Simpleitk use - 3 Common operations

1. corrosion / inflation

1.1 python Realization

import SimpleITK as sitk

demo_mask_path = "./seg.nii.gz"
demo_mask_image = sitk.ReadImage(demo_mask_path)
dilate_img=sitk.GrayscaleDilate(demo_mask_image , kernelRadius=[3,3,3])
sitk.WriteImage(dilate_img, "./dilatenii.gz")

The effect is similar to the following ：

---

Reference resources ：

• Welcome to the SimpleITK Image Filtering Tutorial
• Find it according to the previous reference link ：GrayscaleErodeImageFilter, Go on SimpleITK Online documentation for To search
• And find out ：itk::simple::GrayscaleErodeImageFilter Class Reference
  • These include ：GrayscaleErode() This interface .
• If you accidentally forget the meaning of corrosion and expansion , Take a look at this article ：opencv Learning notes （ 8、 ... and ）： Image morphology operation
  • Corrosion is the dark side getting more , Less light , Every time filter Take the minimum value to cover （0-255,0 It's black ）
  • Expansion is the reduction of darkness , Less light , Every time filter Take the maximum value to cover
• SimpleITK Analyze medical images
• ITK07 Mask processing
• ITK Do corrosive operation , This uses itkGrayscaleErodeImageFilter This class

1.2. C++ Realization

If you want to search ITK Some classes of , You can go straight to SimpleITK Documents Search in , Those... Will be shown here ImageFilter Corresponding ITK The documentation in .

for example ： Search in the document erosion, You can get the following results , It's better to see which function you need

There are several more. , I won't put the screenshot here

1.2.1 inflation (Dilate)

Expansion corresponds to ImageFilter yes ：

• itk::BinaryDilateImageFilter< TInputImage, TOutputImage, TKernel > Class Template Reference
• Expansive C++ Examples in ：SphinxExamples/src/Filtering/BinaryMathematicalMorphology/DilateABinaryImage/Code.cxx
• As follows ：

#include "itkImage.h"
#include "itkImageFileReader.h"
#include "itkImageFileWriter.h"
#include "itkFlatStructuringElement.h"
#include "itkBinaryDilateImageFilter.h"
 
int main(int argc, char * argv[])
{
    
  if (argc < 4)
  {
    
    std::cerr << "Usage: " << std::endl;
    std::cerr << argv[0] << " <inputImage> <outputImage> <radius>";
    std::cerr << std::endl;
    return EXIT_FAILURE;
  }
  const char *       inputImage = argv[1];
  const char *       outputImage = argv[2];
  const unsigned int radiusValue = std::stoi(argv[3]);
 
  using PixelType = unsigned char;
  constexpr unsigned int Dimension = 2;
  using ImageType = itk::Image<PixelType, Dimension>;
 
  const auto input = itk::ReadImage<ImageType>(inputImage);
 
  using StructuringElementType = itk::FlatStructuringElement<Dimension>;
  StructuringElementType::RadiusType radius;
  radius.Fill(radiusValue);
  StructuringElementType structuringElement = StructuringElementType::Ball(radius);
 //  Mainly this sentence 
  using BinaryDilateImageFilterType = itk::BinaryDilateImageFilter<ImageType, ImageType, StructuringElementType>;
 
  BinaryDilateImageFilterType::Pointer dilateFilter = BinaryDilateImageFilterType::New();
  dilateFilter->SetInput(input);
  dilateFilter->SetKernel(structuringElement);
  dilateFilter->SetForegroundValue(255); // Value to dilate
 
  try
  {
    
    itk::WriteImage(dilateFilter->GetOutput(), outputImage);
  }
  catch (itk::ExceptionObject & error)
  {
    
    std::cerr << "Error: " << error << std::endl;
    return EXIT_FAILURE;
  }
 
  return EXIT_SUCCESS;

1.2.2 corrosion (Erode)

Corrosion corresponds to ImageFilter yes ：

• [itk::BinaryErodeImageFilter< TInputImage, TOutputImage, TKernel > Class Template Reference](itk::BinaryErodeImageFilter< TInputImage, TOutputImage, TKernel > Class Template Reference)
• Corrosive C++ Examples in ：SphinxExamples/src/Filtering/MathematicalMorphology/ErodeBinaryImageUsingFlatStruct/Code.cxx, as well as SphinxExamples/src/Filtering/BinaryMathematicalMorphology/ErodeABinaryImage/Code.cxx

2. SimpleITK Conduct padding operation

My usage scenarios ：

• Yes mask The image is done crop, Deleted mask Some unnecessary marking points in
• crop after mask The image size has changed , So we need to change back to crop Previous size

import SimpleITK as sitk

demo_mask_path = "./seg.nii.gz"
demo_mask_image = sitk.ReadImage(demo_mask_path)

cropped_image = sitk.Crop(demo_mask_image ,lowerBoundaryCropSize=[0,0,0],upperBoundaryCropSize=[crop_size,0,0])

half_image_y_pad =sitk.ConstantPad(cropped_image ,padLowerBound=[0,0,0],padUpperBound=[crop_size,0,0],constant=0)

ConstantPad and Crop It's like , Just one is cutting , One is to add .

---

Reference resources ：

• itk::simple::ConstantPadImageFilter Class Reference

3. SimpleITK Extract a slice

According to the reference 1, You can know ,

• Pure use SimpleITK Of Image Go slice , The code is more complex
• It is suggested to directly turn to numpy Array

import SimpleITK as sitk

demo_mask_path = "./seg.nii.gz"
demo_mask_image = sitk.ReadImage(demo_mask_path)
demo_array = sitk.GetArrayFromImage(demo_mask_image)
#  Do some array slicing 
....
demo_image =sitk.GetImageFromArray(demo_array)
demo_image.CopyInformation(demo_mask_image )

---

Reference resources ：

1. SimpleITK file ：Advanced Image Reading
2. SimpleITK reading a slice of an image
3. Python/ExtractSlice.py
4. itk::simple::ExtractImageFilter Class Reference

4. SimpleITK Of GetSize and GetArrayFromImage After xyz Corresponding

Reference resources ：【SimpleITK course 】GetSize() Methods and GetArrayFromImage() Method


namely

padding_path="XXXX.nii.gz"
padding_image=sitk.ReadImage(padding_path)
print(padding_image.GetSize())
padding_array = sitk.GetArrayFromImage(padding_image)
print(padding_array.shape)
padding_array[78,131,80]
> (240, 240, 155)  (x,y,z)
  (155, 240, 240)  (z,y,x)
2

5. SimpleITK Threshold osteotomy

The data I use is relatively simple , Here is a simple preprocessing .

import SimpleITK as sitk
image_path = "./im.nii.gz"
image = sitk.ReadImage(image_path)
skull_mask =sitk.BinaryThreshold(image, lowerThreshold=125, upperThreshold=2000, insideValue=1, outsideValue=0)
#  stay 125~2000 Within the scope of , The assignment is 1, Out of range , The assignment is 0. Got mask Namely 125~2000 The content of this intensity value , Bones .

Like the image below ：

• Above is the brain CT Adjust the window width and window level to level：700,window：500 The resulting image
• Here are the results of using threshold osteotomy , It looks ok
  

---

Reference resources ：

• itk::simple::ThresholdImageFilter Class Reference
• Introduction to ITK Segmentation in SimpleITK Notebooks
• ITK Basics ( Two ) — Image segmentation General Threshold