Preprocess::ImageType2D::Pointer Preprocess::ExtractSlice(ImageType3D::Pointer img, int slice)
{
int size1 = img->GetLargestPossibleRegion().GetSize()[0];
int size2 = img->GetLargestPossibleRegion().GetSize()[1];
int size3 = img->GetLargestPossibleRegion().GetSize()[2];
if(slice >= size3)
return NULL;
ImageType3D::IndexType extractStart = {{ 0,0,slice }};
ImageType3D::SizeType extractSize = {{ size1, size2, 0 }};
ImageType3D::RegionType extractRegion;
extractRegion.SetSize( extractSize );
extractRegion.SetIndex( extractStart );
typedef itk::ExtractImageFilter< ImageType3D, ImageType2D > ExtractFilterType;
ExtractFilterType::Pointer extract = ExtractFilterType::New();
extract->SetInput( img );
extract->SetExtractionRegion( extractRegion );
try
{
extract->Update();
}
catch( itk::ExceptionObject & err )
{
std::cerr << "ITK FILTER ERROR: " << err << std::endl ;
}
return extract->GetOutput();
}
int main( int argc, char *argv[] )
{
if( argc < 4 )
{
std::cerr << "Missing Parameters " << std::endl;
std::cerr << "Usage: " << argv[0];
std::cerr << " fixedImageFile movingImageFile ";
std::cerr << " outputImagefile [differenceBeforeRegistration] ";
std::cerr << " [differenceAfterRegistration] ";
std::cerr << " [sliceBeforeRegistration] ";
std::cerr << " [sliceDifferenceBeforeRegistration] ";
std::cerr << " [sliceDifferenceAfterRegistration] ";
std::cerr << " [sliceAfterRegistration] " << std::endl;
return EXIT_FAILURE;
}
const unsigned int Dimension = 3;
typedef float PixelType;
typedef itk::Image< PixelType, Dimension > FixedImageType;
typedef itk::Image< PixelType, Dimension > MovingImageType;
// Software Guide : BeginLatex
//
// The Transform class is instantiated using the code below. The only
// template parameter to this class is the representation type of the
// space coordinates.
//
// \index{itk::Versor\-Rigid3D\-Transform!Instantiation}
//
// Software Guide : EndLatex
// Software Guide : BeginCodeSnippet
// Software Guide : EndCodeSnippet
typedef itk:: LinearInterpolateImageFunction< MovingImageType, double > InterpolatorType;
typedef itk::ImageRegistrationMethod< FixedImageType, MovingImageType > RegistrationType;
MetricType::Pointer metric = MetricType::New();
OptimizerType::Pointer optimizer = OptimizerType::New();
InterpolatorType::Pointer interpolator = InterpolatorType::New();
RegistrationType::Pointer registration = RegistrationType::New();
registration->SetMetric( metric );
registration->SetOptimizer( optimizer );
registration->SetInterpolator( interpolator );
// Software Guide : BeginLatex
//
// The transform object is constructed below and passed to the registration
// method.
//
// \index{itk::Versor\-Rigid3D\-Transform!New()}
// \index{itk::Versor\-Rigid3D\-Transform!Pointer}
// \index{itk::Registration\-Method!SetTransform()}
//
// Software Guide : EndLatex
// Software Guide : BeginCodeSnippet
TransformType::Pointer transform = TransformType::New();
registration->SetTransform( transform );
// Software Guide : EndCodeSnippet
typedef itk::ImageFileReader< FixedImageType > FixedImageReaderType;
typedef itk::ImageFileReader< MovingImageType > MovingImageReaderType;
FixedImageReaderType::Pointer fixedImageReader = FixedImageReaderType::New();
MovingImageReaderType::Pointer movingImageReader = MovingImageReaderType::New();
fixedImageReader->SetFileName( argv[1] );
movingImageReader->SetFileName( argv[2] );
registration->SetFixedImage( fixedImageReader->GetOutput() );
registration->SetMovingImage( movingImageReader->GetOutput() );
fixedImageReader->Update();
registration->SetFixedImageRegion(
fixedImageReader->GetOutput()->GetBufferedRegion() );
// Software Guide : BeginLatex
//
// The input images are taken from readers. It is not necessary here to
// explicitly call \code{Update()} on the readers since the
// \doxygen{CenteredTransformInitializer} will do it as part of its
// computations. The following code instantiates the type of the
// initializer. This class is templated over the fixed and moving image type
// as well as the transform type. An initializer is then constructed by
// calling the \code{New()} method and assigning the result to a smart
// pointer.
//
// \index{itk::Centered\-Transform\-Initializer!Instantiation}
// \index{itk::Centered\-Transform\-Initializer!New()}
// \index{itk::Centered\-Transform\-Initializer!SmartPointer}
//
// Software Guide : EndLatex
// Software Guide : BeginCodeSnippet
// Software Guide : BeginLatex
//
// Let's execute this example over some of the images available in the ftp
// site
//
// \url{ftp://public.kitware.com/pub/itk/Data/BrainWeb}
//
// Note that the images in the ftp site are compressed in \code{.tgz} files.
// You should download these files an uncompress them in your local system.
// After decompressing and extracting the files you could take a pair of
// volumes, for example the pair:
//
// \begin{itemize}
// \item \code{brainweb1e1a10f20.mha}
// \item \code{brainweb1e1a10f20Rot10Tx15.mha}
// \end{itemize}
//
// The second image is the result of intentionally rotating the first image
// by $10$ degrees around the origin and shifting it $15mm$ in $X$. The
// registration takes $24$ iterations and produces:
//
// \begin{center}
// \begin{verbatim}
// [-6.03744e-05, 5.91487e-06, -0.0871932, 2.64659, -17.4637, -0.00232496]
// \end{verbatim}
// \end{center}
//
// That are interpreted as
//
// \begin{itemize}
// \item Versor = $(-6.03744e-05, 5.91487e-06, -0.0871932)$
// \item Translation = $(2.64659, -17.4637, -0.00232496)$ millimeters
// \end{itemize}
//
// This Versor is equivalent to a rotation of $9.98$ degrees around the $Z$
// axis.
//
// Note that the reported translation is not the translation of $(15.0,0.0,0.0)$
// that we may be naively expecting. The reason is that the
// \code{VersorRigid3DTransform} is applying the rotation around the center
// found by the \code{CenteredTransformInitializer} and then adding the
// translation vector shown above.
//
// It is more illustrative in this case to take a look at the actual
// rotation matrix and offset resulting form the $6$ parameters.
//
// Software Guide : EndLatex
// Software Guide : BeginCodeSnippet
transform->SetParameters( finalParameters );
TransformType::MatrixType matrix = transform->GetMatrix();
TransformType::OffsetType offset = transform->GetOffset();
std::cout << "Matrix = " << std::endl << matrix << std::endl;
std::cout << "Offset = " << std::endl << offset << std::endl;
// Software Guide : EndCodeSnippet
// Software Guide : BeginLatex
//
// The output of this print statements is
//
// \begin{center}
// \begin{verbatim}
// Matrix =
// 0.984795 0.173722 2.23132e-05
// -0.173722 0.984795 0.000119257
// -1.25621e-06 -0.00012132 1
//
// Offset =
// [-15.0105, -0.00672343, 0.0110854]
// \end{verbatim}
// \end{center}
//
// From the rotation matrix it is possible to deduce that the rotation is
// happening in the X,Y plane and that the angle is on the order of
// $\arcsin{(0.173722)}$ which is very close to 10 degrees, as we expected.
//
// Software Guide : EndLatex
// Software Guide : BeginLatex
//
// \begin{figure}
// \center
// \includegraphics[width=0.44\textwidth]{BrainProtonDensitySliceBorder20}
// \includegraphics[width=0.44\textwidth]{BrainProtonDensitySliceR10X13Y17}
// \itkcaption[CenteredTransformInitializer input images]{Fixed and moving image
// provided as input to the registration method using
// CenteredTransformInitializer.}
// \label{fig:FixedMovingImageRegistration8}
// \end{figure}
//
//
// \begin{figure}
// \center
// \includegraphics[width=0.32\textwidth]{ImageRegistration8Output}
// \includegraphics[width=0.32\textwidth]{ImageRegistration8DifferenceBefore}
// \includegraphics[width=0.32\textwidth]{ImageRegistration8DifferenceAfter}
// \itkcaption[CenteredTransformInitializer output images]{Resampled moving
// image (left). Differences between fixed and moving images, before (center)
// and after (right) registration with the
// CenteredTransformInitializer.}
// \label{fig:ImageRegistration8Outputs}
// \end{figure}
//
// Figure \ref{fig:ImageRegistration8Outputs} shows the output of the
// registration. The center image in this figure shows the differences
// between the fixed image and the resampled moving image before the
// registration. The image on the right side presents the difference between
// the fixed image and the resampled moving image after the registration has
// been performed. Note that these images are individual slices extracted
// from the actual volumes. For details, look at the source code of this
// example, where the ExtractImageFilter is used to extract a slice from the
// the center of each one of the volumes. One of the main purposes of this
// example is to illustrate that the toolkit can perform registration on
// images of any dimension. The only limitations are, as usual, the amount of
// memory available for the images and the amount of computation time that it
// will take to complete the optimization process.
//
// \begin{figure}
// \center
// \includegraphics[height=0.32\textwidth]{ImageRegistration8TraceMetric}
// \includegraphics[height=0.32\textwidth]{ImageRegistration8TraceAngle}
// \includegraphics[height=0.32\textwidth]{ImageRegistration8TraceTranslations}
// \itkcaption[CenteredTransformInitializer output plots]{Plots of the metric,
// rotation angle, center of rotation and translations during the
// registration using CenteredTransformInitializer.}
// \label{fig:ImageRegistration8Plots}
// \end{figure}
//
// Figure \ref{fig:ImageRegistration8Plots} shows the plots of the main
// output parameters of the registration process. The metric values at every
// iteration. The Z component of the versor is plotted as an indication of
// how the rotation progress. The X,Y translation components of the
// registration are plotted at every iteration too.
//
// Shell and Gnuplot scripts for generating the diagrams in
// Figure~\ref{fig:ImageRegistration8Plots} are available in the directory
//
// \code{InsightDocuments/SoftwareGuide/Art}
//
// You are strongly encouraged to run the example code, since only in this
// way you can gain a first hand experience with the behavior of the
// registration process. Once again, this is a simple reflection of the
// philosophy that we put forward in this book:
//
// \emph{If you can not replicate it, then it does not exist!}.
//
// We have seen enough published papers with pretty pictures, presenting
// results that in practice are impossible to replicate. That is vanity, not
// science.
//
// Software Guide : EndLatex
typedef itk::ResampleImageFilter<
MovingImageType,
FixedImageType > ResampleFilterType;
TransformType::Pointer finalTransform = TransformType::New();
finalTransform->SetCenter( transform->GetCenter() );
finalTransform->SetParameters( finalParameters );
finalTransform->SetFixedParameters( transform->GetFixedParameters() );
ResampleFilterType::Pointer resampler = ResampleFilterType::New();
resampler->SetTransform( finalTransform );
resampler->SetInput( movingImageReader->GetOutput() );
FixedImageType::Pointer fixedImage = fixedImageReader->GetOutput();
resampler->SetSize( fixedImage->GetLargestPossibleRegion().GetSize() );
resampler->SetOutputOrigin( fixedImage->GetOrigin() );
resampler->SetOutputSpacing( fixedImage->GetSpacing() );
resampler->SetOutputDirection( fixedImage->GetDirection() );
resampler->SetDefaultPixelValue( 100 );
typedef unsigned char OutputPixelType;
typedef itk::Image< OutputPixelType, Dimension > OutputImageType;
typedef itk::CastImageFilter< FixedImageType, OutputImageType > CastFilterType;
typedef itk::ImageFileWriter< OutputImageType > WriterType;
WriterType::Pointer writer = WriterType::New();
CastFilterType::Pointer caster = CastFilterType::New();
writer->SetFileName( argv[3] );
caster->SetInput( resampler->GetOutput() );
writer->SetInput( caster->GetOutput() );
writer->Update();
typedef itk::SubtractImageFilter<
FixedImageType,
FixedImageType,
FixedImageType > DifferenceFilterType;
DifferenceFilterType::Pointer difference = DifferenceFilterType::New();
typedef itk::RescaleIntensityImageFilter<
FixedImageType,
OutputImageType > RescalerType;
RescalerType::Pointer intensityRescaler = RescalerType::New();
intensityRescaler->SetInput( difference->GetOutput() );
intensityRescaler->SetOutputMinimum( 0 );
intensityRescaler->SetOutputMaximum( 255 );
difference->SetInput1( fixedImageReader->GetOutput() );
difference->SetInput2( resampler->GetOutput() );
resampler->SetDefaultPixelValue( 1 );
WriterType::Pointer writer2 = WriterType::New();
writer2->SetInput( intensityRescaler->GetOutput() );
// Compute the difference image between the
// fixed and resampled moving image.
if( argc > 5 )
{
writer2->SetFileName( argv[5] );
writer2->Update();
}
typedef itk::IdentityTransform< double, Dimension > IdentityTransformType;
IdentityTransformType::Pointer identity = IdentityTransformType::New();
// Compute the difference image between the
// fixed and moving image before registration.
if( argc > 4 )
{
resampler->SetTransform( identity );
writer2->SetFileName( argv[4] );
writer2->Update();
}
//
// Here we extract slices from the input volume, and the difference volumes
// produced before and after the registration. These slices are presented as
// figures in the Software Guide.
//
//
typedef itk::Image< OutputPixelType, 2 > OutputSliceType;
typedef itk::ExtractImageFilter<
OutputImageType,
OutputSliceType > ExtractFilterType;
ExtractFilterType::Pointer extractor = ExtractFilterType::New();
extractor->SetDirectionCollapseToSubmatrix();
extractor->InPlaceOn();
FixedImageType::RegionType inputRegion =
fixedImage->GetLargestPossibleRegion();
FixedImageType::SizeType size = inputRegion.GetSize();
FixedImageType::IndexType start = inputRegion.GetIndex();
// Select one slice as output
size[2] = 0;
start[2] = 90;
FixedImageType::RegionType desiredRegion;
desiredRegion.SetSize( size );
desiredRegion.SetIndex( start );
extractor->SetExtractionRegion( desiredRegion );
typedef itk::ImageFileWriter< OutputSliceType > SliceWriterType;
SliceWriterType::Pointer sliceWriter = SliceWriterType::New();
sliceWriter->SetInput( extractor->GetOutput() );
if( argc > 6 )
{
extractor->SetInput( caster->GetOutput() );
resampler->SetTransform( identity );
sliceWriter->SetFileName( argv[6] );
sliceWriter->Update();
}
if( argc > 7 )
{
extractor->SetInput( intensityRescaler->GetOutput() );
resampler->SetTransform( identity );
sliceWriter->SetFileName( argv[7] );
sliceWriter->Update();
}
if( argc > 8 )
{
resampler->SetTransform( finalTransform );
sliceWriter->SetFileName( argv[8] );
sliceWriter->Update();
}
if( argc > 9 )
{
extractor->SetInput( caster->GetOutput() );
resampler->SetTransform( finalTransform );
sliceWriter->SetFileName( argv[9] );
sliceWriter->Update();
}
return EXIT_SUCCESS;
}
void QmitkDenoisingView::StartDenoising()
{
if (!m_ThreadIsRunning)
{
if (m_ImageNode.IsNotNull())
{
m_LastProgressCount = 0;
switch (m_SelectedFilter)
{
case NOFILTERSELECTED:
{
break;
}
case NLM:
{
// initialize NLM
m_InputImage = dynamic_cast<DiffusionImageType*> (m_ImageNode->GetData());
m_NonLocalMeansFilter = NonLocalMeansDenoisingFilterType::New();
if (m_BrainMaskNode.IsNotNull())
{
// use brainmask if set
m_ImageMask = dynamic_cast<mitk::Image*>(m_BrainMaskNode->GetData());
itk::Image<DiffusionPixelType, 3>::Pointer itkMask;
mitk::CastToItkImage(m_ImageMask, itkMask);
m_NonLocalMeansFilter->SetInputMask(itkMask);
itk::ImageRegionIterator< itk::Image<DiffusionPixelType, 3> > mit(itkMask, itkMask->GetLargestPossibleRegion());
mit.GoToBegin();
itk::Image<DiffusionPixelType, 3>::IndexType minIndex;
itk::Image<DiffusionPixelType, 3>::IndexType maxIndex;
minIndex.Fill(10000);
maxIndex.Fill(0);
while (!mit.IsAtEnd())
{
if (mit.Get())
{
// calculation of the start & end index of the smallest masked region
minIndex[0] = minIndex[0] < mit.GetIndex()[0] ? minIndex[0] : mit.GetIndex()[0];
minIndex[1] = minIndex[1] < mit.GetIndex()[1] ? minIndex[1] : mit.GetIndex()[1];
minIndex[2] = minIndex[2] < mit.GetIndex()[2] ? minIndex[2] : mit.GetIndex()[2];
maxIndex[0] = maxIndex[0] > mit.GetIndex()[0] ? maxIndex[0] : mit.GetIndex()[0];
maxIndex[1] = maxIndex[1] > mit.GetIndex()[1] ? maxIndex[1] : mit.GetIndex()[1];
maxIndex[2] = maxIndex[2] > mit.GetIndex()[2] ? maxIndex[2] : mit.GetIndex()[2];
}
++mit;
}
itk::Image<DiffusionPixelType, 3>::SizeType size;
size[0] = maxIndex[0] - minIndex[0] + 1;
size[1] = maxIndex[1] - minIndex[1] + 1;
size[2] = maxIndex[2] - minIndex[2] + 1;
m_MaxProgressCount = size[0] * size[1] * size[2];
}
else
{
// initialize the progressbar
m_MaxProgressCount = m_InputImage->GetDimension(0) * m_InputImage->GetDimension(1) * m_InputImage->GetDimension(2);
}
mitk::ProgressBar::GetInstance()->AddStepsToDo(m_MaxProgressCount);
m_NonLocalMeansFilter->SetInputImage(m_InputImage->GetVectorImage());
m_NonLocalMeansFilter->SetUseRicianAdaption(m_Controls->m_RicianCheckbox->isChecked());
m_NonLocalMeansFilter->SetUseJointInformation(m_Controls->m_JointInformationCheckbox->isChecked());
m_NonLocalMeansFilter->SetSearchRadius(m_Controls->m_SpinBoxParameter1->value());
m_NonLocalMeansFilter->SetComparisonRadius(m_Controls->m_SpinBoxParameter2->value());
m_NonLocalMeansFilter->SetVariance(m_Controls->m_DoubleSpinBoxParameter3->value());
// start denoising in detached thread
m_DenoisingThread.start(QThread::HighestPriority);
break;
}
case GAUSS:
{
// initialize GAUSS and run
m_InputImage = dynamic_cast<DiffusionImageType*> (m_ImageNode->GetData());
ExtractFilterType::Pointer extractor = ExtractFilterType::New();
extractor->SetInput(m_InputImage->GetVectorImage());
ComposeFilterType::Pointer composer = ComposeFilterType::New();
for (unsigned int i = 0; i < m_InputImage->GetVectorImage()->GetVectorLength(); ++i)
{
extractor->SetIndex(i);
extractor->Update();
m_GaussianFilter = GaussianFilterType::New();
m_GaussianFilter->SetVariance(m_Controls->m_SpinBoxParameter1->value());
if (m_BrainMaskNode.IsNotNull())
{
m_ImageMask = dynamic_cast<mitk::Image*>(m_BrainMaskNode->GetData());
itk::Image<DiffusionPixelType, 3>::Pointer itkMask = itk::Image<DiffusionPixelType, 3>::New();
mitk::CastToItkImage(m_ImageMask, itkMask);
itk::MaskImageFilter<itk::Image<DiffusionPixelType, 3> , itk::Image<DiffusionPixelType, 3> >::Pointer maskImageFilter = itk::MaskImageFilter<itk::Image<DiffusionPixelType, 3> , itk::Image<DiffusionPixelType, 3> >::New();
maskImageFilter->SetInput(extractor->GetOutput());
maskImageFilter->SetMaskImage(itkMask);
maskImageFilter->Update();
m_GaussianFilter->SetInput(maskImageFilter->GetOutput());
}
else
{
m_GaussianFilter->SetInput(extractor->GetOutput());
}
m_GaussianFilter->Update();
composer->SetInput(i, m_GaussianFilter->GetOutput());
}
composer->Update();
DiffusionImageType::Pointer image = DiffusionImageType::New();
image->SetVectorImage(composer->GetOutput());
image->SetReferenceBValue(m_InputImage->GetReferenceBValue());
image->SetDirections(m_InputImage->GetDirections());
image->InitializeFromVectorImage();
mitk::DataNode::Pointer imageNode = mitk::DataNode::New();
imageNode->SetData( image );
QString name = m_ImageNode->GetName().c_str();
imageNode->SetName((name+"_gauss_"+QString::number(m_Controls->m_SpinBoxParameter1->value())).toStdString().c_str());
GetDefaultDataStorage()->Add(imageNode);
break;
}
}
}
}
else
{
m_NonLocalMeansFilter->AbortGenerateDataOn();
m_CompletedCalculation = false;
}
}
int main(int argc, char* argv[])
{
mitkCommandLineParser parser;
parser.setTitle("DmriDenoising");
parser.setCategory("Preprocessing Tools");
parser.setDescription("dMRI denoising tool");
parser.setContributor("MIC");
parser.setArgumentPrefix("--", "-");
parser.beginGroup("1. Mandatory arguments:");
parser.addArgument("", "i", mitkCommandLineParser::String, "Input:", "input image", us::Any(), false, false, false, mitkCommandLineParser::Input);
parser.addArgument("", "o", mitkCommandLineParser::String, "Output:", "output image", us::Any(), false, false, false, mitkCommandLineParser::Output);
parser.addArgument("type", "", mitkCommandLineParser::Int, "Type:", "0 (TotalVariation), 1 (Gauss), 2 (NLM)", 0);
parser.endGroup();
parser.beginGroup("2. Total variation parameters:");
parser.addArgument("tv_iterations", "", mitkCommandLineParser::Int, "Iterations:", "", 1);
parser.addArgument("lambda", "", mitkCommandLineParser::Float, "Lambda:", "", 0.1);
parser.endGroup();
parser.beginGroup("3. Gauss parameters:");
parser.addArgument("variance", "", mitkCommandLineParser::Float, "Variance:", "", 1.0);
parser.endGroup();
parser.beginGroup("4. NLM parameters:");
parser.addArgument("nlm_iterations", "", mitkCommandLineParser::Int, "Iterations:", "", 4);
parser.addArgument("sampling_radius", "", mitkCommandLineParser::Int, "Sampling radius:", "", 4);
parser.addArgument("patch_radius", "", mitkCommandLineParser::Int, "Patch radius:", "", 1);
parser.addArgument("num_patches", "", mitkCommandLineParser::Int, "Num. patches:", "", 10);
parser.endGroup();
std::map<std::string, us::Any> parsedArgs = parser.parseArguments(argc, argv);
if (parsedArgs.size()==0)
return EXIT_FAILURE;
// mandatory arguments
std::string imageName = us::any_cast<std::string>(parsedArgs["i"]);
std::string outImage = us::any_cast<std::string>(parsedArgs["o"]);
int type = 0;
if (parsedArgs.count("type"))
type = us::any_cast<int>(parsedArgs["type"]);
int tv_iterations = 1;
if (parsedArgs.count("tv_iterations"))
tv_iterations = us::any_cast<int>(parsedArgs["tv_iterations"]);
float lambda = 0.1;
if (parsedArgs.count("lambda"))
lambda = us::any_cast<float>(parsedArgs["lambda"]);
float variance = 1.0;
if (parsedArgs.count("variance"))
variance = us::any_cast<float>(parsedArgs["variance"]);
int nlm_iterations = 4;
if (parsedArgs.count("nlm_iterations"))
nlm_iterations = us::any_cast<int>(parsedArgs["nlm_iterations"]);
int sampling_radius = 4;
if (parsedArgs.count("sampling_radius"))
sampling_radius = us::any_cast<int>(parsedArgs["sampling_radius"]);
int patch_radius = 1;
if (parsedArgs.count("patch_radius"))
patch_radius = us::any_cast<int>(parsedArgs["patch_radius"]);
int num_patches = 10;
if (parsedArgs.count("num_patches"))
num_patches = us::any_cast<int>(parsedArgs["num_patches"]);
try
{
mitk::PreferenceListReaderOptionsFunctor functor = mitk::PreferenceListReaderOptionsFunctor({"Diffusion Weighted Images"}, {});
mitk::Image::Pointer input_image = mitk::IOUtil::Load<mitk::Image>(imageName, &functor);
typedef short DiffusionPixelType;
typedef itk::VectorImage<DiffusionPixelType, 3> DwiImageType;
typedef itk::Image<DiffusionPixelType, 3> DwiVolumeType;
typedef itk::DiscreteGaussianImageFilter < DwiVolumeType, DwiVolumeType > GaussianFilterType;
typedef itk::PatchBasedDenoisingImageFilter < DwiVolumeType, DwiVolumeType > NlmFilterType;
typedef itk::VectorImageToImageFilter < DiffusionPixelType > ExtractFilterType;
typedef itk::ComposeImageFilter < itk::Image<DiffusionPixelType, 3> > ComposeFilterType;
if (!mitk::DiffusionPropertyHelper::IsDiffusionWeightedImage(input_image))
mitkThrow() << "Input is not a diffusion-weighted image!";
DwiImageType::Pointer itkVectorImagePointer = mitk::DiffusionPropertyHelper::GetItkVectorImage(input_image);
mitk::Image::Pointer denoised_image = nullptr;
switch (type)
{
case 0:
{
ComposeFilterType::Pointer composer = ComposeFilterType::New();
for (unsigned int i=0; i<itkVectorImagePointer->GetVectorLength(); ++i)
{
ExtractFilterType::Pointer extractor = ExtractFilterType::New();
extractor->SetInput( itkVectorImagePointer );
extractor->SetIndex( i );
extractor->Update();
DwiVolumeType::Pointer gradient_volume = extractor->GetOutput();
itk::TotalVariationDenoisingImageFilter< DwiVolumeType, DwiVolumeType >::Pointer filter = itk::TotalVariationDenoisingImageFilter< DwiVolumeType, DwiVolumeType >::New();
filter->SetInput(gradient_volume);
filter->SetLambda(lambda);
filter->SetNumberIterations(tv_iterations);
filter->Update();
composer->SetInput(i, filter->GetOutput());
}
composer->Update();
denoised_image = mitk::GrabItkImageMemory(composer->GetOutput());
break;
}
case 1:
{
ExtractFilterType::Pointer extractor = ExtractFilterType::New();
extractor->SetInput( itkVectorImagePointer );
ComposeFilterType::Pointer composer = ComposeFilterType::New();
for (unsigned int i = 0; i < itkVectorImagePointer->GetVectorLength(); ++i)
{
extractor->SetIndex(i);
extractor->Update();
GaussianFilterType::Pointer filter = GaussianFilterType::New();
filter->SetVariance(variance);
filter->SetInput(extractor->GetOutput());
filter->Update();
composer->SetInput(i, filter->GetOutput());
}
composer->Update();
denoised_image = mitk::GrabItkImageMemory(composer->GetOutput());
break;
}
case 2:
{
typedef itk::Statistics::GaussianRandomSpatialNeighborSubsampler< NlmFilterType::PatchSampleType, DwiVolumeType::RegionType > SamplerType;
// sampling the image to find similar patches
SamplerType::Pointer sampler = SamplerType::New();
sampler->SetRadius( sampling_radius );
sampler->SetVariance( sampling_radius*sampling_radius );
sampler->SetNumberOfResultsRequested( num_patches );
MITK_INFO << "Starting NLM denoising";
ExtractFilterType::Pointer extractor = ExtractFilterType::New();
extractor->SetInput( itkVectorImagePointer );
ComposeFilterType::Pointer composer = ComposeFilterType::New();
for (unsigned int i = 0; i < itkVectorImagePointer->GetVectorLength(); ++i)
{
extractor->SetIndex(i);
extractor->Update();
NlmFilterType::Pointer filter = NlmFilterType::New();
filter->SetInput(extractor->GetOutput());
filter->SetPatchRadius(patch_radius);
filter->SetNoiseModel(NlmFilterType::RICIAN);
filter->UseSmoothDiscPatchWeightsOn();
filter->UseFastTensorComputationsOn();
filter->SetNumberOfIterations(nlm_iterations);
filter->SetSmoothingWeight( 1 );
filter->SetKernelBandwidthEstimation(true);
filter->SetSampler( sampler );
filter->Update();
composer->SetInput(i, filter->GetOutput());
MITK_INFO << "Gradient " << i << " finished";
}
composer->Update();
denoised_image = mitk::GrabItkImageMemory(composer->GetOutput());
break;
}
}
mitk::DiffusionPropertyHelper::SetGradientContainer(denoised_image, mitk::DiffusionPropertyHelper::GetGradientContainer(input_image));
mitk::DiffusionPropertyHelper::SetReferenceBValue(denoised_image, mitk::DiffusionPropertyHelper::GetReferenceBValue(input_image));
mitk::DiffusionPropertyHelper::InitializeImage( denoised_image );
std::string ext = itksys::SystemTools::GetFilenameExtension(outImage);
if (ext==".nii" || ext==".nii.gz")
mitk::IOUtil::Save(denoised_image, "DWI_NIFTI", outImage);
else
mitk::IOUtil::Save(denoised_image, outImage);
}
catch (itk::ExceptionObject e)
{
std::cout << e;
return EXIT_FAILURE;
}
catch (std::exception e)
{
std::cout << e.what();
return EXIT_FAILURE;
}
catch (...)
{
std::cout << "ERROR!?!";
return EXIT_FAILURE;
}
return EXIT_SUCCESS;
}
void Focus::MakeVarianceImage()
{
UCharImageType::Pointer img;
if(imgIn)
img = imgIn;
else
{
typedef itk::RGBToLuminanceImageFilter< RGBImageType, UCharImageType > ConvertFilterType;
ConvertFilterType::Pointer convert = ConvertFilterType::New();
convert->SetInput( imgInColor );
convert->Update();
img = convert->GetOutput();
}
typedef itk::VarianceImageFunction< UCharImageType2D > VarianceFunctionType;
typedef itk::ExtractImageFilter< UCharImageType, UShortImageType2D > ExtractFilterType;
std::cout << "Making Variance Image";
int size1 = (int)img->GetLargestPossibleRegion().GetSize()[0];
int size2 = (int)img->GetLargestPossibleRegion().GetSize()[1];
int size3 = (int)img->GetLargestPossibleRegion().GetSize()[2];
varImg = FloatImageType::New();
FloatImageType::PointType origin;
origin[0] = 0;
origin[1] = 0;
origin[2] = 0;
varImg->SetOrigin( origin );
FloatImageType::IndexType start = {{ 0,0,0 }};
FloatImageType::SizeType size = {{ size1, size2, size3 }};
FloatImageType::RegionType region;
region.SetSize( size );
region.SetIndex( start );
varImg->SetRegions( region );
varImg->Allocate();
for(int z = 0; z < size3; ++z)
{
std::cout << ".";
UCharImageType::IndexType index = { {0,0,z} };
UCharImageType::SizeType size = { {size1, size2, 0} };
UCharImageType::RegionType region;
region.SetSize(size);
region.SetIndex(index);
ExtractFilterType::Pointer extract = ExtractFilterType::New();
extract->SetInput( img );
extract->SetExtractionRegion( region );
extract->Update();
UShortImageType2D::Pointer im2 = extract->GetOutput();
typedef itk::MeanImageFilter<UShortImageType2D,UShortImageType2D> MeanFilterType;
typedef itk::SquareImageFilter<UShortImageType2D,UShortImageType2D> SquareFilterType;
typedef itk::SubtractImageFilter<UShortImageType2D,UShortImageType2D> SubtractFilterType;
UShortImageType2D::SizeType radiussize = {{radius, radius}};
MeanFilterType::Pointer mean1 = MeanFilterType::New();
mean1->SetInput(im2);
mean1->SetRadius(radiussize);
SquareFilterType::Pointer sq1 = SquareFilterType::New();
sq1->SetInput(mean1->GetOutput());
SquareFilterType::Pointer sq2 = SquareFilterType::New();
sq2->SetInput(im2);
MeanFilterType::Pointer mean2 = MeanFilterType::New();
mean2->SetInput(sq2->GetOutput());
mean2->SetRadius(radiussize);
SubtractFilterType::Pointer sb1 = SubtractFilterType::New();
sb1->SetInput1(mean2->GetOutput());
sb1->SetInput2(sq1->GetOutput());
sb1->Update();
typedef itk::ImageRegionIterator<FloatImageType> FloatIteratorType;
typedef itk::ImageRegionIterator<UShortImageType2D> UShortIteratorType;
FloatIteratorType fit(varImg,region);
UShortIteratorType uit(sb1->GetOutput(),sb1->GetOutput()->GetLargestPossibleRegion());
for(fit.GoToBegin(),uit.GoToBegin();!uit.IsAtEnd(); ++fit, ++uit)
{
//printf("%d ", int(uit.Get()));
fit.Set(uit.Get());
}
/* // DONT USE THIS BECAUSE IT IS VERY SLOW
VarianceFunctionType::Pointer varFunction = VarianceFunctionType::New();
varFunction->SetInputImage( im2 );
varFunction->SetNeighborhoodRadius( radius );
for(int x=0; x<size1; ++x)
{
for(int y=0; y<size2; ++y)
{
UCharImageType2D::IndexType ind;
ind[0] = x;
ind[1] = y;
float var = (float)varFunction->EvaluateAtIndex( ind );
FloatImageType::IndexType ind3;
ind3[0] = x;
ind3[1] = y;
ind3[2] = z;
varImg->SetPixel(ind3, var);
}
}
*/
}
typedef itk::ImageFileWriter<FloatImageType> FloatWriter;
FloatWriter::Pointer fwriter = FloatWriter::New();
fwriter->SetInput(varImg);
fwriter->SetFileName("test_fwriter.mhd");
fwriter->Update();
/*
//Rescale:
typedef itk::RescaleIntensityImageFilter< FloatImageType, UCharImageType > RescaleType;
RescaleType::Pointer rescale = RescaleType::New();
rescale->SetOutputMaximum( 255 );
rescale->SetOutputMinimum( 0 );
rescale->SetInput( varImg );
rescale->Update();
*/
std::cout << "done\n";
}
