def watershed(operator, step_pct, input_image, level):
import itk
from tomviz import itkutils
dimension = input_image.GetImageDimension()
watershed_input_type = itk.Image[itk.F, dimension]
watershed_output_type = itk.Image[itk.US, dimension]
caster = itk.CastImageFilter[type(input_image), watershed_input_type].New()
caster.SetInput(input_image)
watershed_filter = \
itk.MorphologicalWatershedImageFilter[
watershed_input_type,
watershed_output_type].New(Input=caster.GetOutput())
watershed_filter.SetLevel(level)
watershed_filter.SetMarkWatershedLine(True)
watershed_filter.SetFullyConnected(True)
operator.progress.message = "Watershed filter"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, watershed_filter,
progress, progress + next(step_pct))
try:
watershed_filter.Update()
except RuntimeError:
return
return watershed_filter.GetOutput()
def watershed(operator, step_pct, input_image, level):
import itk
from tomviz import itkutils
dimension = input_image.GetImageDimension()
watershed_input_type = itk.Image[itk.F, dimension]
watershed_output_type = itk.Image[itk.US, dimension]
caster = itk.CastImageFilter[type(input_image), watershed_input_type].New()
caster.SetInput(input_image)
watershed_filter = \
itk.MorphologicalWatershedImageFilter[
watershed_input_type,
watershed_output_type].New(Input=caster.GetOutput())
watershed_filter.SetLevel(level)
watershed_filter.SetMarkWatershedLine(True)
watershed_filter.SetFullyConnected(True)
operator.progress.message = "Watershed filter"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, watershed_filter, progress,
progress + next(step_pct))
try:
watershed_filter.Update()
except RuntimeError:
return
return watershed_filter.GetOutput()
def transform_scalars(self, dataset, amount=0.5, threshold=0.0,
sigma=1.0):
"""This filter performs anisotropic diffusion on an image using
the classic Perona-Malik, gradient magnitude-based equation.
"""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
step_pct = iter([10, 20, 90, 100])
try:
import itk
from tomviz import itkutils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
try:
self.progress.message = "Converting data to ITK image"
self.progress.value = 0
# Get the ITK image. The itk.GradientAnisotropicDiffusionImageFilter
# is templated over float pixel types only, so explicitly request a
# float ITK image type.
itk_image = itkutils.convert_vtk_to_itk_image(dataset)
self.progress.value = next(step_pct)
self.progress.message = "Running filter"
self.progress.value = next(step_pct)
unsharp_mask = \
itk.UnsharpMaskImageFilter.New(Input=itk_image)
unsharp_mask.SetAmount(amount)
unsharp_mask.SetThreshold(threshold)
unsharp_mask.SetSigma(sigma)
itkutils.observe_filter_progress(self, unsharp_mask,
self.progress.value,
next(step_pct))
try:
unsharp_mask.Update()
except RuntimeError:
return
self.progress.message = "Saving results"
enhanced = unsharp_mask.GetOutput()
itkutils.set_array_from_itk_image(dataset,
enhanced)
self.progress.value = next(step_pct)
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
def transform_scalars(self, dataset, amount=0.5, threshold=0.0, sigma=1.0):
"""This filter performs anisotropic diffusion on an image using
the classic Perona-Malik, gradient magnitude-based equation.
"""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
step_pct = iter([10, 20, 90, 100])
try:
import itk
from tomviz import itkutils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
try:
self.progress.message = "Converting data to ITK image"
self.progress.value = 0
# Get the ITK image. The itk.GradientAnisotropicDiffusionImageFilter
# is templated over float pixel types only, so explicitly request a
# float ITK image type.
itk_image = itkutils.convert_vtk_to_itk_image(dataset)
self.progress.value = next(step_pct)
self.progress.message = "Running filter"
self.progress.value = next(step_pct)
unsharp_mask = \
itk.UnsharpMaskImageFilter.New(Input=itk_image)
unsharp_mask.SetAmount(amount)
unsharp_mask.SetThreshold(threshold)
unsharp_mask.SetSigma(sigma)
itkutils.observe_filter_progress(self,
unsharp_mask, self.progress.value,
next(step_pct))
try:
unsharp_mask.Update()
except RuntimeError:
return
self.progress.message = "Saving results"
enhanced = unsharp_mask.GetOutput()
itkutils.set_array_from_itk_image(dataset, enhanced)
self.progress.value = next(step_pct)
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
def transform_scalars(self, dataset):
"""Define this method for Python operators that transform the input
array. This example uses an ITK filter to add 10 to each voxel value."""
# Try imports to make sure we have everything that is needed
try:
from tomviz import itkutils
import itk
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
self.progress.value = 0
self.progress.maximum = 100
# Add a try/except around the ITK portion. ITK exceptions are
# passed up to the Python layer, so we can at least report what
# went wrong with the script, e.g., unsupported image type.
try:
self.progress.value = 0
self.progress.message = "Converting data to ITK image"
# Get the ITK image
itk_image = itkutils.convert_vtk_to_itk_image(dataset)
itk_input_image_type = type(itk_image)
self.progress.value = 30
self.progress.message = "Running filter"
# ITK filter
filter = itk.AddImageFilter[itk_input_image_type, # Input 1
itk_input_image_type, # Input 2
itk_input_image_type].New() # Output
filter.SetInput1(itk_image)
filter.SetConstant2(10)
itkutils.observe_filter_progress(self, filter, 30, 70)
try:
filter.Update()
except RuntimeError: # Exception thrown when ITK filter is aborted
return
self.progress.message = "Saving results"
itkutils.set_array_from_itk_image(dataset, filter.GetOutput())
self.progress.value = 100
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
def transform(self, dataset):
"""Define this method for Python operators that transform the input
array. This example uses an ITK filter to add 10 to each voxel value."""
# Try imports to make sure we have everything that is needed
try:
from tomviz import itkutils
import itk
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
self.progress.value = 0
self.progress.maximum = 100
# Add a try/except around the ITK portion. ITK exceptions are
# passed up to the Python layer, so we can at least report what
# went wrong with the script, e.g., unsupported image type.
try:
self.progress.value = 0
self.progress.message = "Converting data to ITK image"
# Get the ITK image
itk_image = itkutils.dataset_to_itk_image(dataset)
itk_input_image_type = type(itk_image)
self.progress.value = 30
self.progress.message = "Running filter"
# ITK filter
filter = itk.AddImageFilter[itk_input_image_type, # Input 1
itk_input_image_type, # Input 2
itk_input_image_type].New() # Output
filter.SetInput1(itk_image)
filter.SetConstant2(10)
itkutils.observe_filter_progress(self, filter, 30, 70)
try:
filter.Update()
except RuntimeError: # Exception thrown when ITK filter is aborted
return
self.progress.message = "Saving results"
itkutils.set_itk_image_on_dataset(filter.GetOutput(), dataset)
self.progress.value = 100
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
def fill_holes(operator, step_pct, input_image):
import itk
from tomviz import itkutils
fill_hole = \
itk.GrayscaleFillholeImageFilter.New(Input=input_image)
operator.progress.message = "Fill holes"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, fill_hole, progress,
progress + next(step_pct))
try:
fill_hole.Update()
except RuntimeError:
return
return fill_hole.GetOutput()
def threshold(operator, step_pct, input_image):
import itk
from tomviz import itkutils
import itkExtras
import itkTypes
otsu_filter = \
itk.OtsuMultipleThresholdsImageFilter.New(Input=input_image)
otsu_filter.SetNumberOfThresholds(1)
operator.progress.message = "Otsu threshold"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, otsu_filter,
progress, progress + next(step_pct))
try:
otsu_filter.Update()
except RuntimeError:
return
# Cast threshold output to an integral type if needed.
input_image_type = type(input_image)
voxel_type = itkExtras.template(input_image_type)[1][0]
if voxel_type is itkTypes.F or voxel_type is itkTypes.D:
operator.progress.message = "Casting output to integral type"
# Unsigned char supports 256 labels, or 255 threshold levels.
# This should be sufficient for all but the most unusual use
# cases.
dimension = input_image_type.GetImageDimension()
py_buffer_type = itk.Image[itk.UC, dimension]
caster = itk.CastImageFilter[input_image_type,
py_buffer_type].New()
caster.SetInput(thresholded)
progress = operator.progress.value
itkutils.observe_filter_progress(operator, caster,
progress, progress + next(step_pct))
try:
caster.Update()
except RuntimeError:
return
thresholded = caster.GetOutput()
thresholded = otsu_filter.GetOutput()
return thresholded
def invert(operator, step_pct, input_image):
import itk
from tomviz import itkutils
inverter = \
itk.NotImageFilter.New(Input=input_image)
operator.progress.message = "Invert threshold"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, inverter,
progress, progress + next(step_pct))
try:
inverter.Update()
except RuntimeError:
return
return inverter.GetOutput()
def invert(operator, step_pct, input_image):
import itk
from tomviz import itkutils
inverter = \
itk.NotImageFilter.New(Input=input_image)
operator.progress.message = "Invert threshold"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, inverter, progress,
progress + next(step_pct))
try:
inverter.Update()
except RuntimeError:
return
return inverter.GetOutput()
def fill_holes(operator, step_pct, input_image):
import itk
from tomviz import itkutils
fill_hole = \
itk.GrayscaleFillholeImageFilter.New(Input=input_image)
operator.progress.message = "Fill holes"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, fill_hole,
progress, progress + next(step_pct))
try:
fill_hole.Update()
except RuntimeError:
return
return fill_hole.GetOutput()
def threshold(operator, step_pct, input_image):
import itk
from tomviz import itkutils
import itkExtras
import itkTypes
otsu_filter = \
itk.OtsuMultipleThresholdsImageFilter.New(Input=input_image)
otsu_filter.SetNumberOfThresholds(1)
operator.progress.message = "Otsu threshold"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, otsu_filter, progress,
progress + next(step_pct))
try:
otsu_filter.Update()
except RuntimeError:
return
# Cast threshold output to an integral type if needed.
input_image_type = type(input_image)
voxel_type = itkExtras.template(input_image_type)[1][0]
if voxel_type is itkTypes.F or voxel_type is itkTypes.D:
operator.progress.message = "Casting output to integral type"
# Unsigned char supports 256 labels, or 255 threshold levels.
# This should be sufficient for all but the most unusual use
# cases.
dimension = input_image_type.GetImageDimension()
py_buffer_type = itk.Image[itk.UC, dimension]
caster = itk.CastImageFilter[input_image_type, py_buffer_type].New()
caster.SetInput(thresholded)
progress = operator.progress.value
itkutils.observe_filter_progress(operator, caster, progress,
progress + next(step_pct))
try:
caster.Update()
except RuntimeError:
return
thresholded = caster.GetOutput()
thresholded = otsu_filter.GetOutput()
return thresholded
def morphological_closing(operator, step_pct, input_image, structuring_element):
import itk
from tomviz import itkutils
closer = \
itk.GrayscaleMorphologicalClosingImageFilter.New(Input=input_image)
closer.SetKernel(structuring_element)
operator.progress.message = "Morphological closing"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, closer,
progress, progress + next(step_pct))
try:
closer.Update()
except RuntimeError:
return
return closer.GetOutput()
def morphological_closing(operator, step_pct, input_image, structuring_element):
import itk
from tomviz import itkutils
closer = \
itk.GrayscaleMorphologicalClosingImageFilter.New(Input=input_image)
closer.SetKernel(structuring_element)
operator.progress.message = "Morphological closing"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, closer,
progress, progress + next(step_pct))
try:
closer.Update()
except RuntimeError:
return
return closer.GetOutput()
def get_distance(operator, step_pct, input_image):
import itk
from tomviz import itkutils
distance_mapper = \
itk.SignedMaurerDistanceMapImageFilter.New(Input=input_image)
distance_mapper.SetInsideIsPositive(True)
distance_mapper.SetSquaredDistance(False)
distance_mapper.SetUseImageSpacing(True)
operator.progress.message = "Distance map"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, distance_mapper,
progress, progress + next(step_pct))
try:
distance_mapper.Update()
except RuntimeError:
return
return distance_mapper.GetOutput()
def opening_by_reconstruction(operator, step_pct, input_image,
structuring_element):
import itk
from tomviz import itkutils
opening = \
itk.OpeningByReconstructionImageFilter.New(Input=input_image)
opening.SetKernel(structuring_element)
operator.progress.message = "Opening by reconstruction"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, opening,
progress, progress + next(step_pct))
try:
opening.Update()
except RuntimeError:
return
return opening.GetOutput()
def median_filter(operator, step_pct, input_image):
import itk
from tomviz import itkutils
median_filter = \
itk.MedianImageFilter.New(Input=input_image)
median_radius = itk.Size[3]()
median_radius.Fill(1)
median_filter.SetRadius(median_radius)
operator.progress.message = "Median filter"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, median_filter,
progress, progress + next(step_pct))
try:
median_filter.Update()
except RuntimeError:
return
return median_filter.GetOutput()
def median_filter(operator, step_pct, input_image):
import itk
from tomviz import itkutils
median_filter = \
itk.MedianImageFilter.New(Input=input_image)
median_radius = itk.Size[3]()
median_radius.Fill(1)
median_filter.SetRadius(median_radius)
operator.progress.message = "Median filter"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, median_filter, progress,
progress + next(step_pct))
try:
median_filter.Update()
except RuntimeError:
return
return median_filter.GetOutput()
def get_distance(operator, step_pct, input_image):
import itk
from tomviz import itkutils
distance_mapper = \
itk.SignedMaurerDistanceMapImageFilter.New(Input=input_image)
distance_mapper.SetInsideIsPositive(True)
distance_mapper.SetSquaredDistance(False)
distance_mapper.SetUseImageSpacing(True)
operator.progress.message = "Distance map"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, distance_mapper, progress,
progress + next(step_pct))
try:
distance_mapper.Update()
except RuntimeError:
return
return distance_mapper.GetOutput()
def opening_by_reconstruction(operator, step_pct, input_image,
structuring_element):
import itk
from tomviz import itkutils
opening = \
itk.OpeningByReconstructionImageFilter.New(Input=input_image)
opening.SetKernel(structuring_element)
operator.progress.message = "Opening by reconstruction"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, opening, progress,
progress + next(step_pct))
try:
opening.Update()
except RuntimeError:
return
return opening.GetOutput()
def unsharp_mask(operator, step_pct, input_image):
import itk
from tomviz import itkutils
import numpy as np
enhancer = \
itk.UnsharpMaskImageFilter.New(Input=input_image)
enhancer.SetAmount(3.0)
spacing = input_image.GetSpacing()
enhancer.SetSigma(2.0 * np.max(spacing))
operator.progress.message = "Unsharp mask"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, enhancer,
progress, progress + next(step_pct))
try:
enhancer.Update()
except RuntimeError:
return
return enhancer.GetOutput()
def unsharp_mask(operator, step_pct, input_image):
import itk
from tomviz import itkutils
import numpy as np
enhancer = \
itk.UnsharpMaskImageFilter.New(Input=input_image)
enhancer.SetAmount(3.0)
spacing = input_image.GetSpacing()
enhancer.SetSigma(2.0 * np.max(spacing))
operator.progress.message = "Unsharp mask"
progress = operator.progress.value
itkutils.observe_filter_progress(operator, enhancer, progress,
progress + next(step_pct))
try:
enhancer.Update()
except RuntimeError:
return
return enhancer.GetOutput()
def encapsulate(operator, step_pct, input_image, mask, structuring_element):
import itk
from tomviz import itkutils
dilater = \
itk.GrayscaleDilateImageFilter.New(Input=input_image)
dilater.SetKernel(structuring_element)
operator.progress.message = "Encapsulate"
progress = operator.progress.value
nextprogress = progress + next(step_pct)
itkutils.observe_filter_progress(operator, dilater,
progress, nextprogress)
xor_filter = \
itk.XorImageFilter.New(Input1=mask, Input2=dilater.GetOutput())
progress = nextprogress
nextprogress = progress + next(step_pct)
itkutils.observe_filter_progress(operator, xor_filter,
progress, nextprogress)
or_filter = \
itk.OrImageFilter.New(Input1=input_image, Input2=xor_filter.GetOutput())
progress = nextprogress
nextprogress = progress + next(step_pct)
itkutils.observe_filter_progress(operator, or_filter,
progress, nextprogress)
try:
or_filter.Update()
except RuntimeError:
return
return or_filter.GetOutput()
def encapsulate(operator, step_pct, input_image, mask, structuring_element):
import itk
from tomviz import itkutils
dilater = \
itk.GrayscaleDilateImageFilter.New(Input=input_image)
dilater.SetKernel(structuring_element)
operator.progress.message = "Encapsulate"
progress = operator.progress.value
nextprogress = progress + next(step_pct)
itkutils.observe_filter_progress(operator, dilater, progress, nextprogress)
xor_filter = \
itk.XorImageFilter.New(Input1=mask, Input2=dilater.GetOutput())
progress = nextprogress
nextprogress = progress + next(step_pct)
itkutils.observe_filter_progress(operator, xor_filter, progress,
nextprogress)
or_filter = \
itk.OrImageFilter.New(Input1=input_image, Input2=xor_filter.GetOutput())
progress = nextprogress
nextprogress = progress + next(step_pct)
itkutils.observe_filter_progress(operator, or_filter, progress,
nextprogress)
try:
or_filter.Update()
except RuntimeError:
return
return or_filter.GetOutput()
def transform_scalars(self,
dataset,
conductance=1.0,
iterations=100,
timestep=0.0625):
"""This filter performs anisotropic diffusion on an image using
the classic Perona-Malik, gradient magnitude-based equation.
"""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
STEP_PCT = [10, 20, 90, 100]
try:
import itk
import itkTypes
from tomviz import itkutils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
try:
self.progress.value = STEP_PCT[0]
self.progress.message = "Converting data to ITK image"
# Get the ITK image. The itk.GradientAnisotropicDiffusionImageFilter
# is templated over float pixel types only, so explicitly request a
# float ITK image type.
itk_image = itkutils.convert_vtk_to_itk_image(dataset, itkTypes.F)
itk_image_type = type(itk_image)
self.progress.value = STEP_PCT[1]
self.progress.message = "Running filter"
DiffusionFilterType = \
itk.GradientAnisotropicDiffusionImageFilter[itk_image_type,
itk_image_type]
diffusion_filter = DiffusionFilterType.New()
diffusion_filter.SetConductanceParameter(conductance)
diffusion_filter.SetNumberOfIterations(iterations)
diffusion_filter.SetTimeStep(timestep)
diffusion_filter.SetInput(itk_image)
itkutils.observe_filter_progress(self, diffusion_filter,
STEP_PCT[1], STEP_PCT[2])
try:
diffusion_filter.Update()
except RuntimeError:
return
self.progress.message = "Saving results"
itkutils.set_array_from_itk_image(dataset,
diffusion_filter.GetOutput())
self.progress.value = STEP_PCT[3]
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
def transform_scalars(self, dataset, lower_threshold=40.0,
upper_threshold=255.0):
"""This filter computes a binary threshold on the data set and
stores the result in a child data set. It does not modify the dataset
passed in."""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
STEP_PCT = [20, 40, 75, 90, 100]
# Set up return value
returnValue = None
# Try imports to make sure we have everything that is needed
try:
self.progress.message = "Loading modules"
import itk
import vtk
from tomviz import itkutils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
# Add a try/except around the ITK portion. ITK exceptions are
# passed up to the Python layer, so we can at least report what
# went wrong with the script, e.g,, unsupported image type.
try:
self.progress.value = STEP_PCT[0]
self.progress.message = "Converting data to ITK image"
# Get the ITK image
itk_image = itkutils.convert_vtk_to_itk_image(dataset)
itk_input_image_type = type(itk_image)
self.progress.value = STEP_PCT[1]
self.progress.message = "Running filter"
# We change the output type to unsigned char 3D
# (itk.Image.UC3D) to save memory in the output label map
# representation.
itk_output_image_type = itk.Image.UC3
# ITK's BinaryThresholdImageFilter does the hard work
threshold_filter = itk.BinaryThresholdImageFilter[
itk_input_image_type, itk_output_image_type].New()
python_cast = itkutils.get_python_voxel_type(itk_image)
threshold_filter.SetLowerThreshold(python_cast(lower_threshold))
threshold_filter.SetUpperThreshold(python_cast(upper_threshold))
threshold_filter.SetInsideValue(1)
threshold_filter.SetOutsideValue(0)
threshold_filter.SetInput(itk_image)
itkutils.observe_filter_progress(self, threshold_filter,
STEP_PCT[2], STEP_PCT[3])
try:
threshold_filter.Update()
except RuntimeError:
return returnValue
self.progress.message = "Creating child data set"
# Set the output as a new child data object of the current data set
label_map_dataset = vtk.vtkImageData()
label_map_dataset.CopyStructure(dataset)
itkutils.set_array_from_itk_image(label_map_dataset,
threshold_filter.GetOutput())
self.progress.value = STEP_PCT[4]
returnValue = {
"thresholded_segmentation": label_map_dataset
}
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
return returnValue
def transform_scalars(self, dataset, number_of_thresholds=1,
enable_valley_emphasis=False):
"""This filter performs semi-automatic multithresholding of a data set.
Voxels are automatically classified into a chosen number of classes such
that inter-class variance of the voxel values is minimized. The output
is a label map with one label per voxel class.
"""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
STEP_PCT = [10, 20, 70, 90, 100]
try:
import itk
import itkExtras
import itkTypes
from vtkmodules.vtkCommonDataModel import vtkImageData
from tomviz import itkutils
from tomviz import utils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
# Return values
returnValues = None
# Add a try/except around the ITK portion. ITK exceptions are
# passed up to the Python layer, so we can at least report what
# went wrong with the script, e.g,, unsupported image type.
try:
self.progress.value = STEP_PCT[0]
self.progress.message = "Converting data to ITK image"
# Get the ITK image
itk_image = itkutils.convert_vtk_to_itk_image(dataset)
itk_input_image_type = type(itk_image)
# OtsuMultipleThresholdsImageFilter's wrapping requires that the
# input and output image types be the same.
itk_threshold_image_type = itk_input_image_type
# Otsu multiple threshold filter
otsu_filter = itk.OtsuMultipleThresholdsImageFilter[
itk_input_image_type, itk_threshold_image_type].New()
otsu_filter.SetNumberOfThresholds(number_of_thresholds)
otsu_filter.SetValleyEmphasis(enable_valley_emphasis)
otsu_filter.SetInput(itk_image)
itkutils.observe_filter_progress(self, otsu_filter,
STEP_PCT[1], STEP_PCT[2])
try:
otsu_filter.Update()
except RuntimeError:
return
print("Otsu threshold(s): %s" % (otsu_filter.GetThresholds(),))
itk_image_data = otsu_filter.GetOutput()
# Cast threshold output to an integral type if needed.
py_buffer_type = itk_threshold_image_type
voxel_type = itkExtras.template(itk_threshold_image_type)[1][0]
if voxel_type is itkTypes.F or voxel_type is itkTypes.D:
self.progress.message = "Casting output to integral type"
# Unsigned char supports 256 labels, or 255 threshold levels.
# This should be sufficient for all but the most unusual use
# cases.
py_buffer_type = itk.Image.UC3
caster = itk.CastImageFilter[itk_threshold_image_type,
py_buffer_type].New()
caster.SetInput(itk_image_data)
itkutils.observe_filter_progress(self, caster,
STEP_PCT[2], STEP_PCT[3])
try:
caster.Update()
except RuntimeError:
return
itk_image_data = caster.GetOutput()
self.progress.value = STEP_PCT[3]
self.progress.message = "Saving results"
label_buffer = itk.PyBuffer[py_buffer_type] \
.GetArrayFromImage(itk_image_data)
label_map_dataset = vtkImageData()
label_map_dataset.CopyStructure(dataset)
utils.set_array(label_map_dataset, label_buffer, isFortran=False)
self.progress.value = STEP_PCT[4]
# Set up dictionary to return operator results
returnValues = {}
returnValues["label_map"] = label_map_dataset
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
return returnValues
def transform(self,
dataset,
stencil_radius=2,
iterations=10,
threshold=50.0):
"""This filter smooths a binary image by evolving a level set with a
curvature-based speed function. The Stencil Radius determines the scale
of the noise to remove. The Threshold determines the iso-contour
brightness to discriminate between two pixel classes.
"""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
STEP_PCT = [10, 20, 30, 70, 80, 90, 100]
try:
import itk
import itkTypes
from tomviz import itkutils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
# Return values
returnValue = None
# Add a try/except around the ITK portion. ITK exceptions are
# passed up to the Python layer, so we can at least report what
# went wrong with the script, e.g,, unsupported image type.
try:
self.progress.value = STEP_PCT[0]
self.progress.message = "Converting data to ITK image"
# Get the ITK image
itk_image = itkutils.dataset_to_itk_image(dataset)
itk_input_image_type = type(itk_image)
self.progress.message = "Casting input to float type"
itk_filter_image_type = itk.Image[itkTypes.F,
itk_image.GetImageDimension()]
caster = itk.CastImageFilter[itk_input_image_type,
itk_filter_image_type].New()
caster.SetInput(itk_image)
itkutils.observe_filter_progress(self, caster, STEP_PCT[1],
STEP_PCT[2])
try:
caster.Update()
except RuntimeError:
return
self.progress.message = "Running filter"
smoothing_filter = itk.BinaryMinMaxCurvatureFlowImageFilter[
itk_filter_image_type, itk_filter_image_type].New()
smoothing_filter.SetThreshold(threshold)
smoothing_filter.SetStencilRadius(stencil_radius)
smoothing_filter.SetNumberOfIterations(iterations)
smoothing_filter.SetTimeStep(0.0625)
smoothing_filter.SetInput(caster)
itkutils.observe_filter_progress(self, smoothing_filter,
STEP_PCT[2], STEP_PCT[3])
try:
smoothing_filter.Update()
except RuntimeError:
return
itk_image_data = smoothing_filter.GetOutput()
# Cast output to the input type
self.progress.message = "Casting output to input type"
caster = itk.CastImageFilter[itk_filter_image_type,
itk_input_image_type].New()
caster.SetInput(itk_image_data)
itkutils.observe_filter_progress(self, caster, STEP_PCT[3],
STEP_PCT[4])
try:
caster.Update()
except RuntimeError:
return
itk_image_data = caster.GetOutput()
self.progress.value = STEP_PCT[5]
self.progress.message = "Saving results"
itkutils.set_itk_image_on_dataset(itk_image_data, dataset)
self.progress.value = STEP_PCT[6]
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
return returnValue
def transform_scalars(self, dataset, number_of_thresholds=1,
enable_valley_emphasis=False):
"""This filter performs semi-automatic multithresholding of a data set.
Voxels are automatically classified into a chosen number of classes such
that inter-class variance of the voxel values is minimized. The output
is a label map with one label per voxel class.
"""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
STEP_PCT = [10, 20, 70, 90, 100]
try:
import itk
import itkExtras
import itkTypes
import vtk
from tomviz import itkutils
from tomviz import utils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
# Return values
returnValues = None
# Add a try/except around the ITK portion. ITK exceptions are
# passed up to the Python layer, so we can at least report what
# went wrong with the script, e.g,, unsupported image type.
try:
self.progress.value = STEP_PCT[0]
self.progress.message = "Converting data to ITK image"
# Get the ITK image
itk_image = itkutils.convert_vtk_to_itk_image(dataset)
itk_input_image_type = type(itk_image)
# OtsuMultipleThresholdsImageFilter's wrapping requires that the
# input and output image types be the same.
itk_threshold_image_type = itk_input_image_type
# Otsu multiple threshold filter
otsu_filter = itk.OtsuMultipleThresholdsImageFilter[
itk_input_image_type, itk_threshold_image_type].New()
otsu_filter.SetNumberOfThresholds(number_of_thresholds)
otsu_filter.SetValleyEmphasis(enable_valley_emphasis)
otsu_filter.SetInput(itk_image)
itkutils.observe_filter_progress(self, otsu_filter,
STEP_PCT[1], STEP_PCT[2])
try:
otsu_filter.Update()
except RuntimeError:
return
print("Otsu threshold(s): %s" % (otsu_filter.GetThresholds(),))
itk_image_data = otsu_filter.GetOutput()
# Cast threshold output to an integral type if needed.
py_buffer_type = itk_threshold_image_type
voxel_type = itkExtras.template(itk_threshold_image_type)[1][0]
if voxel_type is itkTypes.F or voxel_type is itkTypes.D:
self.progress.message = "Casting output to integral type"
# Unsigned char supports 256 labels, or 255 threshold levels.
# This should be sufficient for all but the most unusual use
# cases.
py_buffer_type = itk.Image.UC3
caster = itk.CastImageFilter[itk_threshold_image_type,
py_buffer_type].New()
caster.SetInput(itk_image_data)
itkutils.observe_filter_progress(self, caster,
STEP_PCT[2], STEP_PCT[3])
try:
caster.Update()
except RuntimeError:
return
itk_image_data = caster.GetOutput()
self.progress.value = STEP_PCT[3]
self.progress.message = "Saving results"
label_buffer = itk.PyBuffer[py_buffer_type] \
.GetArrayFromImage(itk_image_data)
label_map_dataset = vtk.vtkImageData()
label_map_dataset.CopyStructure(dataset)
utils.set_array(label_map_dataset, label_buffer)
self.progress.value = STEP_PCT[4]
# Set up dictionary to return operator results
returnValues = {}
returnValues["label_map"] = label_map_dataset
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
return returnValues
def transform(self,
dataset,
structuring_element_id=0,
radius=1,
object_label=1,
background_label=0):
"""Erode segmented objects with a given label by a spherically symmetric
structuring element with a given radius.
"""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
STEP_PCT = [10, 20, 90, 100]
try:
import itk
from tomviz import itkutils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
# Add a try/except around the ITK portion. ITK exceptions are
# passed up to the Python layer, so we can at least report what
# went wrong with the script, e.g,, unsupported image type.
try:
self.progress.value = STEP_PCT[0]
self.progress.message = "Converting data to ITK image"
# Get the ITK image
itk_image = itkutils.dataset_to_itk_image(dataset)
itk_input_image_type = type(itk_image)
itk_kernel_type = itk.FlatStructuringElement[3]
if (structuring_element_id == 0):
itk_kernel = itk_kernel_type.Box(radius)
elif (structuring_element_id == 1):
itk_kernel = itk_kernel_type.Ball(radius)
elif (structuring_element_id == 2):
itk_kernel = itk_kernel_type.Cross(radius)
else:
raise Exception('Invalid kernel shape id %d' %
structuring_element_id)
self.progress.value = STEP_PCT[1]
self.progress.message = "Running filter"
erode_filter = itk.BinaryErodeImageFilter[itk_input_image_type,
itk_input_image_type,
itk_kernel_type].New()
erode_filter.SetErodeValue(object_label)
erode_filter.SetBackgroundValue(background_label)
erode_filter.SetKernel(itk_kernel)
erode_filter.SetInput(itk_image)
itkutils.observe_filter_progress(self, erode_filter, STEP_PCT[1],
STEP_PCT[2])
try:
erode_filter.Update()
except RuntimeError:
return
self.progress.message = "Saving results"
itkutils.set_itk_image_on_dataset(erode_filter.GetOutput(),
dataset)
self.progress.value = STEP_PCT[3]
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
def transform_scalars(self,
dataset,
lower_threshold=40.0,
upper_threshold=255.0):
"""This filter computes a binary threshold on the data set and
stores the result in a child data set. It does not modify the dataset
passed in."""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
STEP_PCT = [20, 40, 75, 90, 100]
# Set up return value
returnValue = None
# Try imports to make sure we have everything that is needed
try:
self.progress.message = "Loading modules"
import itk
from vtkmodules.vtkCommonDataModel import vtkImageData
from tomviz import itkutils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
# Add a try/except around the ITK portion. ITK exceptions are
# passed up to the Python layer, so we can at least report what
# went wrong with the script, e.g,, unsupported image type.
try:
self.progress.value = STEP_PCT[0]
self.progress.message = "Converting data to ITK image"
# Get the ITK image
itk_image = itkutils.convert_vtk_to_itk_image(dataset)
itk_input_image_type = type(itk_image)
self.progress.value = STEP_PCT[1]
self.progress.message = "Running filter"
# We change the output type to unsigned char 3D
# (itk.Image.UC3D) to save memory in the output label map
# representation.
itk_output_image_type = itk.Image.UC3
# ITK's BinaryThresholdImageFilter does the hard work
threshold_filter = itk.BinaryThresholdImageFilter[
itk_input_image_type, itk_output_image_type].New()
python_cast = itkutils.get_python_voxel_type(itk_image)
threshold_filter.SetLowerThreshold(python_cast(lower_threshold))
threshold_filter.SetUpperThreshold(python_cast(upper_threshold))
threshold_filter.SetInsideValue(1)
threshold_filter.SetOutsideValue(0)
threshold_filter.SetInput(itk_image)
itkutils.observe_filter_progress(self, threshold_filter,
STEP_PCT[2], STEP_PCT[3])
try:
threshold_filter.Update()
except RuntimeError:
return returnValue
self.progress.message = "Creating child data set"
# Set the output as a new child data object of the current data set
label_map_dataset = vtkImageData()
label_map_dataset.CopyStructure(dataset)
itkutils.set_array_from_itk_image(label_map_dataset,
threshold_filter.GetOutput())
self.progress.value = STEP_PCT[4]
returnValue = {"thresholded_segmentation": label_map_dataset}
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
return returnValue
def transform_scalars(self, dataset, stencil_radius=2, iterations=10,
threshold=50.0):
"""This filter smooths a binary image by evolving a level set with a
curvature-based speed function. The Stencil Radius determines the scale
of the noise to remove. The Threshold determines the iso-contour
brightness to discriminate between two pixel classes.
"""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
STEP_PCT = [10, 20, 30, 70, 80, 90, 100]
try:
import itk
import itkTypes
from tomviz import itkutils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
# Return values
returnValue = None
# Add a try/except around the ITK portion. ITK exceptions are
# passed up to the Python layer, so we can at least report what
# went wrong with the script, e.g,, unsupported image type.
try:
self.progress.value = STEP_PCT[0]
self.progress.message = "Converting data to ITK image"
# Get the ITK image
itk_image = itkutils.convert_vtk_to_itk_image(dataset)
itk_input_image_type = type(itk_image)
self.progress.message = "Casting input to float type"
itk_filter_image_type = itk.Image[itkTypes.F,
itk_image.GetImageDimension()]
caster = itk.CastImageFilter[itk_input_image_type,
itk_filter_image_type].New()
caster.SetInput(itk_image)
itkutils.observe_filter_progress(self, caster,
STEP_PCT[1], STEP_PCT[2])
try:
caster.Update()
except RuntimeError:
return
self.progress.message = "Running filter"
smoothing_filter = itk.BinaryMinMaxCurvatureFlowImageFilter[
itk_filter_image_type, itk_filter_image_type].New()
smoothing_filter.SetThreshold(threshold)
smoothing_filter.SetStencilRadius(stencil_radius)
smoothing_filter.SetNumberOfIterations(iterations)
smoothing_filter.SetTimeStep(0.0625)
smoothing_filter.SetInput(caster)
itkutils.observe_filter_progress(self, smoothing_filter,
STEP_PCT[2], STEP_PCT[3])
try:
smoothing_filter.Update()
except RuntimeError:
return
itk_image_data = smoothing_filter.GetOutput()
# Cast output to the input type
self.progress.message = "Casting output to input type"
caster = itk.CastImageFilter[itk_filter_image_type,
itk_input_image_type].New()
caster.SetInput(itk_image_data)
itkutils.observe_filter_progress(self, caster,
STEP_PCT[3], STEP_PCT[4])
try:
caster.Update()
except RuntimeError:
return
itk_image_data = caster.GetOutput()
self.progress.value = STEP_PCT[5]
self.progress.message = "Saving results"
itkutils.set_array_from_itk_image(dataset,
itk_image_data)
self.progress.value = STEP_PCT[6]
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
return returnValue
def transform_scalars(self, dataset, conductance=1.0, iterations=100,
timestep=0.0625):
"""This filter performs anisotropic diffusion on an image using
the classic Perona-Malik, gradient magnitude-based equation.
"""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
STEP_PCT = [10, 20, 90, 100]
try:
import itk
import itkTypes
from tomviz import itkutils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
try:
self.progress.value = STEP_PCT[0]
self.progress.message = "Converting data to ITK image"
# Get the ITK image. The itk.GradientAnisotropicDiffusionImageFilter
# is templated over float pixel types only, so explicitly request a
# float ITK image type.
itk_image = itkutils.convert_vtk_to_itk_image(dataset, itkTypes.F)
itk_image_type = type(itk_image)
self.progress.value = STEP_PCT[1]
self.progress.message = "Running filter"
DiffusionFilterType = \
itk.GradientAnisotropicDiffusionImageFilter[itk_image_type,
itk_image_type]
diffusion_filter = DiffusionFilterType.New()
diffusion_filter.SetConductanceParameter(conductance)
diffusion_filter.SetNumberOfIterations(iterations)
diffusion_filter.SetTimeStep(timestep)
diffusion_filter.SetInput(itk_image)
itkutils.observe_filter_progress(self, diffusion_filter,
STEP_PCT[1], STEP_PCT[2])
try:
diffusion_filter.Update()
except RuntimeError:
return
self.progress.message = "Saving results"
itkutils.set_array_from_itk_image(dataset,
diffusion_filter.GetOutput())
self.progress.value = STEP_PCT[3]
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
def transform_scalars(self, dataset, structuring_element_id=0, radius=1,
object_label=1, background_label=0):
"""Perform morphological opening on segmented objects with a given label by
a spherically symmetric structuring element with a given radius.
"""
# Initial progress
self.progress.value = 0
self.progress.maximum = 100
# Approximate percentage of work completed after each step in the
# transform
STEP_PCT = [10, 30, 60, 90, 100]
try:
import itk
from tomviz import itkutils
except Exception as exc:
print("Could not import necessary module(s)")
raise exc
# Add a try/except around the ITK portion. ITK exceptions are
# passed up to the Python layer, so we can at least report what
# went wrong with the script, e.g,, unsupported image type.
try:
self.progress.value = STEP_PCT[0]
self.progress.message = "Converting data to ITK image"
# Get the ITK image
itk_image = itkutils.convert_vtk_to_itk_image(dataset)
itk_input_image_type = type(itk_image)
itk_kernel_type = itk.FlatStructuringElement[3]
if (structuring_element_id == 0):
itk_kernel = itk_kernel_type.Box(radius)
elif (structuring_element_id == 1):
itk_kernel = itk_kernel_type.Ball(radius)
elif (structuring_element_id == 2):
itk_kernel = itk_kernel_type.Cross(radius)
else:
raise Exception('Invalid kernel shape id %d' %
structuring_element_id)
self.progress.value = STEP_PCT[1]
self.progress.message = "Running filter"
erode_filter = itk.BinaryErodeImageFilter[itk_input_image_type,
itk_input_image_type,
itk_kernel_type].New()
erode_filter.SetErodeValue(object_label)
erode_filter.SetBackgroundValue(background_label)
erode_filter.SetKernel(itk_kernel)
erode_filter.SetInput(itk_image)
itkutils.observe_filter_progress(self, erode_filter,
STEP_PCT[1], STEP_PCT[2])
dilate_filter = itk.BinaryDilateImageFilter[itk_input_image_type,
itk_input_image_type,
itk_kernel_type].New()
dilate_filter.SetDilateValue(object_label)
dilate_filter.SetBackgroundValue(background_label)
dilate_filter.SetKernel(itk_kernel)
dilate_filter.SetInput(erode_filter.GetOutput())
itkutils.observe_filter_progress(self, dilate_filter,
STEP_PCT[2], STEP_PCT[3])
try:
dilate_filter.Update()
except RuntimeError:
return
self.progress.message = "Saving results"
itkutils.set_array_from_itk_image(dataset,
dilate_filter.GetOutput())
self.progress.value = STEP_PCT[4]
except Exception as exc:
print("Problem encountered while running %s" %
self.__class__.__name__)
raise exc
