def test_read_transformations(self):
directory_motion_correction = os.path.join(
DIR_TEST,
"case-studies",
"fetal-brain",
"reconstruct_volume",
"motion_correction",
)
data_reader = dr.MultipleImagesReader(
file_paths=self.filenames,
dir_motion_correction=directory_motion_correction)
data_reader.read_data()
stacks = data_reader.get_data()
data_reader = dr.SliceTransformationDirectoryReader(
directory_motion_correction)
data_reader.read_data()
transformations_dic = data_reader.get_data()
self.assertEqual(len(stacks) - len(transformations_dic.keys()), 0)
for stack in stacks:
N_slices = stack.get_number_of_slices()
N_slices2 = len(transformations_dic[stack.get_filename()].keys())
self.assertEqual(N_slices - N_slices2, 0)
def main():
input_parser = InputArgparser(
description="Show data/slice coverage over specified reconstruction "
"space.", )
input_parser.add_filenames(required=True)
input_parser.add_reconstruction_space(required=True)
input_parser.add_output(required=True)
input_parser.add_dir_input_mc()
input_parser.add_slice_thicknesses()
input_parser.add_verbose(default=0)
args = input_parser.parse_args()
input_parser.print_arguments(args)
data_reader = dr.MultipleImagesReader(
file_paths=args.filenames,
dir_motion_correction=args.dir_input_mc,
stacks_slice_thicknesses=args.slice_thicknesses,
)
data_reader.read_data()
stacks = data_reader.get_data()
reconstruction_space_sitk = sitk.ReadImage(args.reconstruction_space)
slice_coverage = sc.SliceCoverage(
stacks=stacks,
reconstruction_sitk=reconstruction_space_sitk,
)
slice_coverage.run()
coverage_sitk = slice_coverage.get_coverage_sitk()
dw.DataWriter.write_mask(coverage_sitk, args.output)
if args.verbose:
niftis = [
args.reconstruction_space,
args.output,
]
ph.show_niftis(niftis)
def test_forward_operator_stack(self):
data_reader = dr.MultipleImagesReader(self.paths_to_filenames,
suffix_mask=self.suffix_mask)
data_reader.read_data()
stacks = data_reader.get_data()
stack = stacks[0]
reconstruction = st.Stack.from_filename(self.path_to_recon,
self.path_to_recon_mask)
linear_operators = lin_op.LinearOperators()
simulated_stack = linear_operators.A(reconstruction,
stack,
interpolator_mask="Linear")
simulated_stack.set_filename(stack.get_filename() + "_sim")
# sitkh.show_stacks([stack, simulated_stack])
# simulated_stack.show(1)
# reconstruction.show(1)
# stack.show(1)
filename_reference = "IC_N4ITK_HASTE_exam_3.5mm_800ms_3_simulated"
reference_simulated_stack = st.Stack.from_filename(
os.path.join(self.dir_data, "result-comparison",
filename_reference + ".nii.gz"),
os.path.join(self.dir_data, "result-comparison",
filename_reference + self.suffix_mask + ".nii.gz"))
# Error simulated stack
difference_sitk = simulated_stack.sitk - \
reference_simulated_stack.sitk
error = np.linalg.norm(sitk.GetArrayFromImage(difference_sitk))
self.assertAlmostEqual(error, 0, places=self.precision)
# Error propagated mask
difference_sitk = simulated_stack.sitk_mask - \
reference_simulated_stack.sitk_mask
error = np.linalg.norm(sitk.GetArrayFromImage(difference_sitk))
self.assertAlmostEqual(error, 0, places=self.precision)
def main():
input_parser = InputArgparser(
description="Simulate stacks from obtained reconstruction. "
"Script simulates/projects the slices at estimated positions "
"within reconstructed volume. Ideally, if motion correction was "
"correct, the resulting stack of such obtained projected slices, "
"corresponds to the originally acquired (motion corrupted) data.",
)
input_parser.add_filenames(required=True)
input_parser.add_filenames_masks()
input_parser.add_dir_input_mc(required=True)
input_parser.add_reconstruction(required=True)
input_parser.add_dir_output(required=True)
input_parser.add_suffix_mask(default="_mask")
input_parser.add_prefix_output(default="Simulated_")
input_parser.add_option(
option_string="--copy-data",
type=int,
help="Turn on/off copying of original data (including masks) to "
"output folder.",
default=0)
input_parser.add_option(
option_string="--reconstruction-mask",
type=str,
help="If given, reconstruction image mask is propagated to "
"simulated stack(s) of slices as well",
default=None)
input_parser.add_interpolator(
option_string="--interpolator-mask",
help="Choose the interpolator type to propagate the reconstruction "
"mask (%s)." % (INTERPOLATOR_TYPES),
default="NearestNeighbor")
input_parser.add_log_config(default=0)
input_parser.add_verbose(default=0)
input_parser.add_slice_thicknesses(default=None)
args = input_parser.parse_args()
input_parser.print_arguments(args)
if args.interpolator_mask not in ALLOWED_INTERPOLATORS:
raise IOError(
"Unknown interpolator provided. Possible choices are %s" % (
INTERPOLATOR_TYPES))
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
# Read motion corrected 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()
reconstruction = st.Stack.from_filename(
args.reconstruction, args.reconstruction_mask, extract_slices=False)
linear_operators = lin_op.LinearOperators()
for i, stack in enumerate(stacks):
# initialize image data array(s)
nda = np.zeros_like(sitk.GetArrayFromImage(stack.sitk))
nda[:] = np.nan
if args.reconstruction_mask:
nda_mask = np.zeros_like(sitk.GetArrayFromImage(stack.sitk_mask))
slices = stack.get_slices()
kept_indices = [s.get_slice_number() for s in slices]
# Fill stack information "as if slice was acquired consecutively"
# Therefore, simulated stack slices correspond to acquired slices
# (in case motion correction was correct)
for j in range(nda.shape[0]):
if j in kept_indices:
index = kept_indices.index(j)
simulated_slice = linear_operators.A(
reconstruction,
slices[index],
interpolator_mask=args.interpolator_mask
)
nda[j, :, :] = sitk.GetArrayFromImage(simulated_slice.sitk)
if args.reconstruction_mask:
nda_mask[j, :, :] = sitk.GetArrayFromImage(
simulated_slice.sitk_mask)
# Create nifti image with same image header as original stack
simulated_stack_sitk = sitk.GetImageFromArray(nda)
simulated_stack_sitk.CopyInformation(stack.sitk)
if args.reconstruction_mask:
simulated_stack_sitk_mask = sitk.GetImageFromArray(nda_mask)
simulated_stack_sitk_mask.CopyInformation(stack.sitk_mask)
else:
simulated_stack_sitk_mask = None
simulated_stack = st.Stack.from_sitk_image(
image_sitk=simulated_stack_sitk,
image_sitk_mask=simulated_stack_sitk_mask,
filename=args.prefix_output + stack.get_filename(),
extract_slices=False,
slice_thickness=stack.get_slice_thickness(),
)
if args.verbose:
sitkh.show_stacks([
stack, simulated_stack],
segmentation=stack)
simulated_stack.write(
args.dir_output,
write_mask=False,
write_slices=False,
suffix_mask=args.suffix_mask)
if args.copy_data:
stack.write(
args.dir_output,
write_mask=True,
write_slices=False,
suffix_mask="_mask")
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()
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():
# Set print options
np.set_printoptions(precision=3)
pd.set_option('display.width', 1000)
input_parser = InputArgparser(description=".", )
input_parser.add_filenames(required=True)
input_parser.add_reference(required=True)
input_parser.add_reference_mask()
input_parser.add_dir_output(required=False)
input_parser.add_measures(
default=["PSNR", "RMSE", "MAE", "SSIM", "NCC", "NMI"])
input_parser.add_verbose(default=0)
args = input_parser.parse_args()
input_parser.print_arguments(args)
ph.print_title("Image similarity")
data_reader = dr.MultipleImagesReader(args.filenames)
data_reader.read_data()
stacks = data_reader.get_data()
reference = st.Stack.from_filename(args.reference, args.reference_mask)
for stack in stacks:
try:
stack.sitk - reference.sitk
except RuntimeError as e:
raise IOError(
"All provided images must be at the same image space")
x_ref = sitk.GetArrayFromImage(reference.sitk)
if args.reference_mask is None:
indices = np.where(x_ref != np.inf)
else:
x_ref_mask = sitk.GetArrayFromImage(reference.sitk_mask)
indices = np.where(x_ref_mask > 0)
measures_dic = {
m: lambda x, m=m: SimilarityMeasures.similarity_measures[m]
(x[indices], x_ref[indices])
# SimilarityMeasures.similarity_measures[m](x, x_ref)
for m in args.measures
}
observer = obs.Observer()
observer.set_measures(measures_dic)
for stack in stacks:
nda = sitk.GetArrayFromImage(stack.sitk)
observer.add_x(nda)
if args.verbose:
stacks_comparison = [s for s in stacks]
stacks_comparison.insert(0, reference)
sitkh.show_stacks(
stacks_comparison,
segmentation=reference,
)
observer.compute_measures()
measures = observer.get_measures()
# Store information in array
error = np.zeros((len(stacks), len(measures)))
cols = measures
rows = []
for i_stack, stack in enumerate(stacks):
error[i_stack, :] = np.array([measures[m][i_stack] for m in measures])
rows.append(stack.get_filename())
header = "# Ref: %s, Ref-Mask: %d, %s \n" % (
reference.get_filename(),
args.reference_mask is None,
ph.get_time_stamp(),
)
header += "# %s\n" % ("\t").join(measures)
path_to_file_filenames = os.path.join(args.dir_output, "filenames.txt")
path_to_file_similarities = os.path.join(args.dir_output,
"similarities.txt")
# Write to files
ph.write_to_file(path_to_file_similarities, header)
ph.write_array_to_file(path_to_file_similarities, error, verbose=False)
text = header
text += "%s\n" % "\n".join(rows)
ph.write_to_file(path_to_file_filenames, text)
# Print to screen
ph.print_subtitle("Computed Similarities")
df = pd.DataFrame(error, rows, cols)
print(df)
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()
# 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()
# Set print options
np.set_printoptions(precision=3)
pd.set_option('display.width', 1000)
input_parser = InputArgparser(description=".", )
input_parser.add_filenames()
input_parser.add_filenames_masks()
input_parser.add_dir_input_mc()
input_parser.add_suffix_mask(default="_mask")
input_parser.add_reference(required=True)
input_parser.add_reference_mask()
input_parser.add_dir_output(required=False)
input_parser.add_log_config(default=1)
input_parser.add_measures(default=["PSNR", "RMSE", "SSIM", "NCC", "NMI"])
input_parser.add_verbose(default=0)
input_parser.add_slice_thicknesses(default=None)
input_parser.add_option(option_string="--use-reference-mask",
type=int,
default=1)
input_parser.add_option(option_string="--use-slice-masks",
type=int,
default=1)
args = input_parser.parse_args()
input_parser.print_arguments(args)
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))
reference = st.Stack.from_filename(args.reference, args.reference_mask)
ph.print_title("Slice Residual Similarity")
residual_evaluator = res_ev.ResidualEvaluator(
stacks=stacks,
reference=reference,
measures=args.measures,
use_reference_mask=args.use_reference_mask,
use_slice_masks=args.use_slice_masks,
)
residual_evaluator.compute_slice_projections()
residual_evaluator.evaluate_slice_similarities()
residual_evaluator.write_slice_similarities(args.dir_output)
elapsed_time = ph.stop_timing(time_start)
ph.print_title("Summary")
print("Computational Time for Slice Residual Evaluation: %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="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_filenames(required=True)
input_parser.add_filenames_masks()
input_parser.add_dir_input_mc()
input_parser.add_output(required=True)
input_parser.add_suffix_mask(default="_mask")
input_parser.add_target_stack(default=None)
input_parser.add_extra_frame_target(default=10)
input_parser.add_isotropic_resolution(default=None)
input_parser.add_intensity_correction(default=1)
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=0.01 # 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_log_config(default=1)
input_parser.add_use_masks_srr(default=0)
input_parser.add_slice_thicknesses(default=None)
input_parser.add_verbose(default=0)
input_parser.add_viewer(default="itksnap")
input_parser.add_argument(
"--mask",
"-mask",
action='store_true',
help="If given, input images are interpreted as image masks. "
"Obtained volumetric reconstruction will be exported in uint8 format.")
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.reconstruction_type not in ["TK1L2", "TVL2", "HuberL2"]:
raise IOError("Reconstruction type unknown")
if np.alltrue([not args.output.endswith(t) for t in ALLOWED_EXTENSIONS]):
raise ValueError("output filename '%s' invalid; "
"allowed image extensions are: %s" %
(args.output, ", ".join(ALLOWED_EXTENSIONS)))
dir_output = os.path.dirname(args.output)
ph.create_directory(dir_output)
if args.log_config:
input_parser.log_config(os.path.abspath(__file__))
if args.verbose:
show_niftis = []
# show_niftis = [f for f in args.filenames]
# --------------------------------Read Data--------------------------------
ph.print_title("Read Data")
if args.mask:
filenames_masks = args.filenames
else:
filenames_masks = args.filenames_masks
data_reader = dr.MultipleImagesReader(
file_paths=args.filenames,
file_paths_masks=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))
# Specify target stack for intensity correction and reconstruction space
if args.target_stack is None:
target_stack_index = 0
else:
filenames = ["%s.nii.gz" % s.get_filename() for s in stacks]
filename_target_stack = os.path.basename(args.target_stack)
try:
target_stack_index = filenames.index(filename_target_stack)
except ValueError as e:
raise ValueError(
"--target-stack must correspond to an image as provided by "
"--filenames")
# ---------------------------Intensity Correction--------------------------
if args.intensity_correction and not args.mask:
ph.print_title("Intensity Correction")
intensity_corrector = ic.IntensityCorrection()
intensity_corrector.use_individual_slice_correction(False)
intensity_corrector.use_stack_mask(True)
intensity_corrector.use_reference_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())
# -------------------------Volumetric Reconstruction-----------------------
ph.print_title("Volumetric Reconstruction")
# Reconstruction space is given isotropically resampled target stack
if args.reconstruction_space is None:
recon0 = stacks[target_stack_index].get_isotropically_resampled_stack(
resolution=args.isotropic_resolution,
extra_frame=args.extra_frame_target)
recon0 = recon0.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",
)
# 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[target_stack_index].get_resampled_stack(recon0.sitk)
recon0 = recon0.get_stack_multiplied_with_mask()
ph.print_info("Reconstruction space defined with %s mm3 resolution" %
" x ".join(["%.2f" % s for s in recon0.sitk.GetSpacing()]))
if args.sda:
ph.print_title("Compute SDA reconstruction")
SDA = sda.ScatteredDataApproximation(stacks,
recon0,
sigma=args.alpha,
sda_mask=args.mask)
SDA.run()
recon = SDA.get_reconstruction()
if args.mask:
dw.DataWriter.write_mask(recon.sitk_mask, args.output)
else:
dw.DataWriter.write_image(recon.sitk, args.output)
if args.verbose:
show_niftis.insert(0, args.output)
else:
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=np.min([5, args.iter_max]),
reg_type="TK1",
minimizer="lsmr",
data_loss="linear",
use_masks=args.use_masks_srr,
# verbose=args.verbose,
)
else:
ph.print_title("Compute %s reconstruction" %
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,
use_masks=args.use_masks_srr,
# verbose=args.verbose,
)
SRR0.run()
recon = SRR0.get_reconstruction()
if args.reconstruction_type in ["TVL2", "HuberL2"]:
output = ph.append_to_filename(args.output, "_initTK1L2")
else:
output = args.output
if args.mask:
mask_estimator = bm.BinaryMaskFromMaskSRREstimator(recon.sitk)
mask_estimator.run()
mask_sitk = mask_estimator.get_mask_sitk()
dw.DataWriter.write_mask(mask_sitk, output)
else:
dw.DataWriter.write_image(recon.sitk, output)
if args.verbose:
show_niftis.insert(0, output)
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,
use_masks=args.use_masks_srr,
verbose=args.verbose,
)
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,
use_masks=args.use_masks_srr,
verbose=args.verbose,
)
SRR.run()
recon = SRR.get_reconstruction()
if args.mask:
mask_estimator = bm.BinaryMaskFromMaskSRREstimator(recon.sitk)
mask_estimator.run()
mask_sitk = mask_estimator.get_mask_sitk()
dw.DataWriter.write_mask(mask_sitk, args.output)
else:
dw.DataWriter.write_image(recon.sitk, args.output)
if args.verbose:
show_niftis.insert(0, args.output)
if args.verbose:
ph.show_niftis(show_niftis, viewer=args.viewer)
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="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,
nargs="+",
help="Specify moving image to be warped to fixed space. "
"If multiple images are provided, all images will be transformed "
"uniformly according to the registration obtained for the first one.")
input_parser.add_dir_output(required=True)
input_parser.add_dir_input()
input_parser.add_suffix_mask(default="_mask")
input_parser.add_search_angle(default=180)
input_parser.add_option(
option_string="--transform-only",
type=int,
help="Turn on/off functionality to transform moving image(s) to fixed "
"image only, i.e. no resampling to fixed image space",
default=0)
input_parser.add_option(
option_string="--write-transform",
type=int,
help="Turn on/off functionality to write registration transform",
default=0)
input_parser.add_verbose(default=0)
args = input_parser.parse_args()
input_parser.print_arguments(args)
use_reg_aladin_for_refinement = True
# --------------------------------Read Data--------------------------------
ph.print_title("Read Data")
data_reader = dr.MultipleImagesReader(args.moving, suffix_mask="_mask")
data_reader.read_data()
moving = data_reader.get_data()
data_reader = dr.MultipleImagesReader([args.fixed], suffix_mask="_mask")
data_reader.read_data()
fixed = data_reader.get_data()[0]
# -------------------Register Reconstruction to Template-------------------
ph.print_title("Register Reconstruction to Template")
# 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)
options_args = []
options_args.append(search_angles)
# cost = "mutualinfo"
# options_args.append("-searchcost %s -cost %s" % (cost, cost))
registration = regflirt.FLIRT(
fixed=moving[0],
moving=fixed,
# use_fixed_mask=True,
# use_moving_mask=True, # moving mask only seems to work for SB cases
registration_type="Rigid",
use_verbose=False,
options=(" ").join(options_args),
)
ph.print_info("Run Registration (FLIRT) ... ", newline=False)
registration.run()
print("done")
transform_sitk = registration.get_registration_transform_sitk()
if args.write_transform:
path_to_transform = os.path.join(args.dir_output,
"registration_transform_sitk.txt")
sitk.WriteTransform(transform_sitk, path_to_transform)
# Apply rigidly transform to align reconstruction (moving) with template
# (fixed)
for m in moving:
m.update_motion_correction(transform_sitk)
# 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 use_reg_aladin_for_refinement:
registration = niftyreg.RegAladin(
fixed=m,
use_fixed_mask=True,
moving=fixed,
registration_type="Rigid",
use_verbose=False,
)
ph.print_info("Run Registration (RegAladin) ... ", newline=False)
registration.run()
print("done")
transform2_sitk = registration.get_registration_transform_sitk()
m.update_motion_correction(transform2_sitk)
transform_sitk = sitkh.get_composite_sitk_affine_transform(
transform2_sitk, transform_sitk)
if args.transform_only:
for m in moving:
m.write(args.dir_output, write_mask=False)
ph.exit()
# Resample reconstruction (moving) to template space (fixed)
warped_moving = [
m.get_resampled_stack(fixed.sitk, interpolator="Linear")
for m in moving
]
for wm in warped_moving:
wm.set_filename(wm.get_filename() + "ResamplingToTemplateSpace")
if args.verbose:
sitkh.show_stacks([fixed, wm], segmentation=fixed)
# Write resampled reconstruction (moving)
wm.write(args.dir_output, write_mask=False)
if args.dir_input is not None:
data_reader = dr.ImageSlicesDirectoryReader(
path_to_directory=args.dir_input, suffix_mask=args.suffix_mask)
data_reader.read_data()
stacks = data_reader.get_data()
for i, stack in enumerate(stacks):
stack.update_motion_correction(transform_sitk)
ph.print_info("Stack %d/%d: All slice transforms updated" %
(i + 1, len(stacks)))
# Write transformed slices
stack.write(
os.path.join(args.dir_output, "motion_correction"),
write_mask=True,
write_slices=True,
write_transforms=True,
suffix_mask=args.suffix_mask,
)
elapsed_time_total = ph.stop_timing(time_start)
# Summary
ph.print_title("Summary")
print("Computational Time: %s" % (elapsed_time_total))
return 0
def main():
# Read input
input_parser = InputArgparser(
description="Script to evaluate the similarity of simulated stack "
"from obtained reconstruction against the original stack. "
"This function takes the result of "
"simulate_stacks_from_reconstruction.py as input.", )
input_parser.add_filenames(required=True)
input_parser.add_filenames_masks()
input_parser.add_dir_output(required=True)
input_parser.add_suffix_mask(default="_mask")
input_parser.add_measures(default=["NCC", "SSIM"])
input_parser.add_option(
option_string="--prefix-simulated",
type=str,
help="Specify the prefix of the simulated stacks to distinguish them "
"from the original data.",
default="Simulated_",
)
input_parser.add_option(
option_string="--dir-input-simulated",
type=str,
help="Specify the directory where the simulated stacks are. "
"If not given, it is assumed that they are in the same directory "
"as the original ones.",
default=None)
input_parser.add_slice_thicknesses(default=None)
args = input_parser.parse_args()
input_parser.print_arguments(args)
# --------------------------------Read Data--------------------------------
ph.print_title("Read Data")
# Read original data
filenames_original = args.filenames
data_reader = dr.MultipleImagesReader(
file_paths=filenames_original,
file_paths_masks=args.filenames_masks,
suffix_mask=args.suffix_mask,
stacks_slice_thicknesses=args.slice_thicknesses,
)
data_reader.read_data()
stacks_original = data_reader.get_data()
# Read data simulated from obtained reconstruction
if args.dir_input_simulated is None:
dir_input_simulated = os.path.dirname(filenames_original[0])
else:
dir_input_simulated = args.dir_input_simulated
filenames_simulated = [
os.path.join("%s", "%s%s") %
(dir_input_simulated, args.prefix_simulated, os.path.basename(f))
for f in filenames_original
]
data_reader = dr.MultipleImagesReader(filenames_simulated,
suffix_mask=args.suffix_mask)
data_reader.read_data()
stacks_simulated = data_reader.get_data()
for i in range(len(stacks_original)):
try:
stacks_original[i].sitk - stacks_simulated[i].sitk
except:
raise IOError(
"Images '%s' and '%s' do not occupy the same space!" %
(filenames_original[i], filenames_simulated[i]))
similarity_measures = {
m: SimilarityMeasures.similarity_measures[m]
for m in args.measures
}
similarities = np.zeros(len(args.measures))
for i in range(len(stacks_original)):
nda_3D_original = sitk.GetArrayFromImage(stacks_original[i].sitk)
nda_3D_simulated = sitk.GetArrayFromImage(stacks_simulated[i].sitk)
nda_3D_mask = sitk.GetArrayFromImage(stacks_original[i].sitk_mask)
path_to_file = os.path.join(
args.dir_output,
"Similarity_%s.txt" % stacks_original[i].get_filename())
text = "# Similarity: %s vs %s (%s)." % (os.path.basename(
filenames_original[i]), os.path.basename(
filenames_simulated[i]), ph.get_time_stamp())
text += "\n#\t" + ("\t").join(args.measures)
text += "\n"
ph.write_to_file(path_to_file, text, "w")
for k in range(nda_3D_original.shape[0]):
x_2D_original = nda_3D_original[k, :, :]
x_2D_simulated = nda_3D_simulated[k, :, :]
# zero slice, i.e. rejected during motion correction
if np.abs(x_2D_simulated).sum() < 1e-6:
x_2D_simulated[:] = np.nan
x_2D_mask = nda_3D_mask[k, :, :]
indices = np.where(x_2D_mask > 0)
for m, measure in enumerate(args.measures):
if len(indices[0]) > 0:
similarities[m] = similarity_measures[measure](
x_2D_original[indices], x_2D_simulated[indices])
else:
similarities[m] = np.nan
ph.write_array_to_file(path_to_file, similarities.reshape(1, -1))
return 0
def main():
input_parser = InputArgparser(
description="Script to export a side-by-side comparison of originally "
"acquired and simulated/projected slice given the estimated "
"volumetric reconstruction."
"This function takes the result of "
"simulate_stacks_from_reconstruction.py as input.", )
input_parser.add_filenames(required=True)
input_parser.add_dir_output(required=True)
input_parser.add_option(
option_string="--prefix-simulated",
type=str,
help="Specify the prefix of the simulated stacks to distinguish them "
"from the original data.",
default="Simulated_",
)
input_parser.add_option(
option_string="--dir-input-simulated",
type=str,
help="Specify the directory where the simulated stacks are. "
"If not given, it is assumed that they are in the same directory "
"as the original ones.",
default=None)
input_parser.add_option(
option_string="--resize",
type=float,
help="Factor to resize images (otherwise they might be very small "
"depending on the FOV)",
default=3)
args = input_parser.parse_args()
input_parser.print_arguments(args)
# --------------------------------Read Data--------------------------------
ph.print_title("Read Data")
# Read original data
filenames_original = args.filenames
data_reader = dr.MultipleImagesReader(filenames_original)
data_reader.read_data()
stacks_original = data_reader.get_data()
# Read data simulated from obtained reconstruction
if args.dir_input_simulated is None:
dir_input_simulated = os.path.dirname(filenames_original[0])
else:
dir_input_simulated = args.dir_input_simulated
filenames_simulated = [
os.path.join("%s", "%s%s") %
(dir_input_simulated, args.prefix_simulated, os.path.basename(f))
for f in filenames_original
]
data_reader = dr.MultipleImagesReader(filenames_simulated)
data_reader.read_data()
stacks_simulated = data_reader.get_data()
ph.create_directory(args.dir_output)
for i in range(len(stacks_original)):
try:
stacks_original[i].sitk - stacks_simulated[i].sitk
except:
raise IOError(
"Images '%s' and '%s' do not occupy the same space!" %
(filenames_original[i], filenames_simulated[i]))
# ---------------------Create side-by-side comparisons---------------------
ph.print_title("Create side-by-side comparisons")
intensity_max = 255
intensity_min = 0
for i in range(len(stacks_original)):
ph.print_subtitle("Stack %d/%d" % (i + 1, len(stacks_original)))
nda_3D_original = sitk.GetArrayFromImage(stacks_original[i].sitk)
nda_3D_simulated = sitk.GetArrayFromImage(stacks_simulated[i].sitk)
# Scale uniformly between 0 and 255 according to the simulated stack
# for export to png
scale = np.max(nda_3D_simulated)
nda_3D_original = intensity_max * nda_3D_original / scale
nda_3D_simulated = intensity_max * nda_3D_simulated / scale
nda_3D_simulated = np.clip(nda_3D_simulated, intensity_min,
intensity_max)
nda_3D_original = np.clip(nda_3D_original, intensity_min,
intensity_max)
filename = stacks_original[i].get_filename()
path_to_file = os.path.join(args.dir_output, "%s.pdf" % filename)
# Export side-by-side comparison of each stack to a pdf file
export_comparison_to_file(nda_3D_original,
nda_3D_simulated,
path_to_file,
resize=args.resize)
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 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
np.set_printoptions(precision=3)
pd.set_option('display.width', 1000)
input_parser = InputArgparser(
description=".",
)
input_parser.add_filenames()
input_parser.add_filenames_masks()
input_parser.add_dir_input_mc()
input_parser.add_suffix_mask(default="_mask")
input_parser.add_reference(required=True)
input_parser.add_reference_mask()
input_parser.add_dir_output(required=False)
input_parser.add_log_config(default=1)
input_parser.add_measures(
default=["PSNR", "MAE", "RMSE", "SSIM", "NCC", "NMI"])
input_parser.add_verbose(default=0)
input_parser.add_target_stack(default=None)
input_parser.add_intensity_correction(default=1)
input_parser.add_slice_thicknesses(default=None)
input_parser.add_option(
option_string="--use-reference-mask", type=int, default=1)
input_parser.add_option(
option_string="--use-slice-masks", type=int, default=1)
args = input_parser.parse_args()
input_parser.print_arguments(args)
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))
# Specify target stack for intensity correction and reconstruction space
if args.target_stack is None:
target_stack_index = 0
else:
filenames = ["%s.nii.gz" % s.get_filename() for s in stacks]
filename_target_stack = os.path.basename(args.target_stack)
try:
target_stack_index = filenames.index(filename_target_stack)
except ValueError as e:
raise ValueError(
"--target-stack must correspond to an image as provided by "
"--filenames")
# ---------------------------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_stack_mask(True)
intensity_corrector.use_reference_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())
# ----------------------- Slice Residual Similarity -----------------------
reference = st.Stack.from_filename(args.reference, args.reference_mask)
ph.print_title("Slice Residual Similarity")
residual_evaluator = res_ev.ResidualEvaluator(
stacks=stacks,
reference=reference,
measures=args.measures,
use_reference_mask=args.use_reference_mask,
use_slice_masks=args.use_slice_masks,
)
residual_evaluator.compute_slice_projections()
residual_evaluator.evaluate_slice_similarities()
residual_evaluator.write_slice_similarities(args.dir_output)
elapsed_time = ph.stop_timing(time_start)
ph.print_title("Summary")
print("Computational Time for Slice Residual Evaluation: %s" %
(elapsed_time))
return 0
