Working with NumPy Array Images¶

In [1]:

import itk
import numpy as np
import imageio
from itkwidgets import view, compare, checkerboard

Images as NumPy arrays can be registered.

Convert them to floating point arrays for registration.

In [2]:

fixed = imageio.imread('data/CT_2D_head_fixed.mha')
fixed = np.asarray(fixed).astype(np.float32)
type(fixed)

Out[2]:

numpy.ndarray

In [3]:

moving = imageio.imread('data/CT_2D_head_moving.mha')
moving = np.asarray(moving).astype(np.float32)
type(moving)

Out[3]:

numpy.ndarray

In [4]:

compare(fixed, moving, ui_collapsed=True)

AppLayout(children=(HBox(children=(Label(value='Link:'), Checkbox(value=False, description='cmap'), Checkbox(v…

Before registration, the moving image is not aligned with the fixed image.

In [5]:

checkerboard(fixed, moving, pattern=10)

VBox(children=(Viewer(annotations=False, interpolation=False, rendered_image=<itk.itkImagePython.itkImageF2; p…

In [6]:

# Register!
registered, parameters = itk.elastix_registration_method(fixed, moving)
type(registered)

Out[6]:

itk.itkPyBufferPython.NDArrayITKBase

In [7]:

compare(fixed, registered, ui_collapsed=True)

AppLayout(children=(HBox(children=(Label(value='Link:'), Checkbox(value=False, description='cmap'), Checkbox(v…

The registered moving image is aligned with the fixed image

In [8]:

checkerboard(fixed, registered, pattern=10)

VBox(children=(Viewer(annotations=False, interpolation=False, rendered_image=<itk.itkImagePython.itkImageF2; p…

In [ ]: