# OUTPUTS: {ThresholdSegmentationLevelSetImageFilterWhiteMatter.png}
# 60 116 5 150 180
# INPUTS: {BrainProtonDensitySlice.png}
# OUTPUTS: {ThresholdSegmentationLevelSetImageFilterVentricle.png}
# 81 112 5 210 250
# INPUTS: {BrainProtonDensitySlice.png}
# OUTPUTS: {ThresholdSegmentationLevelSetImageFilterGrayMatter.png}
# 107 69 5 180 210
import itk
from sys import argv, stderr, exit
import os
itk.auto_progress(2)
# itk.auto_progress(1)
if len(argv) < 8:
print(
("Missing Parameters \n Usage: "
"ThresholdSegmentationLevelSetImageFilter.py inputImage outputImage "
"seedX seedY InitialDistance LowerThreshold UpperThreshold "
"[CurvatureScaling == 1.0]"),
file=stderr,
)
exit(1)
InternalPixelType = itk.F
Dimension = 2
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
#==========================================================================*/
#
# Example on the use of the SigmoidImageFilter
#
import itk
from sys import argv
itk.auto_progress(2)
dim = 2
IType = itk.Image[itk.US, dim]
OIType = itk.Image[itk.UC, dim]
reader = itk.ImageFileReader[IType].New( FileName=argv[1] )
filter = itk.SigmoidImageFilter[IType, IType].New( reader,
OutputMinimum=eval( argv[3] ),
OutputMaximum=eval( argv[4] ),
Alpha=eval( argv[5] ),
Beta=eval( argv[6] ),
)
cast = itk.CastImageFilter[IType, OIType].New(filter)
writer = itk.ImageFileWriter[OIType].New( cast, FileName=argv[2] )
image: the input image''')
parser.add_option("-v", "--verbose", action="store_true", dest="verbose", help="display infos about progress")
parser.add_option("-t", "--threads", type="int", dest="threads", default=0, help="number of threads to use. Defaults to the number of procs")
opts, args = parser.parse_args()
# check the arguments
if len(args) != 1:
parser.error("incorrect number of arguments")
inputFileName = args[0]
inputFile = open( inputFileName )
if opts.verbose:
itk.auto_progress()
if opts.threads > 0:
itk.MultiThreader.SetGlobalDefaultNumberOfThreads( opts.threads )
##########################
# nuclei
##########################
labelRobustNuclei = itk.ImageFileReader.IUC3.New()
# select a single nucleus - see the loop at the end
singleMaskRobustNuclei = itk.BinaryThresholdImageFilter.IUC3IUC3.New(labelRobustNuclei, UpperThreshold=1, LowerThreshold=1)
import itk, sys
itk.auto_progress()
Dimension = 2
PixelType = itk.UC
ImageType = itk.Image[PixelType, Dimension]
DistancePixelType = itk.F
DistanceImageType = itk.Image[DistancePixelType, Dimension]
RGBPixelType = itk.RGBPixel[PixelType]
RGBImageType = itk.Image[RGBPixelType, Dimension]
LabelObjectType = itk.StatisticsLabelObject[itk.UL, Dimension]
LabelMapType = itk.LabelMap[LabelObjectType]
# read the image of the nucleus
nuclei = itk.ImageFileReader[ImageType].New(FileName="images/noyaux.png")
# perform a simple binarization. Note that the Otsu filter does not use the same convention as usual : the white part is outside.
otsu = itk.OtsuThresholdImageFilter[ImageType, ImageType].New(nuclei,
OutsideValue=255,
InsideValue=0)
# split the nuclei
maurer = itk.SignedMaurerDistanceMapImageFilter[ImageType,
DistanceImageType].New(otsu)
watershed = itk.MorphologicalWatershedImageFilter[DistanceImageType,
ImageType].New(
maurer,
Level=60,
MarkWatershedLine=False)
mask = itk.MaskImageFilter[ImageType, ImageType,
import itk; itk.auto_progress()
itk.auto_not_in_place()
import sys
def mean(s):
res = float(sum(s))
return res / len(s)
def median(s):
res = sorted(s)
l = len(res)/2
if len(res)%2:
return res[l]
else:
return mean(res[l-1:l+1])
class ClosestLabelDilateImageFilter(itk.pipeline):
def __init__(self, *args, **kargs):
# call the constructor of the superclass but without args and kargs, because the attributes
# are not all already there!
# Set/GetRadius() is created in the constructor for example, with the expose() method
itk.pipeline.__init__(self)
# get the template parameters
template_parameters = kargs["template_parameters"]
# and store them in an easier way
ImageType, DistanceMapType = template_parameters
import itk, math, csv itk.auto_progress(True) toAnalyze = range(1,26) imgDir = 'images/apotome/' csvFile = 'data/nucleus_stats.csv' ## Define pipeline reader = itk.ImageFileReader.IUC3.New() labmap = itk.LabelImageToShapeLabelMapFilter.IUC3LM3.New(reader,ComputePerimeter=True) ## End of pipeline definition toAnalyze = [str(nb) for nb in toAnalyze] dataFile = open(csvFile,'w') dataWriter = csv.writer(dataFile) dataWriter.writerow(['img.nb','label','x','y','z','volume','diameter','surface','shape','elongation','height','a.x','a.y','a.z']) for nb in toAnalyze: filename = imgDir+'gml16_dapi_'+nb+'_nuclei.nrrd' print 'Image filename',filename reader.SetFileName(filename) labmap.UpdateLargestPossibleRegion() lmo = labmap.GetOutput() n = lmo.GetNumberOfLabelObjects() print '\t',n,'nuclei' for i in range(n): row = [nb,i+1] nucleus = lmo.GetNthLabelObject(i) centroid = nucleus.GetCentroid() for j in range(3): row.append(centroid[j])