance(self._moving_points_nda, np.ndarray):
raise IOError("Moving points must be of type np.array")
if self._fixed_points_nda.shape[1] != self._moving_points_nda.shape[1]:
raise IOError(
"Spatial dimensions of fixed and moving points must be equal")
# Execute registration method
time_start = ph.start_timing()
self._run()
# Get computational time
self._computational_time = ph.stop_timing(time_start)
def run(self):
if not isinstance(self._fixed, st.Stack) and \
not isinstance(self._fixed, sl.Slice):
raise TypeError("Fixed image must be of type 'Stack' or 'Slice'")
if not isinstance(self._moving, st.Stack) and \
not isinstance(self._moving, sl.Slice):
raise TypeError("Moving image must be of type 'Stack' or 'Slice'")
time_start = ph.start_timing()
# Execute registration method
self._run()
# Get computational time
self._computational_time = ph.stop_timing(time_start)
if self._use_verbose:
ph.print_info("Required computational time: %s" %
(self.get_computational_time()))
def run(self):
ph.create_directory(dir_tmp, delete_files=True)
# Write images
sitkh.write_nifti_image_sitk(
self._stack1.sitk,
self._dir_tmp + self._stack1.get_filename() + ".nii.gz")
sitkh.write_nifti_image_sitk(
self._stack2.sitk,
self._dir_tmp + self._stack2.get_filename() + ".nii.gz")
cmd = "siena "
cmd += self._dir_tmp + self._stack1.get_filename() + ".nii.gz "
cmd += self._dir_tmp + self._stack2.get_filename() + ".nii.gz "
cmd += "-o " + self._dir_output + " "
cmd += self._options
time_start = ph.start_timing()
ph.execute_command(cmd)
self._elapsed_time = ph.stop_timing(time_start)
# Extract measures from report
self._extract_percentage_brain_volume_change()
def main():
time_start = ph.start_timing()
np.set_printoptions(precision=3)
input_parser = InputArgparser(
description="Register an obtained reconstruction (moving) "
"to a template image/space (fixed) using rigid registration. "
"The resulting registration can optionally be applied to previously "
"obtained motion correction slice transforms so that a volumetric "
"reconstruction is possible in the (standard anatomical) space "
"defined by the fixed.", )
input_parser.add_fixed(required=True)
input_parser.add_moving(required=True)
input_parser.add_output(help="Path to registration transform (.txt)",
required=True)
input_parser.add_fixed_mask(required=False)
input_parser.add_moving_mask(required=False)
input_parser.add_option(
option_string="--initial-transform",
type=str,
help="Path to initial transform. "
"If not provided, registration will be initialized based on "
"rigid alignment of eigenbasis of the fixed/moving image masks "
"using principal component analysis",
default=None)
input_parser.add_v2v_method(
option_string="--method",
help="Registration method used for the registration.",
default="RegAladin",
)
input_parser.add_argument(
"--refine-pca",
"-refine-pca",
action='store_true',
help="If given, PCA-based initializations will be refined using "
"RegAladin registrations.")
input_parser.add_dir_input_mc()
input_parser.add_verbose(default=0)
input_parser.add_log_config(default=1)
args = input_parser.parse_args()
input_parser.print_arguments(args)
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
if not args.output.endswith(".txt"):
raise IOError("output transformation path must end in '.txt'")
dir_output = os.path.dirname(args.output)
ph.create_directory(dir_output)
# --------------------------------Read Data--------------------------------
ph.print_title("Read Data")
fixed = st.Stack.from_filename(file_path=args.fixed,
file_path_mask=args.fixed_mask,
extract_slices=False)
moving = st.Stack.from_filename(file_path=args.moving,
file_path_mask=args.moving_mask,
extract_slices=False)
path_to_tmp_output = os.path.join(
DIR_TMP, ph.append_to_filename(os.path.basename(args.moving),
"_warped"))
# ---------------------------- Initialization ----------------------------
if args.initial_transform is None:
ph.print_title("Estimate initial transform using PCA")
if args.moving_mask is None or args.fixed_mask is None:
ph.print_warning("Fixed and moving masks are strongly recommended")
transform_initializer = tinit.TransformInitializer(
fixed=fixed,
moving=moving,
similarity_measure="NMI",
refine_pca_initializations=args.refine_pca,
)
transform_initializer.run()
transform_init_sitk = transform_initializer.get_transform_sitk()
else:
transform_init_sitk = sitkh.read_transform_sitk(args.initial_transform)
sitk.WriteTransform(transform_init_sitk, args.output)
# -------------------Register Reconstruction to Template-------------------
ph.print_title("Registration")
if args.method == "RegAladin":
path_to_transform_regaladin = os.path.join(DIR_TMP,
"transform_regaladin.txt")
# Convert SimpleITK to RegAladin transform
cmd = "simplereg_transform -sitk2nreg %s %s" % (
args.output, path_to_transform_regaladin)
ph.execute_command(cmd, verbose=False)
# Run NiftyReg
cmd_args = ["reg_aladin"]
cmd_args.append("-ref '%s'" % args.fixed)
cmd_args.append("-flo '%s'" % args.moving)
cmd_args.append("-res '%s'" % path_to_tmp_output)
cmd_args.append("-inaff '%s'" % path_to_transform_regaladin)
cmd_args.append("-aff '%s'" % path_to_transform_regaladin)
cmd_args.append("-rigOnly")
cmd_args.append("-ln 2") # seems to perform better for spina bifida
cmd_args.append("-voff")
if args.fixed_mask is not None:
cmd_args.append("-rmask '%s'" % args.fixed_mask)
# To avoid error "0 correspondences between blocks were found" that can
# occur for some cases. Also, disable moving mask, as this would be ignored
# anyway
cmd_args.append("-noSym")
# if args.moving_mask is not None:
# cmd_args.append("-fmask '%s'" % args.moving_mask)
ph.print_info("Run Registration (RegAladin) ... ", newline=False)
ph.execute_command(" ".join(cmd_args), verbose=False)
print("done")
# Convert RegAladin to SimpleITK transform
cmd = "simplereg_transform -nreg2sitk '%s' '%s'" % (
path_to_transform_regaladin, args.output)
ph.execute_command(cmd, verbose=False)
else:
path_to_transform_flirt = os.path.join(DIR_TMP, "transform_flirt.txt")
# Convert SimpleITK into FLIRT transform
cmd = "simplereg_transform -sitk2flirt '%s' '%s' '%s' '%s'" % (
args.output, args.fixed, args.moving, path_to_transform_flirt)
ph.execute_command(cmd, verbose=False)
# Define search angle ranges for FLIRT in all three dimensions
search_angles = [
"-searchr%s -%d %d" % (x, 180, 180) for x in ["x", "y", "z"]
]
cmd_args = ["flirt"]
cmd_args.append("-in '%s'" % args.moving)
cmd_args.append("-ref '%s'" % args.fixed)
if args.initial_transform is not None:
cmd_args.append("-init '%s'" % path_to_transform_flirt)
cmd_args.append("-omat '%s'" % path_to_transform_flirt)
cmd_args.append("-out '%s'" % path_to_tmp_output)
cmd_args.append("-dof 6")
cmd_args.append((" ").join(search_angles))
if args.moving_mask is not None:
cmd_args.append("-inweight '%s'" % args.moving_mask)
if args.fixed_mask is not None:
cmd_args.append("-refweight '%s'" % args.fixed_mask)
ph.print_info("Run Registration (FLIRT) ... ", newline=False)
ph.execute_command(" ".join(cmd_args), verbose=False)
print("done")
# Convert FLIRT to SimpleITK transform
cmd = "simplereg_transform -flirt2sitk '%s' '%s' '%s' '%s'" % (
path_to_transform_flirt, args.fixed, args.moving, args.output)
ph.execute_command(cmd, verbose=False)
if args.dir_input_mc is not None:
ph.print_title("Update Motion-Correction Transformations")
transform_sitk = sitkh.read_transform_sitk(args.output, inverse=1)
if args.dir_input_mc.endswith("/"):
subdir_mc = args.dir_input_mc.split("/")[-2]
else:
subdir_mc = args.dir_input_mc.split("/")[-1]
dir_output_mc = os.path.join(dir_output, subdir_mc)
ph.create_directory(dir_output_mc, delete_files=True)
pattern = REGEX_FILENAMES + "[.]tfm"
p = re.compile(pattern)
trafos = [t for t in os.listdir(args.dir_input_mc) if p.match(t)]
for t in trafos:
path_to_input_transform = os.path.join(args.dir_input_mc, t)
path_to_output_transform = os.path.join(dir_output_mc, t)
t_sitk = sitkh.read_transform_sitk(path_to_input_transform)
t_sitk = sitkh.get_composite_sitk_affine_transform(
transform_sitk, t_sitk)
sitk.WriteTransform(t_sitk, path_to_output_transform)
ph.print_info("%d transformations written to '%s'" %
(len(trafos), dir_output_mc))
if args.verbose:
ph.show_niftis([args.fixed, path_to_tmp_output])
elapsed_time_total = ph.stop_timing(time_start)
# Summary
ph.print_title("Summary")
print("Computational Time: %s" % (elapsed_time_total))
return 0
def main():
time_start = ph.start_timing()
np.set_printoptions(precision=3)
input_parser = InputArgparser(
description="Run reconstruction pipeline including "
"(i) bias field correction, "
"(ii) volumetric reconstruction in subject space, "
"and (iii) volumetric reconstruction in template space.", )
input_parser.add_filenames(required=True)
input_parser.add_filenames_masks(required=True)
input_parser.add_target_stack(required=False)
input_parser.add_suffix_mask(default="''")
input_parser.add_dir_output(required=True)
input_parser.add_alpha(default=0.01)
input_parser.add_verbose(default=0)
input_parser.add_gestational_age(required=False)
input_parser.add_prefix_output(default="")
input_parser.add_search_angle(default=180)
input_parser.add_multiresolution(default=0)
input_parser.add_log_config(default=1)
input_parser.add_isotropic_resolution()
input_parser.add_reference()
input_parser.add_reference_mask()
input_parser.add_bias_field_correction(default=1)
input_parser.add_intensity_correction(default=1)
input_parser.add_iter_max(default=10)
input_parser.add_two_step_cycles(default=3)
input_parser.add_option(
option_string="--run-bias-field-correction",
type=int,
help="Turn on/off bias field correction. "
"If off, it is assumed that this step was already performed",
default=1)
input_parser.add_option(
option_string="--run-recon-subject-space",
type=int,
help="Turn on/off reconstruction in subject space. "
"If off, it is assumed that this step was already performed",
default=1)
input_parser.add_option(
option_string="--run-recon-template-space",
type=int,
help="Turn on/off reconstruction in template space. "
"If off, it is assumed that this step was already performed",
default=1)
input_parser.add_option(
option_string="--run-data-vs-simulated-data",
type=int,
help="Turn on/off comparison of data vs data simulated from the "
"obtained volumetric reconstruction. "
"If off, it is assumed that this step was already performed",
default=0)
input_parser.add_option(
option_string="--initial-transform",
type=str,
help="Set initial transform to be used for register_image.",
default=None)
input_parser.add_outlier_rejection(default=1)
input_parser.add_argument(
"--sda",
"-sda",
action='store_true',
help="If given, the volume is reconstructed using "
"Scattered Data Approximation (Vercauteren et al., 2006). "
"--alpha is considered the value for the standard deviation then. "
"Recommended value is, e.g., --alpha 0.8")
args = input_parser.parse_args()
input_parser.print_arguments(args)
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
filename_srr = "srr"
dir_output_preprocessing = os.path.join(args.dir_output,
"preprocessing_n4itk")
dir_output_recon_subject_space = os.path.join(args.dir_output,
"recon_subject_space")
dir_output_recon_template_space = os.path.join(args.dir_output,
"recon_template_space")
dir_output_data_vs_simulatd_data = os.path.join(args.dir_output,
"data_vs_simulated_data")
srr_subject = os.path.join(dir_output_recon_subject_space,
"%s_subject.nii.gz" % filename_srr)
srr_subject_mask = ph.append_to_filename(srr_subject, "_mask")
srr_template = os.path.join(dir_output_recon_template_space,
"%s_template.nii.gz" % filename_srr)
srr_template_mask = ph.append_to_filename(srr_template, "_mask")
trafo_template = os.path.join(dir_output_recon_template_space,
"registration_transform_sitk.txt")
if args.target_stack is None:
target_stack = args.filenames[0]
else:
target_stack = args.target_stack
if args.bias_field_correction and args.run_bias_field_correction:
for i, f in enumerate(args.filenames):
output = os.path.join(dir_output_preprocessing,
os.path.basename(f))
cmd_args = []
cmd_args.append("--filename %s" % f)
cmd_args.append("--filename-mask %s" % args.filenames_masks[i])
cmd_args.append("--output %s" % output)
# cmd_args.append("--verbose %d" % args.verbose)
cmd = "niftymic_correct_bias_field %s" % (" ").join(cmd_args)
time_start_bias = ph.start_timing()
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Bias field correction failed")
elapsed_time_bias = ph.stop_timing(time_start_bias)
filenames = [
os.path.join(dir_output_preprocessing, os.path.basename(f))
for f in args.filenames
]
elif args.bias_field_correction and not args.run_bias_field_correction:
elapsed_time_bias = ph.get_zero_time()
filenames = [
os.path.join(dir_output_preprocessing, os.path.basename(f))
for f in args.filenames
]
else:
elapsed_time_bias = ph.get_zero_time()
filenames = args.filenames
if args.run_recon_subject_space:
target_stack_index = args.filenames.index(target_stack)
cmd_args = []
cmd_args.append("--filenames %s" % (" ").join(filenames))
if args.filenames_masks is not None:
cmd_args.append("--filenames-masks %s" %
(" ").join(args.filenames_masks))
cmd_args.append("--multiresolution %d" % args.multiresolution)
cmd_args.append("--target-stack-index %d" % target_stack_index)
cmd_args.append("--output %s" % srr_subject)
cmd_args.append("--suffix-mask '%s'" % args.suffix_mask)
cmd_args.append("--intensity-correction %d" %
args.intensity_correction)
cmd_args.append("--alpha %s" % args.alpha)
cmd_args.append("--iter-max %d" % args.iter_max)
cmd_args.append("--two-step-cycles %d" % args.two_step_cycles)
cmd_args.append("--outlier-rejection %d" % args.outlier_rejection)
cmd_args.append("--verbose %d" % args.verbose)
if args.isotropic_resolution is not None:
cmd_args.append("--isotropic-resolution %f" %
args.isotropic_resolution)
if args.reference is not None:
cmd_args.append("--reference %s" % args.reference)
if args.reference_mask is not None:
cmd_args.append("--reference-mask %s" % args.reference_mask)
if args.sda:
cmd_args.append("--sda")
cmd = "niftymic_reconstruct_volume %s" % (" ").join(cmd_args)
time_start_volrec = ph.start_timing()
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Reconstruction in subject space failed")
# Compute SRR mask in subject space
# (Approximated using SDA within reconstruct_volume)
if 0:
dir_motion_correction = os.path.join(
dir_output_recon_subject_space, "motion_correction")
cmd_args = ["niftymic_reconstruct_volume_from_slices"]
cmd_args.append("--filenames %s" % " ".join(args.filenames_masks))
cmd_args.append("--dir-input-mc %s" % dir_motion_correction)
cmd_args.append("--output %s" % srr_subject_mask)
cmd_args.append("--reconstruction-space %s" % srr_subject)
cmd_args.append("--suffix-mask '%s'" % args.suffix_mask)
cmd_args.append("--mask")
if args.sda:
cmd_args.append("--sda")
cmd_args.append("--alpha 1")
else:
cmd_args.append("--alpha 0.1")
cmd_args.append("--iter-max 5")
cmd = (" ").join(cmd_args)
ph.execute_command(cmd)
elapsed_time_volrec = ph.stop_timing(time_start_volrec)
else:
elapsed_time_volrec = ph.get_zero_time()
if args.run_recon_template_space:
if args.gestational_age is None:
template_stack_estimator = \
tse.TemplateStackEstimator.from_mask(srr_subject_mask)
gestational_age = template_stack_estimator.get_estimated_gw()
ph.print_info("Estimated gestational age: %d" % gestational_age)
else:
gestational_age = args.gestational_age
template = os.path.join(DIR_TEMPLATES,
"STA%d.nii.gz" % gestational_age)
template_mask = os.path.join(DIR_TEMPLATES,
"STA%d_mask.nii.gz" % gestational_age)
cmd_args = []
cmd_args.append("--fixed %s" % template)
cmd_args.append("--moving %s" % srr_subject)
cmd_args.append("--fixed-mask %s" % template_mask)
cmd_args.append("--moving-mask %s" % srr_subject_mask)
cmd_args.append(
"--dir-input-mc %s" %
os.path.join(dir_output_recon_subject_space, "motion_correction"))
cmd_args.append("--output %s" % trafo_template)
cmd_args.append("--verbose %s" % args.verbose)
if args.initial_transform is not None:
cmd_args.append("--initial-transform %s" % args.initial_transform)
cmd_args.append("--use-flirt 0")
cmd_args.append("--test-ap-flip 0")
cmd = "niftymic_register_image %s" % (" ").join(cmd_args)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Registration to template space failed")
# reconstruct volume in template space
# pattern = "[a-zA-Z0-9_.]+(ResamplingToTemplateSpace.nii.gz)"
# p = re.compile(pattern)
# reconstruction_space = [
# os.path.join(dir_output_recon_template_space, p.match(f).group(0))
# for f in os.listdir(dir_output_recon_template_space)
# if p.match(f)][0]
dir_input_mc = os.path.join(dir_output_recon_template_space,
"motion_correction")
cmd_args = ["niftymic_reconstruct_volume_from_slices"]
cmd_args.append("--filenames %s" % (" ").join(filenames))
cmd_args.append("--dir-input-mc %s" % dir_input_mc)
cmd_args.append("--output %s" % srr_template)
cmd_args.append("--reconstruction-space %s" % template)
cmd_args.append("--iter-max %d" % args.iter_max)
cmd_args.append("--alpha %s" % args.alpha)
cmd_args.append("--suffix-mask '%s'" % args.suffix_mask)
cmd_args.append("--verbose %s" % args.verbose)
if args.sda:
cmd_args.append("--sda")
cmd = (" ").join(cmd_args)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Reconstruction in template space failed")
# Compute SRR mask in template space
if 1:
dir_motion_correction = os.path.join(
dir_output_recon_template_space, "motion_correction")
cmd_args = ["niftymic_reconstruct_volume_from_slices"]
cmd_args.append("--filenames %s" % " ".join(args.filenames_masks))
cmd_args.append("--dir-input-mc %s" % dir_motion_correction)
cmd_args.append("--output %s" % srr_template_mask)
cmd_args.append("--reconstruction-space %s" % srr_template)
cmd_args.append("--suffix-mask '%s'" % args.suffix_mask)
cmd_args.append("--mask")
if args.sda:
cmd_args.append("--sda")
cmd_args.append("--alpha 1")
else:
cmd_args.append("--alpha 0.1")
cmd_args.append("--iter-max 5")
cmd = (" ").join(cmd_args)
ph.execute_command(cmd)
# Copy SRR to output directory
output = "%sSRR_Stacks%d.nii.gz" % (args.prefix_output,
len(args.filenames))
path_to_output = os.path.join(args.dir_output, output)
cmd = "cp -p %s %s" % (srr_template, path_to_output)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Copy of SRR to output directory failed")
# Multiply template mask with reconstruction
cmd_args = ["niftymic_multiply"]
fnames = [
srr_template,
srr_template_mask,
]
output_masked = "Masked_%s" % output
path_to_output_masked = os.path.join(args.dir_output, output_masked)
cmd_args.append("--filenames %s" % " ".join(fnames))
cmd_args.append("--output %s" % path_to_output_masked)
cmd = (" ").join(cmd_args)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("SRR brain masking failed")
else:
elapsed_time_template = ph.get_zero_time()
if args.run_data_vs_simulated_data:
dir_input_mc = os.path.join(dir_output_recon_template_space,
"motion_correction")
# Get simulated/projected slices
cmd_args = []
cmd_args.append("--filenames %s" % (" ").join(filenames))
if args.filenames_masks is not None:
cmd_args.append("--filenames-masks %s" %
(" ").join(args.filenames_masks))
cmd_args.append("--dir-input-mc %s" % dir_input_mc)
cmd_args.append("--dir-output %s" % dir_output_data_vs_simulatd_data)
cmd_args.append("--reconstruction %s" % srr_template)
cmd_args.append("--copy-data 1")
cmd_args.append("--suffix-mask '%s'" % args.suffix_mask)
# cmd_args.append("--verbose %s" % args.verbose)
exe = os.path.abspath(simulate_stacks_from_reconstruction.__file__)
cmd = "python %s %s" % (exe, (" ").join(cmd_args))
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("SRR slice projections failed")
filenames_simulated = [
os.path.join(dir_output_data_vs_simulatd_data, os.path.basename(f))
for f in filenames
]
dir_output_evaluation = os.path.join(dir_output_data_vs_simulatd_data,
"evaluation")
dir_output_figures = os.path.join(dir_output_data_vs_simulatd_data,
"figures")
dir_output_side_by_side = os.path.join(dir_output_figures,
"side-by-side")
# Evaluate slice similarities to ground truth
cmd_args = []
cmd_args.append("--filenames %s" % (" ").join(filenames_simulated))
if args.filenames_masks is not None:
cmd_args.append("--filenames-masks %s" %
(" ").join(args.filenames_masks))
cmd_args.append("--suffix-mask '%s'" % args.suffix_mask)
cmd_args.append("--measures NCC SSIM")
cmd_args.append("--dir-output %s" % dir_output_evaluation)
exe = os.path.abspath(evaluate_simulated_stack_similarity.__file__)
cmd = "python %s %s" % (exe, (" ").join(cmd_args))
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Evaluation of slice similarities failed")
# Generate figures showing the quantitative comparison
cmd_args = []
cmd_args.append("--dir-input %s" % dir_output_evaluation)
cmd_args.append("--dir-output %s" % dir_output_figures)
exe = os.path.abspath(
show_evaluated_simulated_stack_similarity.__file__)
cmd = "python %s %s" % (exe, (" ").join(cmd_args))
exit_code = ph.execute_command(cmd)
if exit_code != 0:
ph.print_warning("Visualization of slice similarities failed")
# Generate pdfs showing all the side-by-side comparisons
cmd_args = []
cmd_args.append("--filenames %s" % (" ").join(filenames_simulated))
cmd_args.append("--dir-output %s" % dir_output_side_by_side)
exe = os.path.abspath(
export_side_by_side_simulated_vs_original_slice_comparison.__file__
)
cmd = "python %s %s" % (exe, (" ").join(cmd_args))
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Generation of PDF overview failed")
ph.print_title("Summary")
print("Computational Time for Bias Field Correction: %s" %
elapsed_time_bias)
print("Computational Time for Volumetric Reconstruction: %s" %
elapsed_time_volrec)
print("Computational Time for Pipeline: %s" % ph.stop_timing(time_start))
return 0
def main():
time_start = ph.start_timing()
# Read input
parser = argparse.ArgumentParser(
description="Perform rigid registration using landmarks",
prog=None,
epilog="Author: Michael Ebner ([email protected])",
)
parser.add_argument(
"-f",
"--fixed",
help="Path to fixed image landmarks.",
type=str,
required=1,
)
parser.add_argument(
"-m",
"--moving",
help="Path to moving image landmarks.",
type=str,
required=1,
)
parser.add_argument(
"-o",
"--output",
help="Path for obtained SimpleITK registration transform (.txt)",
type=str,
required=1,
)
parser.add_argument(
"-v",
"--verbose",
help="Turn on/off verbose output",
type=int,
required=0,
default=0,
)
parser.add_argument(
"--pca",
"-pca",
action="store_true",
help="If given, principal component analysis (PCA) is used "
"to test various initializations for the point based registrations.")
args = parser.parse_args()
landmarks_fixed_nda = dr.DataReader.read_landmarks(args.fixed)
landmarks_moving_nda = dr.DataReader.read_landmarks(args.moving)
if args.pca:
ph.print_subtitle("Use PCA to initialize registrations")
pca_fixed = pca.PrincipalComponentAnalysis(landmarks_fixed_nda)
pca_fixed.run()
eigvec_fixed = pca_fixed.get_eigvec()
mean_fixed = pca_fixed.get_mean()
pca_moving = pca.PrincipalComponentAnalysis(landmarks_moving_nda)
pca_moving.run()
eigvec_moving = pca_moving.get_eigvec()
mean_moving = pca_moving.get_mean()
# test different initializations based on eigenvector orientations
orientations = [
[1, 1],
[1, -1],
[-1, 1],
[-1, -1],
]
error = np.inf
for i_o, orientation in enumerate(orientations):
eigvec_moving_o = np.array(eigvec_moving)
eigvec_moving_o[:, 0] *= orientation[0]
eigvec_moving_o[:, 1] *= orientation[1]
# get right-handed coordinate system
cross = np.cross(eigvec_moving_o[:, 0], eigvec_moving_o[:, 1])
eigvec_moving_o[:, 2] = cross
# transformation to align fixed with moving eigenbasis
R = eigvec_moving_o.dot(eigvec_fixed.transpose())
t = mean_moving - R.dot(mean_fixed)
ph.print_info(
"Registration based on PCA eigenvector initialization "
"%d/%d ... " % (i_o + 1, len(orientations)),
newline=False)
reg = pycpd.rigid_registration(
**{
"Y": landmarks_fixed_nda,
"X": landmarks_moving_nda,
"max_iterations": 100,
"R": R,
"t": t,
})
reg.register()
params = reg.get_registration_parameters()
scale, R, t = params
error_o = reg.err
print("done. Error: %.2f" % error_o)
if error_o < error:
error = error_o
rotation_matrix_nda = np.array(R)
translation_nda = np.array(t)
ph.print_info("Currently best estimate")
else:
reg = pycpd.rigid_registration(
**{
"Y": landmarks_fixed_nda,
"X": landmarks_moving_nda,
"max_iterations": 100,
})
if args.verbose:
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
callback = partial(visualize, ax=ax)
else:
callback = None
ph.print_info("Registration ... ", newline=False)
reg.register(callback)
if args.verbose:
plt.show(block=False)
# reg.register()
scale, R, t = reg.get_registration_parameters()
rotation_matrix_nda = R
translation_nda = t
print("done. Error: %.2f" % reg.err)
rigid_transform_sitk = sitk.Euler3DTransform()
rigid_transform_sitk.SetMatrix(rotation_matrix_nda.flatten())
rigid_transform_sitk.SetTranslation(translation_nda)
dw.DataWriter.write_transform(rigid_transform_sitk,
args.output,
verbose=True)
elapsed_time_total = ph.stop_timing(time_start)
ph.print_info("Computational Time: %s" % elapsed_time_total)
return 0
def main():
time_start = ph.start_timing()
# Set print options for numpy
np.set_printoptions(precision=3)
input_parser = InputArgparser(
description="Volumetric MRI reconstruction framework to reconstruct "
"an isotropic, high-resolution 3D volume from multiple stacks of 2D "
"slices with motion correction. The resolution of the computed "
"Super-Resolution Reconstruction (SRR) is given by the in-plane "
"spacing of the selected target stack. A region of interest can be "
"specified by providing a mask for the selected target stack. Only "
"this region will then be reconstructed by the SRR algorithm which "
"can substantially reduce the computational time.",
)
input_parser.add_filenames(required=True)
input_parser.add_filenames_masks()
input_parser.add_output(required=True)
input_parser.add_suffix_mask(default="_mask")
input_parser.add_target_stack(default=None)
input_parser.add_search_angle(default=45)
input_parser.add_multiresolution(default=0)
input_parser.add_shrink_factors(default=[3, 2, 1])
input_parser.add_smoothing_sigmas(default=[1.5, 1, 0])
input_parser.add_sigma(default=1)
input_parser.add_reconstruction_type(default="TK1L2")
input_parser.add_iterations(default=15)
input_parser.add_alpha(default=0.015)
input_parser.add_alpha_first(default=0.2)
input_parser.add_iter_max(default=10)
input_parser.add_iter_max_first(default=5)
input_parser.add_dilation_radius(default=3)
input_parser.add_extra_frame_target(default=10)
input_parser.add_bias_field_correction(default=0)
input_parser.add_intensity_correction(default=1)
input_parser.add_isotropic_resolution(default=1)
input_parser.add_log_config(default=1)
input_parser.add_subfolder_motion_correction()
input_parser.add_write_motion_correction(default=1)
input_parser.add_verbose(default=0)
input_parser.add_two_step_cycles(default=3)
input_parser.add_use_masks_srr(default=0)
input_parser.add_boundary_stacks(default=[10, 10, 0])
input_parser.add_metric(default="Correlation")
input_parser.add_metric_radius(default=10)
input_parser.add_reference()
input_parser.add_reference_mask()
input_parser.add_outlier_rejection(default=1)
input_parser.add_threshold_first(default=0.5)
input_parser.add_threshold(default=0.8)
input_parser.add_interleave(default=3)
input_parser.add_slice_thicknesses(default=None)
input_parser.add_viewer(default="itksnap")
input_parser.add_v2v_method(default="RegAladin")
input_parser.add_argument(
"--v2v-robust", "-v2v-robust",
action='store_true',
help="If given, a more robust volume-to-volume registration step is "
"performed, i.e. four rigid registrations are performed using four "
"rigid transform initializations based on "
"principal component alignment of associated masks."
)
input_parser.add_argument(
"--s2v-hierarchical", "-s2v-hierarchical",
action='store_true',
help="If given, a hierarchical approach for the first slice-to-volume "
"registration cycle is used, i.e. sub-packages defined by the "
"specified interleave (--interleave) are registered until each "
"slice is registered independently."
)
input_parser.add_argument(
"--sda", "-sda",
action='store_true',
help="If given, the volumetric reconstructions are performed using "
"Scattered Data Approximation (Vercauteren et al., 2006). "
"'alpha' is considered the final 'sigma' for the "
"iterative adjustment. "
"Recommended value is, e.g., --alpha 0.8"
)
input_parser.add_option(
option_string="--transforms-history",
type=int,
help="Write entire history of applied slice motion correction "
"transformations to motion correction output directory",
default=0,
)
args = input_parser.parse_args()
input_parser.print_arguments(args)
rejection_measure = "NCC"
threshold_v2v = -2 # 0.3
debug = False
if args.v2v_method not in V2V_METHOD_OPTIONS:
raise ValueError("v2v-method must be in {%s}" % (
", ".join(V2V_METHOD_OPTIONS)))
if np.alltrue([not args.output.endswith(t) for t in ALLOWED_EXTENSIONS]):
raise ValueError(
"output filename invalid; allowed extensions are: %s" %
", ".join(ALLOWED_EXTENSIONS))
if args.alpha_first < args.alpha and not args.sda:
raise ValueError("It must hold alpha-first >= alpha")
if args.threshold_first > args.threshold:
raise ValueError("It must hold threshold-first <= threshold")
dir_output = os.path.dirname(args.output)
ph.create_directory(dir_output)
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
# --------------------------------Read Data--------------------------------
ph.print_title("Read Data")
data_reader = dr.MultipleImagesReader(
file_paths=args.filenames,
file_paths_masks=args.filenames_masks,
suffix_mask=args.suffix_mask,
stacks_slice_thicknesses=args.slice_thicknesses,
)
if len(args.boundary_stacks) is not 3:
raise IOError(
"Provide exactly three values for '--boundary-stacks' to define "
"cropping in i-, j-, and k-dimension of the input stacks")
data_reader.read_data()
stacks = data_reader.get_data()
ph.print_info("%d input stacks read for further processing" % len(stacks))
if all(s.is_unity_mask() is True for s in stacks):
ph.print_warning("No mask is provided! "
"Generated reconstruction space may be very big!")
ph.print_warning("Consider using a mask to speed up computations")
# args.extra_frame_target = 0
# ph.wrint_warning("Overwritten: extra-frame-target set to 0")
# Specify target stack for intensity correction and reconstruction space
if args.target_stack is None:
target_stack_index = 0
else:
try:
target_stack_index = args.filenames.index(args.target_stack)
except ValueError as e:
raise ValueError(
"--target-stack must correspond to an image as provided by "
"--filenames")
# ---------------------------Data Preprocessing---------------------------
ph.print_title("Data Preprocessing")
segmentation_propagator = segprop.SegmentationPropagation(
# registration_method=regflirt.FLIRT(use_verbose=args.verbose),
# registration_method=niftyreg.RegAladin(use_verbose=False),
dilation_radius=args.dilation_radius,
dilation_kernel="Ball",
)
data_preprocessing = dp.DataPreprocessing(
stacks=stacks,
segmentation_propagator=segmentation_propagator,
use_cropping_to_mask=True,
use_N4BiasFieldCorrector=args.bias_field_correction,
target_stack_index=target_stack_index,
boundary_i=args.boundary_stacks[0],
boundary_j=args.boundary_stacks[1],
boundary_k=args.boundary_stacks[2],
unit="mm",
)
data_preprocessing.run()
time_data_preprocessing = data_preprocessing.get_computational_time()
# Get preprocessed stacks
stacks = data_preprocessing.get_preprocessed_stacks()
# Define reference/target stack for registration and reconstruction
if args.reference is not None:
reference = st.Stack.from_filename(
file_path=args.reference,
file_path_mask=args.reference_mask,
extract_slices=False)
else:
reference = st.Stack.from_stack(stacks[target_stack_index])
# ------------------------Volume-to-Volume Registration--------------------
if len(stacks) > 1:
if args.v2v_method == "FLIRT":
# Define search angle ranges for FLIRT in all three dimensions
search_angles = ["-searchr%s -%d %d" %
(x, args.search_angle, args.search_angle)
for x in ["x", "y", "z"]]
options = (" ").join(search_angles)
# options += " -noresample"
vol_registration = regflirt.FLIRT(
registration_type="Rigid",
use_fixed_mask=True,
use_moving_mask=True,
options=options,
use_verbose=False,
)
else:
vol_registration = niftyreg.RegAladin(
registration_type="Rigid",
use_fixed_mask=True,
use_moving_mask=True,
# options="-ln 2 -voff",
use_verbose=False,
)
v2vreg = pipeline.VolumeToVolumeRegistration(
stacks=stacks,
reference=reference,
registration_method=vol_registration,
verbose=debug,
robust=args.v2v_robust,
)
v2vreg.run()
stacks = v2vreg.get_stacks()
time_registration = v2vreg.get_computational_time()
else:
time_registration = ph.get_zero_time()
# ---------------------------Intensity Correction--------------------------
if args.intensity_correction:
ph.print_title("Intensity Correction")
intensity_corrector = ic.IntensityCorrection()
intensity_corrector.use_individual_slice_correction(False)
intensity_corrector.use_reference_mask(True)
intensity_corrector.use_stack_mask(True)
intensity_corrector.use_verbose(False)
for i, stack in enumerate(stacks):
if i == target_stack_index:
ph.print_info("Stack %d (%s): Reference image. Skipped." % (
i + 1, stack.get_filename()))
continue
else:
ph.print_info("Stack %d (%s): Intensity Correction ... " % (
i + 1, stack.get_filename()), newline=False)
intensity_corrector.set_stack(stack)
intensity_corrector.set_reference(
stacks[target_stack_index].get_resampled_stack(
resampling_grid=stack.sitk,
interpolator="NearestNeighbor",
))
intensity_corrector.run_linear_intensity_correction()
stacks[i] = intensity_corrector.get_intensity_corrected_stack()
print("done (c1 = %g) " %
intensity_corrector.get_intensity_correction_coefficients())
# ---------------------------Create first volume---------------------------
time_tmp = ph.start_timing()
# Isotropic resampling to define HR target space
ph.print_title("Reconstruction Space Generation")
HR_volume = reference.get_isotropically_resampled_stack(
resolution=args.isotropic_resolution)
ph.print_info(
"Isotropic reconstruction space with %g mm resolution is created" %
HR_volume.sitk.GetSpacing()[0])
if args.reference is None:
# Create joint image mask in target space
joint_image_mask_builder = imb.JointImageMaskBuilder(
stacks=stacks,
target=HR_volume,
dilation_radius=1,
)
joint_image_mask_builder.run()
HR_volume = joint_image_mask_builder.get_stack()
ph.print_info(
"Isotropic reconstruction space is centered around "
"joint stack masks. ")
# Crop to space defined by mask (plus extra margin)
HR_volume = HR_volume.get_cropped_stack_based_on_mask(
boundary_i=args.extra_frame_target,
boundary_j=args.extra_frame_target,
boundary_k=args.extra_frame_target,
unit="mm",
)
# Create first volume
# If outlier rejection is activated, eliminate obvious outliers early
# from stack and re-run SDA to get initial volume without them
ph.print_title("First Estimate of HR Volume")
if args.outlier_rejection and threshold_v2v > -1:
ph.print_subtitle("SDA Approximation")
SDA = sda.ScatteredDataApproximation(
stacks, HR_volume, sigma=args.sigma)
SDA.run()
HR_volume = SDA.get_reconstruction()
# Identify and reject outliers
ph.print_subtitle("Eliminate slice outliers (%s < %g)" % (
rejection_measure, threshold_v2v))
outlier_rejector = outre.OutlierRejector(
stacks=stacks,
reference=HR_volume,
threshold=threshold_v2v,
measure=rejection_measure,
verbose=True,
)
outlier_rejector.run()
stacks = outlier_rejector.get_stacks()
ph.print_subtitle("SDA Approximation Image")
SDA = sda.ScatteredDataApproximation(
stacks, HR_volume, sigma=args.sigma)
SDA.run()
HR_volume = SDA.get_reconstruction()
ph.print_subtitle("SDA Approximation Image Mask")
SDA = sda.ScatteredDataApproximation(
stacks, HR_volume, sigma=args.sigma, sda_mask=True)
SDA.run()
# HR volume contains updated mask based on SDA
HR_volume = SDA.get_reconstruction()
HR_volume.set_filename(SDA.get_setting_specific_filename())
time_reconstruction = ph.stop_timing(time_tmp)
if args.verbose:
tmp = list(stacks)
tmp.insert(0, HR_volume)
sitkh.show_stacks(tmp, segmentation=HR_volume, viewer=args.viewer)
# -----------Two-step Slice-to-Volume Registration-Reconstruction----------
if args.two_step_cycles > 0:
# Slice-to-volume registration set-up
if args.metric == "ANTSNeighborhoodCorrelation":
metric_params = {"radius": args.metric_radius}
else:
metric_params = None
registration = regsitk.SimpleItkRegistration(
moving=HR_volume,
use_fixed_mask=True,
use_moving_mask=True,
interpolator="Linear",
metric=args.metric,
metric_params=metric_params,
use_multiresolution_framework=args.multiresolution,
shrink_factors=args.shrink_factors,
smoothing_sigmas=args.smoothing_sigmas,
initializer_type="SelfGEOMETRY",
optimizer="ConjugateGradientLineSearch",
optimizer_params={
"learningRate": 1,
"numberOfIterations": 100,
"lineSearchUpperLimit": 2,
},
scales_estimator="Jacobian",
use_verbose=debug,
)
# Volumetric reconstruction set-up
if args.sda:
recon_method = sda.ScatteredDataApproximation(
stacks,
HR_volume,
sigma=args.sigma,
use_masks=args.use_masks_srr,
)
alpha_range = [args.sigma, args.alpha]
else:
recon_method = tk.TikhonovSolver(
stacks=stacks,
reconstruction=HR_volume,
reg_type="TK1",
minimizer="lsmr",
alpha=args.alpha_first,
iter_max=np.min([args.iter_max_first, args.iter_max]),
verbose=True,
use_masks=args.use_masks_srr,
)
alpha_range = [args.alpha_first, args.alpha]
# Define the regularization parameters for the individual
# reconstruction steps in the two-step cycles
alphas = np.linspace(
alpha_range[0], alpha_range[1], args.two_step_cycles)
# Define outlier rejection threshold after each S2V-reg step
thresholds = np.linspace(
args.threshold_first, args.threshold, args.two_step_cycles)
two_step_s2v_reg_recon = \
pipeline.TwoStepSliceToVolumeRegistrationReconstruction(
stacks=stacks,
reference=HR_volume,
registration_method=registration,
reconstruction_method=recon_method,
cycles=args.two_step_cycles,
alphas=alphas[0:args.two_step_cycles - 1],
outlier_rejection=args.outlier_rejection,
threshold_measure=rejection_measure,
thresholds=thresholds,
interleave=args.interleave,
viewer=args.viewer,
verbose=args.verbose,
use_hierarchical_registration=args.s2v_hierarchical,
)
two_step_s2v_reg_recon.run()
HR_volume_iterations = \
two_step_s2v_reg_recon.get_iterative_reconstructions()
time_registration += \
two_step_s2v_reg_recon.get_computational_time_registration()
time_reconstruction += \
two_step_s2v_reg_recon.get_computational_time_reconstruction()
stacks = two_step_s2v_reg_recon.get_stacks()
# no two-step s2v-registration/reconstruction iterations
else:
HR_volume_iterations = []
# Write motion-correction results
ph.print_title("Write Motion Correction Results")
if args.write_motion_correction:
dir_output_mc = os.path.join(
dir_output, args.subfolder_motion_correction)
ph.clear_directory(dir_output_mc)
for stack in stacks:
stack.write(
dir_output_mc,
write_stack=False,
write_mask=False,
write_slices=False,
write_transforms=True,
write_transforms_history=args.transforms_history,
)
if args.outlier_rejection:
deleted_slices_dic = {}
for i, stack in enumerate(stacks):
deleted_slices = stack.get_deleted_slice_numbers()
deleted_slices_dic[stack.get_filename()] = deleted_slices
# check whether any stack was removed entirely
stacks0 = data_preprocessing.get_preprocessed_stacks()
if len(stacks) != len(stacks0):
stacks_remain = [s.get_filename() for s in stacks]
for stack in stacks0:
if stack.get_filename() in stacks_remain:
continue
# add info that all slices of this stack were rejected
deleted_slices = [
slice.get_slice_number()
for slice in stack.get_slices()
]
deleted_slices_dic[stack.get_filename()] = deleted_slices
ph.print_info(
"All slices of stack '%s' were rejected entirely. "
"Information added." % stack.get_filename())
ph.write_dictionary_to_json(
deleted_slices_dic,
os.path.join(
dir_output,
args.subfolder_motion_correction,
"rejected_slices.json"
)
)
# ---------------------Final Volumetric Reconstruction---------------------
ph.print_title("Final Volumetric Reconstruction")
if args.sda:
recon_method = sda.ScatteredDataApproximation(
stacks,
HR_volume,
sigma=args.alpha,
use_masks=args.use_masks_srr,
)
else:
if args.reconstruction_type in ["TVL2", "HuberL2"]:
recon_method = pd.PrimalDualSolver(
stacks=stacks,
reconstruction=HR_volume,
reg_type="TV" if args.reconstruction_type == "TVL2" else "huber",
iterations=args.iterations,
use_masks=args.use_masks_srr,
)
else:
recon_method = tk.TikhonovSolver(
stacks=stacks,
reconstruction=HR_volume,
reg_type="TK1" if args.reconstruction_type == "TK1L2" else "TK0",
use_masks=args.use_masks_srr,
)
recon_method.set_alpha(args.alpha)
recon_method.set_iter_max(args.iter_max)
recon_method.set_verbose(True)
recon_method.run()
time_reconstruction += recon_method.get_computational_time()
HR_volume_final = recon_method.get_reconstruction()
ph.print_subtitle("Final SDA Approximation Image Mask")
SDA = sda.ScatteredDataApproximation(
stacks, HR_volume_final, sigma=args.sigma, sda_mask=True)
SDA.run()
# HR volume contains updated mask based on SDA
HR_volume_final = SDA.get_reconstruction()
time_reconstruction += SDA.get_computational_time()
elapsed_time_total = ph.stop_timing(time_start)
# Write SRR result
filename = recon_method.get_setting_specific_filename()
HR_volume_final.set_filename(filename)
dw.DataWriter.write_image(
HR_volume_final.sitk,
args.output,
description=filename)
dw.DataWriter.write_mask(
HR_volume_final.sitk_mask,
ph.append_to_filename(args.output, "_mask"),
description=SDA.get_setting_specific_filename())
HR_volume_iterations.insert(0, HR_volume_final)
for stack in stacks:
HR_volume_iterations.append(stack)
if args.verbose:
sitkh.show_stacks(
HR_volume_iterations,
segmentation=HR_volume_final,
viewer=args.viewer,
)
# Summary
ph.print_title("Summary")
exe_file_info = os.path.basename(os.path.abspath(__file__)).split(".")[0]
print("%s | Computational Time for Data Preprocessing: %s" %
(exe_file_info, time_data_preprocessing))
print("%s | Computational Time for Registrations: %s" %
(exe_file_info, time_registration))
print("%s | Computational Time for Reconstructions: %s" %
(exe_file_info, time_reconstruction))
print("%s | Computational Time for Entire Reconstruction Pipeline: %s" %
(exe_file_info, elapsed_time_total))
ph.print_line_separator()
return 0
def main():
time_start = ph.start_timing()
# Set print options for numpy
np.set_printoptions(precision=3)
# Read input
input_parser = InputArgparser(
description="Volumetric MRI reconstruction framework to reconstruct "
"an isotropic, high-resolution 3D volume from multiple stacks of 2D "
"slices with motion correction. The resolution of the computed "
"Super-Resolution Reconstruction (SRR) is given by the in-plane "
"spacing of the selected target stack. A region of interest can be "
"specified by providing a mask for the selected target stack. Only "
"this region will then be reconstructed by the SRR algorithm which "
"can substantially reduce the computational time.", )
input_parser.add_dir_input()
input_parser.add_filenames()
input_parser.add_dir_output(required=True)
input_parser.add_suffix_mask(default="_mask")
input_parser.add_target_stack_index(default=0)
input_parser.add_search_angle(default=90)
input_parser.add_multiresolution(default=0)
input_parser.add_shrink_factors(default=[2, 1])
input_parser.add_smoothing_sigmas(default=[1, 0])
input_parser.add_sigma(default=0.9)
input_parser.add_reconstruction_type(default="TK1L2")
input_parser.add_iterations(default=15)
input_parser.add_alpha(default=0.02)
input_parser.add_alpha_first(default=0.05)
input_parser.add_iter_max(default=10)
input_parser.add_iter_max_first(default=5)
input_parser.add_dilation_radius(default=3)
input_parser.add_extra_frame_target(default=10)
input_parser.add_bias_field_correction(default=0)
input_parser.add_intensity_correction(default=0)
input_parser.add_isotropic_resolution(default=None)
input_parser.add_log_script_execution(default=1)
input_parser.add_subfolder_motion_correction()
input_parser.add_provide_comparison(default=0)
input_parser.add_subfolder_comparison()
input_parser.add_write_motion_correction(default=1)
input_parser.add_verbose(default=0)
input_parser.add_two_step_cycles(default=3)
input_parser.add_use_masks_srr(default=1)
input_parser.add_boundary_stacks(default=[10, 10, 0])
input_parser.add_reference()
input_parser.add_reference_mask()
args = input_parser.parse_args()
input_parser.print_arguments(args)
# Write script execution call
if args.log_script_execution:
input_parser.write_performed_script_execution(
os.path.abspath(__file__))
# Use FLIRT for volume-to-volume reg. step. Otherwise, RegAladin is used.
use_flirt_for_v2v_registration = True
# --------------------------------Read Data--------------------------------
ph.print_title("Read Data")
# Neither '--dir-input' nor '--filenames' was specified
if args.filenames is not None and args.dir_input is not None:
raise IOError("Provide input by either '--dir-input' or '--filenames' "
"but not both together")
# '--dir-input' specified
elif args.dir_input is not None:
data_reader = dr.ImageDirectoryReader(args.dir_input,
suffix_mask=args.suffix_mask)
# '--filenames' specified
elif args.filenames is not None:
data_reader = dr.MultipleImagesReader(args.filenames,
suffix_mask=args.suffix_mask)
else:
raise IOError("Provide input by either '--dir-input' or '--filenames'")
if len(args.boundary_stacks) is not 3:
raise IOError(
"Provide exactly three values for '--boundary-stacks' to define "
"cropping in i-, j-, and k-dimension of the input stacks")
data_reader.read_data()
stacks = data_reader.get_data()
ph.print_info("%d input stacks read for further processing" % len(stacks))
if all(s.is_unity_mask() is True for s in stacks):
ph.print_warning("No mask is provided! "
"Generated reconstruction space may be very big!")
# ---------------------------Data Preprocessing---------------------------
ph.print_title("Data Preprocessing")
segmentation_propagator = segprop.SegmentationPropagation(
# registration_method=regflirt.FLIRT(use_verbose=args.verbose),
dilation_radius=args.dilation_radius,
dilation_kernel="Ball",
)
data_preprocessing = dp.DataPreprocessing(
stacks=stacks,
segmentation_propagator=segmentation_propagator,
use_cropping_to_mask=True,
use_N4BiasFieldCorrector=args.bias_field_correction,
use_intensity_correction=args.intensity_correction,
target_stack_index=args.target_stack_index,
boundary_i=args.boundary_stacks[0],
boundary_j=args.boundary_stacks[1],
boundary_k=args.boundary_stacks[2],
unit="mm",
)
data_preprocessing.run()
time_data_preprocessing = data_preprocessing.get_computational_time()
# Get preprocessed stacks
stacks = data_preprocessing.get_preprocessed_stacks()
# Define reference/target stack for registration and reconstruction
if args.reference is not None:
reference = st.Stack.from_filename(file_path=args.reference,
file_path_mask=args.reference_mask,
extract_slices=False)
else:
reference = st.Stack.from_stack(stacks[args.target_stack_index])
# ------------------------Volume-to-Volume Registration--------------------
if args.two_step_cycles > 0:
# Define search angle ranges for FLIRT in all three dimensions
search_angles = [
"-searchr%s -%d %d" % (x, args.search_angle, args.search_angle)
for x in ["x", "y", "z"]
]
search_angles = (" ").join(search_angles)
if use_flirt_for_v2v_registration:
vol_registration = regflirt.FLIRT(
registration_type="Rigid",
use_fixed_mask=True,
use_moving_mask=True,
options=search_angles,
use_verbose=False,
)
else:
vol_registration = niftyreg.RegAladin(
registration_type="Rigid",
use_fixed_mask=True,
use_moving_mask=True,
use_verbose=False,
)
v2vreg = pipeline.VolumeToVolumeRegistration(
stacks=stacks,
reference=reference,
registration_method=vol_registration,
verbose=args.verbose,
)
v2vreg.run()
stacks = v2vreg.get_stacks()
time_registration = v2vreg.get_computational_time()
else:
time_registration = ph.get_zero_time()
# ---------------------------Create first volume---------------------------
time_tmp = ph.start_timing()
# Isotropic resampling to define HR target space
ph.print_title("Reconstruction Space Generation")
HR_volume = reference.get_isotropically_resampled_stack(
resolution=args.isotropic_resolution)
ph.print_info(
"Isotropic reconstruction space with %g mm resolution is created" %
HR_volume.sitk.GetSpacing()[0])
if args.reference is None:
# Create joint image mask in target space
joint_image_mask_builder = imb.JointImageMaskBuilder(
stacks=stacks,
target=HR_volume,
dilation_radius=1,
)
joint_image_mask_builder.run()
HR_volume = joint_image_mask_builder.get_stack()
ph.print_info("Isotropic reconstruction space is centered around "
"joint stack masks. ")
# Crop to space defined by mask (plus extra margin)
HR_volume = HR_volume.get_cropped_stack_based_on_mask(
boundary_i=args.extra_frame_target,
boundary_j=args.extra_frame_target,
boundary_k=args.extra_frame_target,
unit="mm",
)
# Scattered Data Approximation to get first estimate of HR volume
ph.print_title("First Estimate of HR Volume")
SDA = sda.ScatteredDataApproximation(stacks,
HR_volume,
sigma=args.sigma)
SDA.run()
HR_volume = SDA.get_reconstruction()
time_reconstruction = ph.stop_timing(time_tmp)
if args.verbose:
tmp = list(stacks)
tmp.insert(0, HR_volume)
sitkh.show_stacks(tmp, segmentation=HR_volume)
# ----------------Two-step Slice-to-Volume Registration SRR----------------
SRR = tk.TikhonovSolver(
stacks=stacks,
reconstruction=HR_volume,
reg_type="TK1",
minimizer="lsmr",
alpha=args.alpha_first,
iter_max=args.iter_max_first,
verbose=True,
use_masks=args.use_masks_srr,
)
if args.two_step_cycles > 0:
registration = regsitk.SimpleItkRegistration(
moving=HR_volume,
use_fixed_mask=True,
use_moving_mask=True,
use_verbose=args.verbose,
interpolator="Linear",
metric="Correlation",
use_multiresolution_framework=args.multiresolution,
shrink_factors=args.shrink_factors,
smoothing_sigmas=args.smoothing_sigmas,
initializer_type="SelfGEOMETRY",
optimizer="ConjugateGradientLineSearch",
optimizer_params={
"learningRate": 1,
"numberOfIterations": 100,
"lineSearchUpperLimit": 2,
},
scales_estimator="Jacobian",
)
two_step_s2v_reg_recon = \
pipeline.TwoStepSliceToVolumeRegistrationReconstruction(
stacks=stacks,
reference=HR_volume,
registration_method=registration,
reconstruction_method=SRR,
cycles=args.two_step_cycles,
alpha_range=[args.alpha_first, args.alpha],
verbose=args.verbose,
)
two_step_s2v_reg_recon.run()
HR_volume_iterations = \
two_step_s2v_reg_recon.get_iterative_reconstructions()
time_registration += \
two_step_s2v_reg_recon.get_computational_time_registration()
time_reconstruction += \
two_step_s2v_reg_recon.get_computational_time_reconstruction()
else:
HR_volume_iterations = []
# Write motion-correction results
if args.write_motion_correction:
for stack in stacks:
stack.write(
os.path.join(args.dir_output,
args.subfolder_motion_correction),
write_mask=True,
write_slices=True,
write_transforms=True,
suffix_mask=args.suffix_mask,
)
# ------------------Final Super-Resolution Reconstruction------------------
ph.print_title("Final Super-Resolution Reconstruction")
if args.reconstruction_type in ["TVL2", "HuberL2"]:
SRR = pd.PrimalDualSolver(
stacks=stacks,
reconstruction=HR_volume,
reg_type="TV" if args.reconstruction_type == "TVL2" else "huber",
iterations=args.iterations,
)
else:
SRR = tk.TikhonovSolver(
stacks=stacks,
reconstruction=HR_volume,
reg_type="TK1" if args.reconstruction_type == "TK1L2" else "TK0",
use_masks=args.use_masks_srr,
)
SRR.set_alpha(args.alpha)
SRR.set_iter_max(args.iter_max)
SRR.set_verbose(True)
SRR.run()
time_reconstruction += SRR.get_computational_time()
elapsed_time_total = ph.stop_timing(time_start)
# Write SRR result
HR_volume_final = SRR.get_reconstruction()
HR_volume_final.set_filename(SRR.get_setting_specific_filename())
HR_volume_final.write(args.dir_output,
write_mask=True,
suffix_mask=args.suffix_mask)
HR_volume_iterations.insert(0, HR_volume_final)
for stack in stacks:
HR_volume_iterations.append(stack)
if args.verbose and not args.provide_comparison:
sitkh.show_stacks(HR_volume_iterations, segmentation=HR_volume)
# HR_volume_final.show()
# Show SRR together with linearly resampled input data.
# Additionally, a script is generated to open files
if args.provide_comparison:
sitkh.show_stacks(
HR_volume_iterations,
segmentation=HR_volume,
show_comparison_file=args.provide_comparison,
dir_output=os.path.join(args.dir_output,
args.subfolder_comparison),
)
# Summary
ph.print_title("Summary")
print("Computational Time for Data Preprocessing: %s" %
(time_data_preprocessing))
print("Computational Time for Registrations: %s" % (time_registration))
print("Computational Time for Reconstructions: %s" % (time_reconstruction))
print("Computational Time for Entire Reconstruction Pipeline: %s" %
(elapsed_time_total))
ph.print_line_separator()
return 0
def main():
time_start = ph.start_timing()
np.set_printoptions(precision=3)
input_parser = InputArgparser(
description="Perform (linear) intensity correction across "
"stacks/images given a reference stack/image", )
input_parser.add_filenames(required=True)
input_parser.add_dir_output(required=True)
input_parser.add_reference(required=True)
input_parser.add_suffix_mask(default="_mask")
input_parser.add_search_angle(default=180)
input_parser.add_prefix_output(default="IC_")
input_parser.add_log_config(default=1)
input_parser.add_option(
option_string="--registration",
type=int,
help="Turn on/off registration from image to reference prior to "
"intensity correction.",
default=0)
input_parser.add_verbose(default=0)
args = input_parser.parse_args()
input_parser.print_arguments(args)
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
if args.reference in args.filenames:
args.filenames.remove(args.reference)
# Read data
data_reader = dr.MultipleImagesReader(args.filenames,
suffix_mask=args.suffix_mask,
extract_slices=False)
data_reader.read_data()
stacks = data_reader.get_data()
data_reader = dr.MultipleImagesReader([args.reference],
suffix_mask=args.suffix_mask,
extract_slices=False)
data_reader.read_data()
reference = data_reader.get_data()[0]
if args.registration:
# Define search angle ranges for FLIRT in all three dimensions
search_angles = [
"-searchr%s -%d %d" % (x, args.search_angle, args.search_angle)
for x in ["x", "y", "z"]
]
search_angles = (" ").join(search_angles)
registration = regflirt.FLIRT(
moving=reference,
registration_type="Rigid",
use_fixed_mask=True,
use_moving_mask=True,
options=search_angles,
use_verbose=False,
)
# Perform Intensity Correction
ph.print_title("Perform Intensity Correction")
intensity_corrector = ic.IntensityCorrection(
use_reference_mask=True,
use_individual_slice_correction=False,
prefix_corrected=args.prefix_output,
use_verbose=False,
)
stacks_corrected = [None] * len(stacks)
for i, stack in enumerate(stacks):
if args.registration:
ph.print_info("Image %d/%d: Registration ... " %
(i + 1, len(stacks)),
newline=False)
registration.set_fixed(stack)
registration.run()
transform_sitk = registration.get_registration_transform_sitk()
stack.update_motion_correction(transform_sitk)
print("done")
ph.print_info("Image %d/%d: Intensity Correction ... " %
(i + 1, len(stacks)),
newline=False)
ref = reference.get_resampled_stack(stack.sitk)
ref = st.Stack.from_sitk_image(image_sitk=ref.sitk,
image_sitk_mask=stack.sitk_mask *
ref.sitk_mask,
filename=reference.get_filename())
intensity_corrector.set_stack(stack)
intensity_corrector.set_reference(ref)
intensity_corrector.run_linear_intensity_correction()
# intensity_corrector.run_affine_intensity_correction()
stacks_corrected[i] = \
intensity_corrector.get_intensity_corrected_stack()
print("done (c1 = %g) " %
intensity_corrector.get_intensity_correction_coefficients())
# Write Data
stacks_corrected[i].write(args.dir_output,
write_mask=True,
suffix_mask=args.suffix_mask)
if args.verbose:
sitkh.show_stacks(
[
reference,
stacks_corrected[i],
# stacks[i],
],
segmentation=stacks_corrected[i])
# ph.pause()
# Write reference too (although not intensity corrected)
reference.write(args.dir_output,
filename=args.prefix_output + reference.get_filename(),
write_mask=True,
suffix_mask=args.suffix_mask)
elapsed_time = ph.stop_timing(time_start)
ph.print_title("Summary")
print("Computational Time for Intensity Correction(s): %s" %
(elapsed_time))
return 0
def main():
time_start = ph.start_timing()
np.set_printoptions(precision=3)
input_parser = InputArgparser(
description="Perform Bias Field correction on images based on N4ITK.",
)
input_parser.add_filenames(required=True)
input_parser.add_dir_output(required=True)
input_parser.add_suffix_mask(default="_mask")
input_parser.add_prefix_output(default="N4ITK_")
input_parser.add_option(
option_string="--convergence-threshold",
type=float,
help="Specify the convergence threshold.",
default=1e-6,
)
input_parser.add_option(
option_string="--spline-order",
type=int,
help="Specify the spline order defining the bias field estimate.",
default=3,
)
input_parser.add_option(
option_string="--wiener-filter-noise",
type=float,
help="Specify the noise estimate defining the Wiener filter.",
default=0.11,
)
input_parser.add_option(
option_string="--bias-field-fwhm",
type=float,
help="Specify the full width at half maximum parameter characterizing "
"the width of the Gaussian deconvolution.",
default=0.15,
)
input_parser.add_log_script_execution(default=1)
input_parser.add_verbose(default=0)
args = input_parser.parse_args()
input_parser.print_arguments(args)
# Write script execution call
if args.log_script_execution:
input_parser.write_performed_script_execution(
os.path.abspath(__file__))
# Read data
data_reader = dr.MultipleImagesReader(args.filenames,
suffix_mask=args.suffix_mask)
data_reader.read_data()
stacks = data_reader.get_data()
# Perform Bias Field Correction
ph.print_title("Perform Bias Field Correction")
bias_field_corrector = n4itk.N4BiasFieldCorrection(
convergence_threshold=args.convergence_threshold,
spline_order=args.spline_order,
wiener_filter_noise=args.wiener_filter_noise,
bias_field_fwhm=args.bias_field_fwhm,
prefix_corrected=args.prefix_output,
)
stacks_corrected = [None] * len(stacks)
for i, stack in enumerate(stacks):
ph.print_info("Image %d/%d: N4ITK Bias Field Correction ... " %
(i + 1, len(stacks)),
newline=False)
bias_field_corrector.set_stack(stack)
bias_field_corrector.run_bias_field_correction()
stacks_corrected[i] = \
bias_field_corrector.get_bias_field_corrected_stack()
print("done")
ph.print_info("Image %d/%d: Computational time = %s" %
(i + 1, len(stacks),
bias_field_corrector.get_computational_time()))
# Write Data
stacks_corrected[i].write(args.dir_output,
write_mask=True,
suffix_mask=args.suffix_mask)
if args.verbose:
sitkh.show_stacks([stacks[i], stacks_corrected[i]],
segmentation=stacks[i])
elapsed_time = ph.stop_timing(time_start)
ph.print_title("Summary")
print("Computational Time for Bias Field Correction(s): %s" %
(elapsed_time))
return 0
def main():
time_start = ph.start_timing()
# Set print options for numpy
np.set_printoptions(precision=3)
# Read input
input_parser = InputArgparser(
description="Script to study reconstruction parameters and their "
"impact on the volumetric reconstruction quality.",
)
input_parser.add_dir_input()
input_parser.add_filenames()
input_parser.add_image_selection()
input_parser.add_dir_output(required=True)
input_parser.add_suffix_mask(default="_mask")
input_parser.add_reconstruction_space()
input_parser.add_reference(
help="Path to reference NIfTI image file. If given the volumetric "
"reconstructed is performed in this physical space. "
"Either a reconstruction space or a reference must be provided",
required=False)
input_parser.add_reference_mask(default=None)
input_parser.add_study_name()
input_parser.add_reconstruction_type(default="TK1L2")
input_parser.add_measures(default=["PSNR", "RMSE", "SSIM", "NCC", "NMI"])
input_parser.add_tv_solver(default="PD")
input_parser.add_iterations(default=50)
input_parser.add_rho(default=0.1)
input_parser.add_iter_max(default=10)
input_parser.add_minimizer(default="lsmr")
input_parser.add_alpha(default=0.01)
input_parser.add_data_loss(default="linear")
input_parser.add_data_loss_scale(default=1)
input_parser.add_log_script_execution(default=1)
input_parser.add_verbose(default=1)
# Range for parameter sweeps
input_parser.add_alpha_range(default=[0.001, 0.05, 20]) # TK1L2
# input_parser.add_alpha_range(default=[0.001, 0.003, 10]) # TVL2, HuberL2
input_parser.add_data_losses(
# default=["linear", "arctan"]
)
input_parser.add_data_loss_scale_range(
# default=[0.1, 1.5, 2]
)
args = input_parser.parse_args()
input_parser.print_arguments(args)
if args.reference is None and args.reconstruction_space is None:
raise IOError("Either reference (--reference) or reconstruction space "
"(--reconstruction-space) must be provided.")
# Write script execution call
if args.log_script_execution:
input_parser.write_performed_script_execution(
os.path.abspath(__file__))
# --------------------------------Read Data--------------------------------
ph.print_title("Read Data")
# Neither '--dir-input' nor '--filenames' was specified
if args.filenames is not None and args.dir_input is not None:
raise IOError(
"Provide input by either '--dir-input' or '--filenames' "
"but not both together")
# '--dir-input' specified
elif args.dir_input is not None:
data_reader = dr.ImageSlicesDirectoryReader(
path_to_directory=args.dir_input,
suffix_mask=args.suffix_mask,
image_selection=args.image_selection)
# '--filenames' specified
elif args.filenames is not None:
data_reader = dr.MultipleImagesReader(
args.filenames, suffix_mask=args.suffix_mask)
else:
raise IOError(
"Provide input by either '--dir-input' or '--filenames'")
data_reader.read_data()
stacks = data_reader.get_data()
ph.print_info("%d input stacks read for further processing" % len(stacks))
if args.reference is not None:
reference = st.Stack.from_filename(
file_path=args.reference,
file_path_mask=args.reference_mask,
extract_slices=False)
reconstruction_space = stacks[0].get_resampled_stack(reference.sitk)
reconstruction_space = \
reconstruction_space.get_stack_multiplied_with_mask()
x_ref = sitk.GetArrayFromImage(reference.sitk).flatten()
x_ref_mask = sitk.GetArrayFromImage(reference.sitk_mask).flatten()
else:
reconstruction_space = st.Stack.from_filename(
file_path=args.reconstruction_space,
extract_slices=False)
reconstruction_space = stacks[0].get_resampled_stack(
reconstruction_space.sitk)
reconstruction_space = \
reconstruction_space.get_stack_multiplied_with_mask()
x_ref = None
x_ref_mask = None
# ----------------------------Set Up Parameters----------------------------
parameters = {}
parameters["alpha"] = np.linspace(
args.alpha_range[0], args.alpha_range[1], int(args.alpha_range[2]))
if args.data_losses is not None:
parameters["data_loss"] = args.data_losses
if args.data_loss_scale_range is not None:
parameters["data_loss_scale"] = np.linspace(
args.data_loss_scale_range[0],
args.data_loss_scale_range[1],
int(args.data_loss_scale_range[2]))
# --------------------------Set Up Parameter Study-------------------------
if args.study_name is None:
name = args.reconstruction_type
else:
name = args.study_name
reconstruction_info = {
"shape": reconstruction_space.sitk.GetSize()[::-1],
"origin": reconstruction_space.sitk.GetOrigin(),
"spacing": reconstruction_space.sitk.GetSpacing(),
"direction": reconstruction_space.sitk.GetDirection(),
}
# Create Tikhonov solver from which all information can be extracted
# (also for other reconstruction types)
tmp = tk.TikhonovSolver(
stacks=stacks,
reconstruction=reconstruction_space,
alpha=args.alpha,
iter_max=args.iter_max,
data_loss=args.data_loss,
data_loss_scale=args.data_loss_scale,
reg_type="TK1",
minimizer=args.minimizer,
verbose=args.verbose,
)
solver = tmp.get_solver()
parameter_study_interface = \
deconv_interface.DeconvolutionParameterStudyInterface(
A=solver.get_A(),
A_adj=solver.get_A_adj(),
D=solver.get_B(),
D_adj=solver.get_B_adj(),
b=solver.get_b(),
x0=solver.get_x0(),
alpha=solver.get_alpha(),
x_scale=solver.get_x_scale(),
data_loss=solver.get_data_loss(),
data_loss_scale=solver.get_data_loss_scale(),
iter_max=solver.get_iter_max(),
minimizer=solver.get_minimizer(),
iterations=args.iterations,
measures=args.measures,
dimension=3,
L2=16./reconstruction_space.sitk.GetSpacing()[0]**2,
reconstruction_type=args.reconstruction_type,
rho=args.rho,
dir_output=args.dir_output,
parameters=parameters,
name=name,
reconstruction_info=reconstruction_info,
x_ref=x_ref,
x_ref_mask=x_ref_mask,
tv_solver=args.tv_solver,
verbose=args.verbose,
)
parameter_study_interface.set_up_parameter_study()
parameter_study = parameter_study_interface.get_parameter_study()
# Run parameter study
parameter_study.run()
print("\nComputational time for Deconvolution Parameter Study %s: %s" %
(name, parameter_study.get_computational_time()))
return 0
def from_motion_score(cls, file_paths, file_paths_masks):
if len(file_paths) != len(file_paths_masks):
raise ValueError("Number of provided images and masks must match")
t0 = ph.start_timing()
tse = cls()
volumes = np.array([
TargetStackEstimator._compute_volume(f) for f in file_paths_masks
])
# only allow stacks with minimum volume, i.e. anatomical/brain coverage
vol_min = 0.7 * np.median(volumes)
indices = [i for i in range(len(volumes)) if volumes[i] > vol_min]
# read all eligible stacks
stacks = [
st.Stack.from_filename(
file_path=file_paths[i],
file_path_mask=file_paths_masks[i],
extract_slices=False,
) for i in indices
]
# crop stack to bounding box of mask
stacks = [s.get_cropped_stack_based_on_mask() for s in stacks]
# debug
# for i_stack, stack in enumerate(stacks):
# stack.show(label=str(indices[i_stack]))
# compute motion scores of eligible stacks
motion_scores = [None] * len(indices)
for i_stack in range(len(indices)):
# compute singular values
s = TargetStackEstimator._compute_singular_values(stacks[i_stack])
# compute motion score
motion_scores[i_stack] = tse._compute_motion_score[tse._mode](s)
# select stack with minimum motion (score)
selection_best = np.argmin(motion_scores)
# reference back to input file_paths index
target_stack_index = indices[selection_best]
tse._target_stack_index = target_stack_index
# computational time
tse._computational_time = ph.stop_timing(t0)
# debug
# print(indices, len(indices), len(file_paths))
# print("Best: %d" % target_stack_index)
# print(motion_scores)
# print(tse.get_computational_time())
# ph.killall_itksnap()
return tse
def main():
time_start = ph.start_timing()
np.set_printoptions(precision=3)
input_parser = InputArgparser(
description="Perform Bias Field correction using N4ITK.", )
input_parser.add_filename(required=True)
input_parser.add_output(required=True)
input_parser.add_filename_mask()
input_parser.add_option(
option_string="--convergence-threshold",
type=float,
help="Specify the convergence threshold.",
default=1e-6,
)
input_parser.add_option(
option_string="--spline-order",
type=int,
help="Specify the spline order defining the bias field estimate.",
default=3,
)
input_parser.add_option(
option_string="--wiener-filter-noise",
type=float,
help="Specify the noise estimate defining the Wiener filter.",
default=0.11,
)
input_parser.add_option(
option_string="--bias-field-fwhm",
type=float,
help="Specify the full width at half maximum parameter characterizing "
"the width of the Gaussian deconvolution.",
default=0.15,
)
input_parser.add_log_config(default=1)
input_parser.add_verbose(default=0)
args = input_parser.parse_args()
input_parser.print_arguments(args)
if np.alltrue([not args.output.endswith(t) for t in ALLOWED_EXTENSIONS]):
raise ValueError(
"output filename invalid; allowed extensions are: %s" %
", ".join(ALLOWED_EXTENSIONS))
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
# Read data
stack = st.Stack.from_filename(
file_path=args.filename,
file_path_mask=args.filename_mask,
extract_slices=False,
)
# Perform Bias Field Correction
# ph.print_title("Perform Bias Field Correction")
bias_field_corrector = n4itk.N4BiasFieldCorrection(
stack=stack,
use_mask=True if args.filename_mask is not None else False,
convergence_threshold=args.convergence_threshold,
spline_order=args.spline_order,
wiener_filter_noise=args.wiener_filter_noise,
bias_field_fwhm=args.bias_field_fwhm,
)
ph.print_info("N4ITK Bias Field Correction ... ", newline=False)
bias_field_corrector.run_bias_field_correction()
stack_corrected = bias_field_corrector.get_bias_field_corrected_stack()
print("done")
dw.DataWriter.write_image(stack_corrected.sitk, args.output)
elapsed_time = ph.stop_timing(time_start)
if args.verbose:
ph.show_niftis([args.filename, args.output])
ph.print_title("Summary")
exe_file_info = os.path.basename(os.path.abspath(__file__)).split(".")[0]
print("%s | Computational Time for Bias Field Correction: %s" %
(exe_file_info, elapsed_time))
return 0
def main():
time_start = ph.start_timing()
# Set print options for numpy
np.set_printoptions(precision=3)
# Read input
input_parser = InputArgparser(
description="Volumetric MRI reconstruction framework to reconstruct "
"an isotropic, high-resolution 3D volume from multiple "
"motion-corrected (or static) stacks of low-resolution slices.", )
input_parser.add_dir_input()
input_parser.add_filenames()
input_parser.add_image_selection()
input_parser.add_dir_output(required=True)
input_parser.add_prefix_output(default="SRR_")
input_parser.add_suffix_mask(default="_mask")
input_parser.add_target_stack_index(default=0)
input_parser.add_extra_frame_target(default=10)
input_parser.add_isotropic_resolution(default=None)
input_parser.add_reconstruction_space(default=None)
input_parser.add_minimizer(default="lsmr")
input_parser.add_iter_max(default=10)
input_parser.add_reconstruction_type(default="TK1L2")
input_parser.add_data_loss(default="linear")
input_parser.add_data_loss_scale(default=1)
input_parser.add_alpha(default=0.02 # TK1L2
# default=0.006 #TVL2, HuberL2
)
input_parser.add_rho(default=0.5)
input_parser.add_tv_solver(default="PD")
input_parser.add_pd_alg_type(default="ALG2")
input_parser.add_iterations(default=15)
input_parser.add_subfolder_comparison()
input_parser.add_provide_comparison(default=0)
input_parser.add_log_script_execution(default=1)
input_parser.add_verbose(default=0)
args = input_parser.parse_args()
input_parser.print_arguments(args)
# Write script execution call
if args.log_script_execution:
input_parser.write_performed_script_execution(
os.path.abspath(__file__))
# --------------------------------Read Data--------------------------------
ph.print_title("Read Data")
# Neither '--dir-input' nor '--filenames' was specified
if args.filenames is not None and args.dir_input is not None:
raise IOError("Provide input by either '--dir-input' or '--filenames' "
"but not both together")
# '--dir-input' specified
elif args.dir_input is not None:
data_reader = dr.ImageSlicesDirectoryReader(
path_to_directory=args.dir_input,
suffix_mask=args.suffix_mask,
image_selection=args.image_selection)
# '--filenames' specified
elif args.filenames is not None:
data_reader = dr.MultipleImagesReader(args.filenames,
suffix_mask=args.suffix_mask)
else:
raise IOError("Provide input by either '--dir-input' or '--filenames'")
if args.reconstruction_type not in ["TK1L2", "TVL2", "HuberL2"]:
raise IOError("Reconstruction type unknown")
data_reader.read_data()
stacks = data_reader.get_data()
ph.print_info("%d input stacks read for further processing" % len(stacks))
# Reconstruction space is given isotropically resampled target stack
if args.reconstruction_space is None:
recon0 = \
stacks[args.target_stack_index].get_isotropically_resampled_stack(
resolution=args.isotropic_resolution,
extra_frame=args.extra_frame_target)
# Reconstruction space was provided by user
else:
recon0 = st.Stack.from_filename(args.reconstruction_space,
extract_slices=False)
# Change resolution for isotropic resolution if provided by user
if args.isotropic_resolution is not None:
recon0 = recon0.get_isotropically_resampled_stack(
args.isotropic_resolution)
# Use image information of selected target stack as recon0 serves
# as initial value for reconstruction
recon0 = \
stacks[args.target_stack_index].get_resampled_stack(recon0.sitk)
recon0 = recon0.get_stack_multiplied_with_mask()
if args.reconstruction_type in ["TVL2", "HuberL2"]:
ph.print_title("Compute Initial value for %s" %
args.reconstruction_type)
SRR0 = tk.TikhonovSolver(
stacks=stacks,
reconstruction=recon0,
alpha=args.alpha,
iter_max=args.iter_max,
reg_type="TK1",
minimizer=args.minimizer,
data_loss=args.data_loss,
data_loss_scale=args.data_loss_scale,
# verbose=args.verbose,
)
SRR0.run()
recon = SRR0.get_reconstruction()
recon.set_filename(SRR0.get_setting_specific_filename(args.prefix_output))
recon.write(args.dir_output)
# List to store SRRs
recons = []
for i in range(0, len(stacks)):
recons.append(stacks[i])
recons.insert(0, recon)
if args.reconstruction_type in ["TVL2", "HuberL2"]:
ph.print_title("Compute %s reconstruction" % args.reconstruction_type)
if args.tv_solver == "ADMM":
SRR = admm.ADMMSolver(
stacks=stacks,
reconstruction=st.Stack.from_stack(SRR0.get_reconstruction()),
minimizer=args.minimizer,
alpha=args.alpha,
iter_max=args.iter_max,
rho=args.rho,
data_loss=args.data_loss,
iterations=args.iterations,
verbose=args.verbose,
)
SRR.run()
recon = SRR.get_reconstruction()
recon.set_filename(
SRR.get_setting_specific_filename(args.prefix_output))
recons.insert(0, recon)
recon.write(args.dir_output)
else:
SRR = pd.PrimalDualSolver(
stacks=stacks,
reconstruction=st.Stack.from_stack(SRR0.get_reconstruction()),
minimizer=args.minimizer,
alpha=args.alpha,
iter_max=args.iter_max,
iterations=args.iterations,
alg_type=args.pd_alg_type,
reg_type="TV"
if args.reconstruction_type == "TVL2" else "huber",
data_loss=args.data_loss,
verbose=args.verbose,
)
SRR.run()
recon = SRR.get_reconstruction()
recon.set_filename(
SRR.get_setting_specific_filename(args.prefix_output))
recons.insert(0, recon)
recon.write(args.dir_output)
if args.verbose and not args.provide_comparison:
sitkh.show_stacks(recons)
# Show SRR together with linearly resampled input data.
# Additionally, a script is generated to open files
if args.provide_comparison:
sitkh.show_stacks(
recons,
show_comparison_file=args.provide_comparison,
dir_output=os.path.join(args.dir_output,
args.subfolder_comparison),
)
ph.print_line_separator()
elapsed_time = ph.stop_timing(time_start)
ph.print_title("Summary")
print("Computational Time for Volumetric Reconstruction: %s" %
(elapsed_time))
return 0
def main():
time_start = ph.start_timing()
np.set_printoptions(precision=3)
input_parser = InputArgparser(
description="Perform automatic brain masking using "
"fetal_brain_seg, part of the MONAIfbs package "
"(https://github.com/gift-surg/MONAIfbs). ",
)
input_parser.add_filenames(required=True)
input_parser.add_filenames_masks(required=False)
input_parser.add_dir_output(required=False)
input_parser.add_verbose(default=0)
input_parser.add_log_config(default=0)
input_parser.add_option(
option_string="--neuroimage-legacy-seg",
type=int,
required=False,
default=0,
help="If set to 1, use the legacy method for fetal brain segmentation "
"i.e. the two-step approach proposed in Ebner, Wang et al "
"NeuroImage (2020)"
)
args = input_parser.parse_args()
input_parser.print_arguments(args)
if args.neuroimage_legacy_seg:
try:
DIR_FETAL_BRAIN_SEG = os.environ["FETAL_BRAIN_SEG"]
except KeyError as e:
raise RuntimeError(
"Environment variable FETAL_BRAIN_SEG is not specified. "
"Specify the root directory of fetal_brain_seg "
"(https://github.com/gift-surg/fetal_brain_seg) "
"using "
"'export FETAL_BRAIN_SEG=path_to_fetal_brain_seg_dir' "
"(in bashrc).")
else:
try:
import monaifbs
DIR_FETAL_BRAIN_SEG = os.path.dirname(monaifbs.__file__)
except ImportError as e:
raise RuntimeError(
"monaifbs not correctly installed. "
"Please check its installation running "
"pip install -e MONAIfbs/ "
)
print("Using executable from {}".format(DIR_FETAL_BRAIN_SEG))
if args.filenames_masks is None and args.dir_output is None:
raise IOError("Either --filenames-masks or --dir-output must be set")
if args.dir_output is not None:
args.filenames_masks = [
os.path.join(args.dir_output, os.path.basename(f))
for f in args.filenames
]
if len(args.filenames) != len(args.filenames_masks):
raise IOError("Number of filenames and filenames-masks must match")
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
cd_fetal_brain_seg = "cd %s" % DIR_FETAL_BRAIN_SEG
for f, m in zip(args.filenames, args.filenames_masks):
if not ph.file_exists(f):
raise IOError("File '%s' does not exist" % f)
# use absolute path for input image
f = os.path.abspath(f)
# use absolute path for output image
dir_output = os.path.dirname(m)
if not os.path.isabs(dir_output):
dir_output = os.path.realpath(
os.path.join(os.getcwd(), dir_output))
m = os.path.join(dir_output, os.path.basename(m))
ph.create_directory(dir_output)
# Change to root directory of fetal_brain_seg
cmds = [cd_fetal_brain_seg]
# Run masking independently (Takes longer but ensures that it does
# not terminate because of provided 'non-brain images')
cmd_args = ["python fetal_brain_seg.py"]
cmd_args.append("--input_names '%s'" % f)
cmd_args.append("--segment_output_names '%s'" % m)
cmds.append(" ".join(cmd_args))
# Execute both steps
cmd = " && ".join(cmds)
flag = ph.execute_command(cmd)
if flag != 0:
ph.print_warning(
"Error using fetal_brain_seg. \n"
"Execute '%s' for further investigation" %
cmd)
ph.print_info("Fetal brain segmentation written to '%s'" % m)
if args.verbose:
ph.show_nifti(f, segmentation=m)
elapsed_time_total = ph.stop_timing(time_start)
ph.print_title("Summary")
exe_file_info = os.path.basename(os.path.abspath(__file__)).split(".")[0]
print("%s | Computational Time: %s" % (exe_file_info, elapsed_time_total))
return 0
def run(self):
print_precisicion = 3
print_suppress = True
if self._optimizer_method in ["lm"]:
verbose = 1
if self._optimizer_loss not in ["linear"]:
self._optimizer_loss = "linear"
print(
"Optimizer method 'lm' only supports 'linear' loss function. "
)
else:
verbose = 2
jac = '2-point'
# jac = '3-point'
x_scale = 1.0 # or array
# x_scale = 'jac' #or array
# Initialize registration pipeline
self._run_registration_pipeline_initialization()
if self._use_verbose:
print("Initial values = ")
ph.print_numpy_array(self._parameters,
precision=print_precisicion,
suppress=print_suppress)
# Parameter normalization
if self._use_parameter_normalization:
parameter_normalization = pn.ParameterNormalization(
self._parameters)
parameter_normalization.compute_normalization_coefficients()
coefficients = parameter_normalization.get_normalization_coefficients(
)
# Use absolute mean for normalization
scale = abs(np.array(coefficients[0]))
# scale could be zero (like for rotation)
scale[np.where(scale == 0)] = 1
if self._use_verbose:
print("Normalization parameters:")
ph.print_numpy_array(scale,
precision=print_precisicion,
suppress=print_suppress)
# Each slice with the same scaling
x_scale = np.tile(scale, self._parameters.shape[0])
# HACK
self._transforms_2D_itk = [None] * self._N_slices
for i in range(0, self._N_slices):
self._transforms_2D_itk[i] = self._new_transform_itk[
self._transform_type]()
self._transforms_2D_itk[i].SetParameters(
itk.OptimizerParameters[itk.D](
self._transforms_2D_sitk[i].GetParameters()))
self._transforms_2D_itk[i].SetFixedParameters(
itk.OptimizerParameters[itk.D](
self._transforms_2D_sitk[i].GetFixedParameters()))
# Get cost function and its Jacobian w.r.t. the parameters
fun = self._get_residual_call()
jac = self._get_jacobian_residual_call()
x0 = self._parameters0_vec.flatten()
time_start = ph.start_timing()
if self._optimizer == "least_squares":
self._print_info_text_least_squares()
res = self._run_optimizer_least_squares(
fun=fun,
jac=jac,
x0=x0,
method=self._optimizer_method,
loss=self._optimizer_loss,
iter_max=self._optimizer_iter_max,
verbose=verbose,
x_scale=x_scale)
else:
self._print_info_text_minimize()
res = self._run_optimizer_minimize(
fun=fun,
jac=jac,
x0=x0,
method=self._optimizer,
loss=self._optimizer_loss,
iter_max=self._optimizer_iter_max,
verbose=verbose,
x_scale=x_scale)
self._elapsed_time = ph.stop_timing(time_start)
# Get and reshape final transform parameters for each slice
self._parameters = res.reshape(self._parameters.shape)
# Denormalize parameters
# self._parameters = self._parameter_normalizer.denormalize_parameters(self._parameters)
if self._use_verbose:
print("Final values = ")
ph.print_numpy_array(self._parameters,
precision=print_precisicion,
suppress=print_suppress)
# if self._use_verbose:
# print("Final values = ")
# print(self._parameters)
# Apply motion correction and compute slice transforms
self._apply_motion_correction()
def main():
time_start = ph.start_timing()
np.set_printoptions(precision=3)
input_parser = InputArgparser(
description="Register an obtained reconstruction (moving) "
"to a template image/space (fixed) using rigid registration. "
"The resulting registration can optionally be applied to previously "
"obtained motion correction slice transforms so that a volumetric "
"reconstruction is possible in the (standard anatomical) space "
"defined by the fixed.", )
input_parser.add_fixed(required=True)
input_parser.add_moving(required=True)
input_parser.add_output(help="Path to registration transform (.txt)",
required=True)
input_parser.add_fixed_mask()
input_parser.add_moving_mask()
input_parser.add_dir_input_mc()
input_parser.add_search_angle(default=180)
input_parser.add_option(option_string="--initial-transform",
type=str,
help="Path to initial transform.",
default=None)
input_parser.add_option(
option_string="--test-ap-flip",
type=int,
help="Turn on/off functionality to run an additional registration "
"after an AP-flip. Seems to be more robust to find a better "
"registration outcome in general.",
default=1)
input_parser.add_option(
option_string="--use-flirt",
type=int,
help="Turn on/off functionality to use FLIRT for the registration.",
default=1)
input_parser.add_option(
option_string="--use-regaladin",
type=int,
help="Turn on/off functionality to use RegAladin for the "
"registration.",
default=1)
input_parser.add_verbose(default=0)
input_parser.add_log_config(default=1)
args = input_parser.parse_args()
input_parser.print_arguments(args)
debug = 0
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
if not args.use_regaladin and not args.use_flirt:
raise IOError("Either RegAladin or FLIRT must be activated.")
if not args.output.endswith(".txt"):
raise IOError("output transformation path must end in '.txt'")
dir_output = os.path.dirname(args.output)
# --------------------------------Read Data--------------------------------
ph.print_title("Read Data")
fixed = st.Stack.from_filename(file_path=args.fixed,
file_path_mask=args.fixed_mask,
extract_slices=False)
moving = st.Stack.from_filename(file_path=args.moving,
file_path_mask=args.moving_mask,
extract_slices=False)
if args.initial_transform is not None:
transform_sitk = sitkh.read_transform_sitk(args.initial_transform)
else:
transform_sitk = sitk.AffineTransform(fixed.sitk.GetDimension())
sitk.WriteTransform(transform_sitk, args.output)
path_to_tmp_output = os.path.join(
DIR_TMP, ph.append_to_filename(os.path.basename(args.moving),
"_warped"))
# -------------------Register Reconstruction to Template-------------------
ph.print_title("Register Reconstruction to Template")
if args.use_flirt:
path_to_transform_flirt = os.path.join(DIR_TMP, "transform_flirt.txt")
# Convert SimpleITK into FLIRT transform
cmd = "simplereg_transform -sitk2flirt %s %s %s %s" % (
args.output, args.fixed, args.moving, path_to_transform_flirt)
ph.execute_command(cmd, verbose=False)
# Define search angle ranges for FLIRT in all three dimensions
search_angles = [
"-searchr%s -%d %d" % (x, args.search_angle, args.search_angle)
for x in ["x", "y", "z"]
]
# flt = nipype.interfaces.fsl.FLIRT()
# flt.inputs.in_file = args.moving
# flt.inputs.reference = args.fixed
# if args.initial_transform is not None:
# flt.inputs.in_matrix_file = path_to_transform_flirt
# flt.inputs.out_matrix_file = path_to_transform_flirt
# # flt.inputs.output_type = "NIFTI_GZ"
# flt.inputs.out_file = path_to_tmp_output
# flt.inputs.args = "-dof 6"
# flt.inputs.args += " %s" % " ".join(search_angles)
# if args.moving_mask is not None:
# flt.inputs.in_weight = args.moving_mask
# if args.fixed_mask is not None:
# flt.inputs.ref_weight = args.fixed_mask
# ph.print_info("Run Registration (FLIRT) ... ", newline=False)
# flt.run()
# print("done")
cmd_args = ["flirt"]
cmd_args.append("-in %s" % args.moving)
cmd_args.append("-ref %s" % args.fixed)
if args.initial_transform is not None:
cmd_args.append("-init %s" % path_to_transform_flirt)
cmd_args.append("-omat %s" % path_to_transform_flirt)
cmd_args.append("-out %s" % path_to_tmp_output)
cmd_args.append("-dof 6")
cmd_args.append((" ").join(search_angles))
if args.moving_mask is not None:
cmd_args.append("-inweight %s" % args.moving_mask)
if args.fixed_mask is not None:
cmd_args.append("-refweight %s" % args.fixed_mask)
ph.print_info("Run Registration (FLIRT) ... ", newline=False)
ph.execute_command(" ".join(cmd_args), verbose=False)
print("done")
# Convert FLIRT to SimpleITK transform
cmd = "simplereg_transform -flirt2sitk %s %s %s %s" % (
path_to_transform_flirt, args.fixed, args.moving, args.output)
ph.execute_command(cmd, verbose=False)
if debug:
ph.show_niftis([args.fixed, path_to_tmp_output])
# Additionally, use RegAladin for more accurate alignment
# Rationale: FLIRT has better capture range, but RegAladin seems to
# find better alignment once it is within its capture range.
if args.use_regaladin:
path_to_transform_regaladin = os.path.join(DIR_TMP,
"transform_regaladin.txt")
# Convert SimpleITK to RegAladin transform
cmd = "simplereg_transform -sitk2nreg %s %s" % (
args.output, path_to_transform_regaladin)
ph.execute_command(cmd, verbose=False)
# nreg = nipype.interfaces.niftyreg.RegAladin()
# nreg.inputs.ref_file = args.fixed
# nreg.inputs.flo_file = args.moving
# nreg.inputs.res_file = path_to_tmp_output
# nreg.inputs.in_aff_file = path_to_transform_regaladin
# nreg.inputs.aff_file = path_to_transform_regaladin
# nreg.inputs.args = "-rigOnly -voff"
# if args.moving_mask is not None:
# nreg.inputs.fmask_file = args.moving_mask
# if args.fixed_mask is not None:
# nreg.inputs.rmask_file = args.fixed_mask
# ph.print_info("Run Registration (RegAladin) ... ", newline=False)
# nreg.run()
# print("done")
cmd_args = ["reg_aladin"]
cmd_args.append("-ref %s" % args.fixed)
cmd_args.append("-flo %s" % args.moving)
cmd_args.append("-res %s" % path_to_tmp_output)
if args.initial_transform is not None or args.use_flirt == 1:
cmd_args.append("-inaff %s" % path_to_transform_regaladin)
cmd_args.append("-aff %s" % path_to_transform_regaladin)
# cmd_args.append("-cog")
# cmd_args.append("-ln 2")
cmd_args.append("-rigOnly")
cmd_args.append("-voff")
if args.moving_mask is not None:
cmd_args.append("-fmask %s" % args.moving_mask)
if args.fixed_mask is not None:
cmd_args.append("-rmask %s" % args.fixed_mask)
ph.print_info("Run Registration (RegAladin) ... ", newline=False)
ph.execute_command(" ".join(cmd_args), verbose=False)
print("done")
# Convert RegAladin to SimpleITK transform
cmd = "simplereg_transform -nreg2sitk %s %s" % (
path_to_transform_regaladin, args.output)
ph.execute_command(cmd, verbose=False)
if debug:
ph.show_niftis([args.fixed, path_to_tmp_output])
if args.test_ap_flip:
path_to_transform_flip = os.path.join(DIR_TMP, "transform_flip.txt")
path_to_tmp_output_flip = os.path.join(DIR_TMP, "output_flip.nii.gz")
# Get AP-flip transform
transform_ap_flip_sitk = get_ap_flip_transform(args.fixed)
path_to_transform_flip_regaladin = os.path.join(
DIR_TMP, "transform_flip_regaladin.txt")
sitk.WriteTransform(transform_ap_flip_sitk, path_to_transform_flip)
# Compose current transform with AP flip transform
cmd = "simplereg_transform -c %s %s %s" % (
args.output, path_to_transform_flip, path_to_transform_flip)
ph.execute_command(cmd, verbose=False)
# Convert SimpleITK to RegAladin transform
cmd = "simplereg_transform -sitk2nreg %s %s" % (
path_to_transform_flip, path_to_transform_flip_regaladin)
ph.execute_command(cmd, verbose=False)
# nreg = nipype.interfaces.niftyreg.RegAladin()
# nreg.inputs.ref_file = args.fixed
# nreg.inputs.flo_file = args.moving
# nreg.inputs.res_file = path_to_tmp_output_flip
# nreg.inputs.in_aff_file = path_to_transform_flip_regaladin
# nreg.inputs.aff_file = path_to_transform_flip_regaladin
# nreg.inputs.args = "-rigOnly -voff"
# if args.moving_mask is not None:
# nreg.inputs.fmask_file = args.moving_mask
# if args.fixed_mask is not None:
# nreg.inputs.rmask_file = args.fixed_mask
# ph.print_info("Run Registration AP-flipped (RegAladin) ... ",
# newline=False)
# nreg.run()
# print("done")
cmd_args = ["reg_aladin"]
cmd_args.append("-ref %s" % args.fixed)
cmd_args.append("-flo %s" % args.moving)
cmd_args.append("-res %s" % path_to_tmp_output_flip)
cmd_args.append("-inaff %s" % path_to_transform_flip_regaladin)
cmd_args.append("-aff %s" % path_to_transform_flip_regaladin)
cmd_args.append("-rigOnly")
# cmd_args.append("-ln 2")
cmd_args.append("-voff")
if args.moving_mask is not None:
cmd_args.append("-fmask %s" % args.moving_mask)
if args.fixed_mask is not None:
cmd_args.append("-rmask %s" % args.fixed_mask)
ph.print_info("Run Registration AP-flipped (RegAladin) ... ",
newline=False)
ph.execute_command(" ".join(cmd_args), verbose=False)
print("done")
if debug:
ph.show_niftis(
[args.fixed, path_to_tmp_output, path_to_tmp_output_flip])
warped_moving = st.Stack.from_filename(path_to_tmp_output,
extract_slices=False)
warped_moving_flip = st.Stack.from_filename(path_to_tmp_output_flip,
extract_slices=False)
fixed = st.Stack.from_filename(args.fixed, args.fixed_mask)
stacks = [warped_moving, warped_moving_flip]
image_similarity_evaluator = ise.ImageSimilarityEvaluator(
stacks=stacks, reference=fixed)
image_similarity_evaluator.compute_similarities()
similarities = image_similarity_evaluator.get_similarities()
if similarities["NMI"][1] > similarities["NMI"][0]:
ph.print_info("AP-flipped outcome better")
# Convert RegAladin to SimpleITK transform
cmd = "simplereg_transform -nreg2sitk %s %s" % (
path_to_transform_flip_regaladin, args.output)
ph.execute_command(cmd, verbose=False)
# Copy better outcome
cmd = "cp -p %s %s" % (path_to_tmp_output_flip, path_to_tmp_output)
ph.execute_command(cmd, verbose=False)
else:
ph.print_info("AP-flip does not improve outcome")
if args.dir_input_mc is not None:
transform_sitk = sitkh.read_transform_sitk(args.output, inverse=1)
if args.dir_input_mc.endswith("/"):
subdir_mc = args.dir_input_mc.split("/")[-2]
else:
subdir_mc = args.dir_input_mc.split("/")[-1]
dir_output_mc = os.path.join(dir_output, subdir_mc)
ph.create_directory(dir_output_mc, delete_files=True)
pattern = REGEX_FILENAMES + "[.]tfm"
p = re.compile(pattern)
trafos = [t for t in os.listdir(args.dir_input_mc) if p.match(t)]
for t in trafos:
path_to_input_transform = os.path.join(args.dir_input_mc, t)
path_to_output_transform = os.path.join(dir_output_mc, t)
t_sitk = sitkh.read_transform_sitk(path_to_input_transform)
t_sitk = sitkh.get_composite_sitk_affine_transform(
transform_sitk, t_sitk)
sitk.WriteTransform(t_sitk, path_to_output_transform)
if args.verbose:
ph.show_niftis([args.fixed, path_to_tmp_output])
elapsed_time_total = ph.stop_timing(time_start)
# Summary
ph.print_title("Summary")
print("Computational Time: %s" % (elapsed_time_total))
return 0
def main():
time_start = ph.start_timing()
np.set_printoptions(precision=3)
input_parser = InputArgparser(
description="Run reconstruction pipeline including "
"(i) bias field correction, "
"(ii) volumetric reconstruction in subject space, "
"(iii) volumetric reconstruction in template space, "
"and (iv) some diagnostics to assess the obtained reconstruction.", )
input_parser.add_filenames(required=True)
input_parser.add_filenames_masks(required=True)
input_parser.add_target_stack(required=False)
input_parser.add_suffix_mask(default="")
input_parser.add_dir_output(required=True)
input_parser.add_alpha(default=0.01)
input_parser.add_verbose(default=0)
input_parser.add_gestational_age(required=False)
input_parser.add_prefix_output(default="")
input_parser.add_search_angle(default=180)
input_parser.add_multiresolution(default=0)
input_parser.add_log_config(default=1)
input_parser.add_isotropic_resolution()
input_parser.add_reference()
input_parser.add_reference_mask()
input_parser.add_bias_field_correction(default=1)
input_parser.add_intensity_correction(default=1)
input_parser.add_iter_max(default=10)
input_parser.add_two_step_cycles(default=3)
input_parser.add_slice_thicknesses(default=None)
input_parser.add_option(
option_string="--run-bias-field-correction",
type=int,
help="Turn on/off bias field correction. "
"If off, it is assumed that this step was already performed "
"if --bias-field-correction is active.",
default=1)
input_parser.add_option(
option_string="--run-recon-subject-space",
type=int,
help="Turn on/off reconstruction in subject space. "
"If off, it is assumed that this step was already performed.",
default=1)
input_parser.add_option(
option_string="--run-recon-template-space",
type=int,
help="Turn on/off reconstruction in template space. "
"If off, it is assumed that this step was already performed.",
default=1)
input_parser.add_option(
option_string="--run-diagnostics",
type=int,
help="Turn on/off diagnostics of the obtained volumetric "
"reconstruction. ",
default=0)
input_parser.add_option(
option_string="--initial-transform",
type=str,
help="Set initial transform to be used for register_image.",
default=None)
input_parser.add_outlier_rejection(default=1)
input_parser.add_threshold_first(default=0.5)
input_parser.add_threshold(default=0.8)
input_parser.add_argument(
"--sda",
"-sda",
action='store_true',
help="If given, the volume is reconstructed using "
"Scattered Data Approximation (Vercauteren et al., 2006). "
"--alpha is considered the value for the standard deviation then. "
"Recommended value is, e.g., --alpha 0.8")
input_parser.add_argument(
"--v2v-robust",
"-v2v-robust",
action='store_true',
help="If given, a more robust volume-to-volume registration step is "
"performed, i.e. four rigid registrations are performed using four "
"rigid transform initializations based on "
"principal component alignment of associated masks.")
input_parser.add_interleave(default=3)
input_parser.add_argument(
"--s2v-hierarchical",
"-s2v-hierarchical",
action='store_true',
help="If given, a hierarchical approach for the first slice-to-volume "
"registration cycle is used, i.e. sub-packages defined by the "
"specified interleave (--interleave) are registered until each "
"slice is registered independently.")
args = input_parser.parse_args()
input_parser.print_arguments(args)
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
filename_srr = "srr"
dir_output_preprocessing = os.path.join(args.dir_output,
"preprocessing_n4itk")
dir_output_recon_subject_space = os.path.join(args.dir_output,
"recon_subject_space")
dir_output_recon_template_space = os.path.join(args.dir_output,
"recon_template_space")
dir_output_diagnostics = os.path.join(args.dir_output, "diagnostics")
srr_subject = os.path.join(dir_output_recon_subject_space,
"%s_subject.nii.gz" % filename_srr)
srr_subject_mask = ph.append_to_filename(srr_subject, "_mask")
srr_template = os.path.join(dir_output_recon_template_space,
"%s_template.nii.gz" % filename_srr)
srr_template_mask = ph.append_to_filename(srr_template, "_mask")
trafo_template = os.path.join(dir_output_recon_template_space,
"registration_transform_sitk.txt")
srr_slice_coverage = os.path.join(
dir_output_diagnostics,
"%s_template_slicecoverage.nii.gz" % filename_srr)
if args.bias_field_correction and args.run_bias_field_correction:
for i, f in enumerate(args.filenames):
output = os.path.join(dir_output_preprocessing,
os.path.basename(f))
cmd_args = []
cmd_args.append("--filename '%s'" % f)
cmd_args.append("--filename-mask '%s'" % args.filenames_masks[i])
cmd_args.append("--output '%s'" % output)
# cmd_args.append("--verbose %d" % args.verbose)
cmd_args.append("--log-config %d" % args.log_config)
cmd = "niftymic_correct_bias_field %s" % (" ").join(cmd_args)
time_start_bias = ph.start_timing()
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Bias field correction failed")
elapsed_time_bias = ph.stop_timing(time_start_bias)
filenames = [
os.path.join(dir_output_preprocessing, os.path.basename(f))
for f in args.filenames
]
elif args.bias_field_correction and not args.run_bias_field_correction:
elapsed_time_bias = ph.get_zero_time()
filenames = [
os.path.join(dir_output_preprocessing, os.path.basename(f))
for f in args.filenames
]
else:
elapsed_time_bias = ph.get_zero_time()
filenames = args.filenames
# Specify target stack for intensity correction and reconstruction space
if args.target_stack is None:
target_stack = filenames[0]
else:
try:
target_stack_index = args.filenames.index(args.target_stack)
except ValueError as e:
raise ValueError(
"--target-stack must correspond to an image as provided by "
"--filenames")
target_stack = filenames[target_stack_index]
# Add single quotes around individual filenames to account for whitespaces
filenames = ["'" + f + "'" for f in filenames]
filenames_masks = ["'" + f + "'" for f in args.filenames_masks]
if args.run_recon_subject_space:
cmd_args = ["niftymic_reconstruct_volume"]
cmd_args.append("--filenames %s" % (" ").join(filenames))
cmd_args.append("--filenames-masks %s" % (" ").join(filenames_masks))
cmd_args.append("--multiresolution %d" % args.multiresolution)
cmd_args.append("--target-stack '%s'" % target_stack)
cmd_args.append("--output '%s'" % srr_subject)
cmd_args.append("--suffix-mask '%s'" % args.suffix_mask)
cmd_args.append("--intensity-correction %d" %
args.intensity_correction)
cmd_args.append("--alpha %s" % args.alpha)
cmd_args.append("--iter-max %d" % args.iter_max)
cmd_args.append("--two-step-cycles %d" % args.two_step_cycles)
cmd_args.append("--outlier-rejection %d" % args.outlier_rejection)
cmd_args.append("--threshold-first %f" % args.threshold_first)
cmd_args.append("--threshold %f" % args.threshold)
if args.slice_thicknesses is not None:
cmd_args.append("--slice-thicknesses %s" %
" ".join(map(str, args.slice_thicknesses)))
cmd_args.append("--verbose %d" % args.verbose)
cmd_args.append("--log-config %d" % args.log_config)
if args.isotropic_resolution is not None:
cmd_args.append("--isotropic-resolution %f" %
args.isotropic_resolution)
if args.reference is not None:
cmd_args.append("--reference %s" % args.reference)
if args.reference_mask is not None:
cmd_args.append("--reference-mask %s" % args.reference_mask)
if args.sda:
cmd_args.append("--sda")
if args.v2v_robust:
cmd_args.append("--v2v-robust")
if args.s2v_hierarchical:
cmd_args.append("--s2v-hierarchical")
cmd = (" ").join(cmd_args)
time_start_volrec = ph.start_timing()
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Reconstruction in subject space failed")
# Compute SRR mask in subject space
# (Approximated using SDA within reconstruct_volume)
if 0:
dir_motion_correction = os.path.join(
dir_output_recon_subject_space, "motion_correction")
cmd_args = ["niftymic_reconstruct_volume_from_slices"]
cmd_args.append("--filenames %s" % " ".join(filenames_masks))
cmd_args.append("--dir-input-mc '%s'" % dir_motion_correction)
cmd_args.append("--output '%s'" % srr_subject_mask)
cmd_args.append("--reconstruction-space '%s'" % srr_subject)
cmd_args.append("--suffix-mask '%s'" % args.suffix_mask)
cmd_args.append("--mask")
cmd_args.append("--log-config %d" % args.log_config)
if args.slice_thicknesses is not None:
cmd_args.append("--slice-thicknesses %s" %
" ".join(map(str, args.slice_thicknesses)))
if args.sda:
cmd_args.append("--sda")
cmd_args.append("--alpha 1")
else:
cmd_args.append("--alpha 0.1")
cmd_args.append("--iter-max 5")
cmd = (" ").join(cmd_args)
ph.execute_command(cmd)
elapsed_time_volrec = ph.stop_timing(time_start_volrec)
else:
elapsed_time_volrec = ph.get_zero_time()
if args.run_recon_template_space:
if args.gestational_age is None:
template_stack_estimator = \
tse.TemplateStackEstimator.from_mask(srr_subject_mask)
gestational_age = template_stack_estimator.get_estimated_gw()
ph.print_info("Estimated gestational age: %d" % gestational_age)
else:
gestational_age = args.gestational_age
template = os.path.join(DIR_TEMPLATES,
"STA%d.nii.gz" % gestational_age)
template_mask = os.path.join(DIR_TEMPLATES,
"STA%d_mask.nii.gz" % gestational_age)
# Register SRR to template space
cmd_args = ["niftymic_register_image"]
cmd_args.append("--fixed '%s'" % template)
cmd_args.append("--moving '%s'" % srr_subject)
cmd_args.append("--fixed-mask '%s'" % template_mask)
cmd_args.append("--moving-mask '%s'" % srr_subject_mask)
cmd_args.append(
"--dir-input-mc '%s'" %
os.path.join(dir_output_recon_subject_space, "motion_correction"))
cmd_args.append("--output '%s'" % trafo_template)
cmd_args.append("--verbose %s" % args.verbose)
cmd_args.append("--log-config %d" % args.log_config)
cmd_args.append("--refine-pca")
if args.initial_transform is not None:
cmd_args.append("--initial-transform '%s'" %
args.initial_transform)
cmd = (" ").join(cmd_args)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Registration to template space failed")
# Compute SRR in template space
dir_input_mc = os.path.join(dir_output_recon_template_space,
"motion_correction")
cmd_args = ["niftymic_reconstruct_volume_from_slices"]
cmd_args.append("--filenames %s" % (" ").join(filenames))
cmd_args.append("--filenames-masks %s" % (" ").join(filenames_masks))
cmd_args.append("--dir-input-mc '%s'" % dir_input_mc)
cmd_args.append("--output '%s'" % srr_template)
cmd_args.append("--reconstruction-space '%s'" % template)
cmd_args.append("--target-stack '%s'" % target_stack)
cmd_args.append("--iter-max %d" % args.iter_max)
cmd_args.append("--alpha %s" % args.alpha)
cmd_args.append("--suffix-mask '%s'" % args.suffix_mask)
cmd_args.append("--verbose %s" % args.verbose)
cmd_args.append("--log-config %d" % args.log_config)
if args.slice_thicknesses is not None:
cmd_args.append("--slice-thicknesses %s" %
" ".join(map(str, args.slice_thicknesses)))
if args.sda:
cmd_args.append("--sda")
cmd = (" ").join(cmd_args)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Reconstruction in template space failed")
# Compute SRR mask in template space
if 1:
dir_motion_correction = os.path.join(
dir_output_recon_template_space, "motion_correction")
cmd_args = ["niftymic_reconstruct_volume_from_slices"]
cmd_args.append("--filenames %s" % " ".join(filenames_masks))
cmd_args.append("--dir-input-mc '%s'" % dir_motion_correction)
cmd_args.append("--output '%s'" % srr_template_mask)
cmd_args.append("--reconstruction-space '%s'" % srr_template)
cmd_args.append("--suffix-mask '%s'" % args.suffix_mask)
cmd_args.append("--log-config %d" % args.log_config)
cmd_args.append("--mask")
if args.slice_thicknesses is not None:
cmd_args.append("--slice-thicknesses %s" %
" ".join(map(str, args.slice_thicknesses)))
if args.sda:
cmd_args.append("--sda")
cmd_args.append("--alpha 1")
else:
cmd_args.append("--alpha 0.1")
cmd_args.append("--iter-max 5")
cmd = (" ").join(cmd_args)
ph.execute_command(cmd)
# Copy SRR to output directory
if 0:
output = "%sSRR_Stacks%d.nii.gz" % (args.prefix_output,
len(args.filenames))
path_to_output = os.path.join(args.dir_output, output)
cmd = "cp -p '%s' '%s'" % (srr_template, path_to_output)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Copy of SRR to output directory failed")
# Multiply template mask with reconstruction
if 0:
cmd_args = ["niftymic_multiply"]
fnames = [
srr_template,
srr_template_mask,
]
output_masked = "Masked_%s" % output
path_to_output_masked = os.path.join(args.dir_output,
output_masked)
cmd_args.append("--filenames %s" % " ".join(fnames))
cmd_args.append("--output '%s'" % path_to_output_masked)
cmd = (" ").join(cmd_args)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("SRR brain masking failed")
else:
elapsed_time_template = ph.get_zero_time()
if args.run_diagnostics:
dir_input_mc = os.path.join(dir_output_recon_template_space,
"motion_correction")
dir_output_orig_vs_proj = os.path.join(dir_output_diagnostics,
"original_vs_projected")
dir_output_selfsimilarity = os.path.join(dir_output_diagnostics,
"selfsimilarity")
dir_output_orig_vs_proj_pdf = os.path.join(dir_output_orig_vs_proj,
"pdf")
# Show slice coverage over reconstruction space
exe = os.path.abspath(show_slice_coverage.__file__)
cmd_args = ["python %s" % exe]
cmd_args.append("--filenames %s" % (" ").join(filenames))
cmd_args.append("--dir-input-mc '%s'" % dir_input_mc)
cmd_args.append("--reconstruction-space '%s'" % srr_template)
cmd_args.append("--output '%s'" % srr_slice_coverage)
cmd = (" ").join(cmd_args)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Slice coverage visualization failed")
# Get simulated/projected slices
exe = os.path.abspath(simulate_stacks_from_reconstruction.__file__)
cmd_args = ["python %s" % exe]
cmd_args.append("--filenames %s" % (" ").join(filenames))
if args.filenames_masks is not None:
cmd_args.append("--filenames-masks %s" %
(" ").join(filenames_masks))
cmd_args.append("--dir-input-mc '%s'" % dir_input_mc)
cmd_args.append("--dir-output '%s'" % dir_output_orig_vs_proj)
cmd_args.append("--reconstruction '%s'" % srr_template)
cmd_args.append("--copy-data 1")
if args.slice_thicknesses is not None:
cmd_args.append("--slice-thicknesses %s" %
" ".join(map(str, args.slice_thicknesses)))
# cmd_args.append("--verbose %s" % args.verbose)
cmd = (" ").join(cmd_args)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("SRR slice projections failed")
filenames_simulated = [
"'%s" % os.path.join(dir_output_orig_vs_proj, os.path.basename(f))
for f in filenames
]
# Evaluate slice similarities to ground truth
exe = os.path.abspath(evaluate_simulated_stack_similarity.__file__)
cmd_args = ["python %s" % exe]
cmd_args.append("--filenames %s" % (" ").join(filenames_simulated))
if args.filenames_masks is not None:
cmd_args.append("--filenames-masks %s" %
(" ").join(filenames_masks))
cmd_args.append("--measures NCC SSIM")
cmd_args.append("--dir-output '%s'" % dir_output_selfsimilarity)
cmd = (" ").join(cmd_args)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Evaluation of stack similarities failed")
# Generate figures showing the quantitative comparison
exe = os.path.abspath(
show_evaluated_simulated_stack_similarity.__file__)
cmd_args = ["python %s" % exe]
cmd_args.append("--dir-input '%s'" % dir_output_selfsimilarity)
cmd_args.append("--dir-output '%s'" % dir_output_selfsimilarity)
cmd = (" ").join(cmd_args)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
ph.print_warning("Visualization of stack similarities failed")
# Generate pdfs showing all the side-by-side comparisons
if 0:
exe = os.path.abspath(
export_side_by_side_simulated_vs_original_slice_comparison.
__file__)
cmd_args = ["python %s" % exe]
cmd_args.append("--filenames %s" % (" ").join(filenames_simulated))
cmd_args.append("--dir-output '%s'" % dir_output_orig_vs_proj_pdf)
cmd = "python %s %s" % (exe, (" ").join(cmd_args))
cmd = (" ").join(cmd_args)
exit_code = ph.execute_command(cmd)
if exit_code != 0:
raise RuntimeError("Generation of PDF overview failed")
ph.print_title("Summary")
print("Computational Time for Bias Field Correction: %s" %
elapsed_time_bias)
print("Computational Time for Volumetric Reconstruction: %s" %
elapsed_time_volrec)
print("Computational Time for Pipeline: %s" % ph.stop_timing(time_start))
return 0
def main():
time_start = ph.start_timing()
np.set_printoptions(precision=3)
input_parser = InputArgparser(
description="Perform automatic brain masking using "
"fetal_brain_seg (https://github.com/gift-surg/fetal_brain_seg). ", )
input_parser.add_filenames(required=True)
input_parser.add_filenames_masks(required=False)
input_parser.add_dir_output(required=False)
input_parser.add_verbose(default=0)
input_parser.add_log_config(default=0)
args = input_parser.parse_args()
input_parser.print_arguments(args)
try:
DIR_FETAL_BRAIN_SEG = os.environ["FETAL_BRAIN_SEG"]
except KeyError as e:
raise RuntimeError(
"Environment variable FETAL_BRAIN_SEG is not specified. "
"Specify the root directory of fetal_brain_seg "
"(https://github.com/gift-surg/fetal_brain_seg) "
"using "
"'export FETAL_BRAIN_SEG=path_to_fetal_brain_seg_dir' "
"(in bashrc).")
if args.filenames_masks is None and args.dir_output is None:
raise IOError("Either --filenames-masks or --dir-output must be set")
if args.dir_output is not None:
args.filenames_masks = [
os.path.join(args.dir_output, os.path.basename(f))
for f in args.filenames
]
if len(args.filenames) != len(args.filenames_masks):
raise IOError("Number of filenames and filenames-masks must match")
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
cd_fetal_brain_seg = "cd %s" % DIR_FETAL_BRAIN_SEG
for f, m in zip(args.filenames, args.filenames_masks):
if not ph.file_exists(f):
raise IOError("File '%s' does not exist" % f)
# use absolute path for input image
f = os.path.abspath(f)
# use absolute path for output image
dir_output = os.path.dirname(m)
if not os.path.isabs(dir_output):
dir_output = os.path.realpath(os.path.join(os.getcwd(),
dir_output))
m = os.path.join(dir_output, os.path.basename(m))
ph.create_directory(dir_output)
# Change to root directory of fetal_brain_seg
cmds = [cd_fetal_brain_seg]
# Run masking independently (Takes longer but ensures that it does
# not terminate because of provided 'non-brain images')
cmd_args = ["python fetal_brain_seg.py"]
cmd_args.append("--input_names '%s'" % f)
cmd_args.append("--segment_output_names '%s'" % m)
cmds.append(" ".join(cmd_args))
# Execute both steps
cmd = " && ".join(cmds)
flag = ph.execute_command(cmd)
if flag != 0:
ph.print_warning("Error using fetal_brain_seg. \n"
"Execute '%s' for further investigation" % cmd)
ph.print_info("Fetal brain segmentation written to '%s'" % m)
if args.verbose:
ph.show_nifti(f, segmentation=m)
return 0
def main():
time_start = ph.start_timing()
# Set print options for numpy
np.set_printoptions(precision=3)
# Read input
input_parser = InputArgparser(
description="Script to study reconstruction parameters and their "
"impact on the volumetric reconstruction quality. "
"This script can only be used to sweep through one single parameter, "
"e.g. the regularization parameter 'alpha'. ")
input_parser.add_filenames(required=True)
input_parser.add_filenames_masks()
input_parser.add_suffix_mask(default="_mask")
input_parser.add_dir_input_mc()
input_parser.add_dir_output(required=True)
input_parser.add_reconstruction_space()
input_parser.add_reference(
help="Path to reference NIfTI image file. If given the volumetric "
"reconstructed is performed in this physical space. "
"Either a reconstruction space or a reference must be provided",
required=False)
input_parser.add_reference_mask(default=None)
input_parser.add_study_name()
input_parser.add_reconstruction_type(default="TK1L2")
input_parser.add_measures(
default=["PSNR", "MAE", "RMSE", "SSIM", "NCC", "NMI"])
input_parser.add_tv_solver(default="PD")
input_parser.add_iterations(default=50)
input_parser.add_rho(default=0.1)
input_parser.add_iter_max(default=10)
input_parser.add_minimizer(default="lsmr")
input_parser.add_log_config(default=1)
input_parser.add_use_masks_srr(default=0)
input_parser.add_verbose(default=1)
input_parser.add_slice_thicknesses(default=None)
input_parser.add_argument(
"--append",
"-append",
action='store_true',
help="If given, results are appended to previously executed parameter "
"study with identical parameters and study name store in the output "
"directory.")
# Range for parameter sweeps
input_parser.add_alphas(default=list(np.linspace(0.01, 0.5, 5)))
input_parser.add_data_losses(default=["linear"]
# default=["linear", "arctan"]
)
input_parser.add_data_loss_scales(default=[1]
# default=[0.1, 0.5, 1.5]
)
args = input_parser.parse_args()
input_parser.print_arguments(args)
if args.reference is None and args.reconstruction_space is None:
raise IOError("Either reference (--reference) or reconstruction space "
"(--reconstruction-space) must be provided.")
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
# --------------------------------Read Data--------------------------------
ph.print_title("Read Data")
data_reader = dr.MultipleImagesReader(
file_paths=args.filenames,
file_paths_masks=args.filenames_masks,
suffix_mask=args.suffix_mask,
dir_motion_correction=args.dir_input_mc,
stacks_slice_thicknesses=args.slice_thicknesses,
)
data_reader.read_data()
stacks = data_reader.get_data()
ph.print_info("%d input stacks read for further processing" % len(stacks))
if args.reference is not None:
reference = st.Stack.from_filename(file_path=args.reference,
file_path_mask=args.reference_mask,
extract_slices=False)
reconstruction_space = stacks[0].get_resampled_stack(reference.sitk)
reconstruction_space = \
reconstruction_space.get_stack_multiplied_with_mask()
x_ref = sitk.GetArrayFromImage(reference.sitk).flatten()
x_ref_mask = sitk.GetArrayFromImage(reference.sitk_mask).flatten()
else:
reconstruction_space = st.Stack.from_filename(
file_path=args.reconstruction_space, extract_slices=False)
reconstruction_space = stacks[0].get_resampled_stack(
reconstruction_space.sitk)
reconstruction_space = \
reconstruction_space.get_stack_multiplied_with_mask()
x_ref = None
x_ref_mask = None
# ----------------------------Set Up Parameters----------------------------
parameters = {}
parameters["alpha"] = args.alphas
if len(args.data_losses) > 1:
parameters["data_loss"] = args.data_losses
if len(args.data_loss_scales) > 1:
parameters["data_loss_scale"] = args.data_loss_scales
# --------------------------Set Up Parameter Study-------------------------
ph.print_title("Run Parameter Study")
if args.study_name is None:
name = args.reconstruction_type
else:
name = args.study_name
reconstruction_info = {
"shape": reconstruction_space.sitk.GetSize()[::-1],
"origin": reconstruction_space.sitk.GetOrigin(),
"spacing": reconstruction_space.sitk.GetSpacing(),
"direction": reconstruction_space.sitk.GetDirection(),
}
# Create Tikhonov solver from which all information can be extracted
# (also for other reconstruction types)
tmp = tk.TikhonovSolver(
stacks=stacks,
reconstruction=reconstruction_space,
alpha=args.alphas[0],
iter_max=args.iter_max,
data_loss=args.data_losses[0],
data_loss_scale=args.data_loss_scales[0],
reg_type="TK1",
minimizer=args.minimizer,
verbose=args.verbose,
use_masks=args.use_masks_srr,
)
solver = tmp.get_solver()
parameter_study_interface = \
deconv_interface.DeconvolutionParameterStudyInterface(
A=solver.get_A(),
A_adj=solver.get_A_adj(),
D=solver.get_B(),
D_adj=solver.get_B_adj(),
b=solver.get_b(),
x0=solver.get_x0(),
alpha=solver.get_alpha(),
x_scale=solver.get_x_scale(),
data_loss=solver.get_data_loss(),
data_loss_scale=solver.get_data_loss_scale(),
iter_max=solver.get_iter_max(),
minimizer=solver.get_minimizer(),
iterations=args.iterations,
measures=args.measures,
dimension=3,
L2=16. / reconstruction_space.sitk.GetSpacing()[0]**2,
reconstruction_type=args.reconstruction_type,
rho=args.rho,
dir_output=args.dir_output,
parameters=parameters,
name=name,
reconstruction_info=reconstruction_info,
x_ref=x_ref,
x_ref_mask=x_ref_mask,
tv_solver=args.tv_solver,
verbose=args.verbose,
append=args.append,
)
parameter_study_interface.set_up_parameter_study()
parameter_study = parameter_study_interface.get_parameter_study()
# Run parameter study
parameter_study.run()
print("\nComputational time for Deconvolution Parameter Study %s: %s" %
(name, parameter_study.get_computational_time()))
return 0
def main():
time_start = ph.start_timing()
# Set print options for numpy
np.set_printoptions(precision=3)
input_parser = InputArgparser(
description="Propagate image mask using rigid registration.", )
input_parser.add_moving(required=True)
input_parser.add_moving_mask(required=True)
input_parser.add_fixed(required=True)
input_parser.add_output(required=True)
input_parser.add_v2v_method(
option_string="--method",
help="Registration method used for the registration (%s)." %
(", or ".join(V2V_METHOD_OPTIONS)),
default="RegAladin",
)
input_parser.add_option(
option_string="--use-moving-mask",
type=int,
help="Turn on/off use of moving mask to constrain the registration.",
default=0,
)
input_parser.add_dilation_radius(default=1)
input_parser.add_verbose(default=0)
input_parser.add_log_config(default=0)
args = input_parser.parse_args()
input_parser.print_arguments(args)
if np.alltrue([not args.output.endswith(t) for t in ALLOWED_EXTENSIONS]):
raise ValueError(
"output filename invalid; allowed extensions are: %s" %
", ".join(ALLOWED_EXTENSIONS))
if args.method not in V2V_METHOD_OPTIONS:
raise ValueError("method must be in {%s}" %
(", ".join(V2V_METHOD_OPTIONS)))
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
stack = st.Stack.from_filename(
file_path=args.fixed,
extract_slices=False,
)
template = st.Stack.from_filename(
file_path=args.moving,
file_path_mask=args.moving_mask,
extract_slices=False,
)
if args.method == "FLIRT":
# Define search angle ranges for FLIRT in all three dimensions
# search_angles = ["-searchr%s -%d %d" %
# (x, args.search_angle, args.search_angle)
# for x in ["x", "y", "z"]]
# options = (" ").join(search_angles)
# options += " -noresample"
registration = regflirt.FLIRT(
registration_type="Rigid",
fixed=stack,
moving=template,
use_fixed_mask=False,
use_moving_mask=args.use_moving_mask,
# options=options,
use_verbose=False,
)
else:
registration = niftyreg.RegAladin(
registration_type="Rigid",
fixed=stack,
moving=template,
use_fixed_mask=False,
use_moving_mask=args.use_moving_mask,
# options="-ln 2",
use_verbose=False,
)
try:
registration.run()
except RuntimeError as e:
raise RuntimeError(
"%s\n\n"
"Have you tried running the script with '--use-moving-mask 0'?" %
e)
transform_sitk = registration.get_registration_transform_sitk()
stack.sitk_mask = sitk.Resample(template.sitk_mask, stack.sitk_mask,
transform_sitk, sitk.sitkNearestNeighbor,
0, template.sitk_mask.GetPixelIDValue())
if args.dilation_radius > 0:
stack_mask_morpher = stmorph.StackMaskMorphologicalOperations.from_sitk_mask(
mask_sitk=stack.sitk_mask,
dilation_radius=args.dilation_radius,
dilation_kernel="Ball",
use_dilation_in_plane_only=True,
)
stack_mask_morpher.run_dilation()
stack.sitk_mask = stack_mask_morpher.get_processed_mask_sitk()
dw.DataWriter.write_mask(stack.sitk_mask, args.output)
elapsed_time = ph.stop_timing(time_start)
if args.verbose:
ph.show_nifti(args.fixed, segmentation=args.output)
ph.print_title("Summary")
exe_file_info = os.path.basename(os.path.abspath(__file__)).split(".")[0]
print("%s | Computational Time for Segmentation Propagation: %s" %
(exe_file_info, elapsed_time))
return 0
