python - 如何使用特定平面将 3d Nifti(.nii) 图像切片为 2d 图像？

Question

我正在编写一个脚本，可以估计 3d Nifti(.nii) 图像的清晰度。在我的方法中，我需要先取出3D图像的x-z(轴)切片，然后将其保存为.png文件。(为了提高效率，只取一个)然后，估计图像的清晰度。但是，我不知道如何使用特定平面(切片)来切片 3D 图像。是否有任何现有的代码或库可以进行切片？

我使用的是 Python 3.7(在 Window 10 中运行)。

我尝试过这个库:https://pypi.org/project/nii2png/但是，它无法输出单个硅片。

我也尝试过这个页面的方法 https://nipy.org/nibabel/coordinate_systems.html#introducing-someone然而，这不起作用。原因可能是 Nifti 文件不同。我认为nifti格式文件有两种。

import nibabel as nib
import numpy as np
import matplotlib.pyplot as plt

def show_slices(slices):
    """ Function to display row of image slices """
    fig, axes = plt.subplots(1, len(slices))
    for i, slice in enumerate(slices):
        axes[i].imshow(slice.T, cmap="gray", origin="lower")

data = nib.load('D:\\Work\\Script\\__Project\\s\\ADNI\\good_img\\MPRAGE_SENSE2\\2012-11-08_07_32_36.0\\S174286\\ADNI_002_S_5018_MR_MPRAGE_SENSE2__br_raw_20121112145413785_28_S174286_I346236.nii')
data.get_fdata()
data = data.get_fdata()
data.shape
#d_data = np.delete(data, 3, 0) #doesn't work, because it's object of type 'Nifti1Image'
#matplotlib inline
#plt.imshow(data.get_data()[:,:,50])
plt.plot(np.mean(data,axis=(0,1,2)))
plt.show()

slice_0 = data[26, :, :, :]
slice_1 = data[:, 30, :, :]
slice_2 = data[:, :, 16, :]
slice_3 = data[:, :, :, 0]
show_slices([slice_0, slice_1, slice_2, slice_3])
plt.suptitle("Center slices for EPI image") 

然后我得到了错误:

Warning (from warnings module):
  File "D:\Program_Files_2\Python\lib\site-packages\dicom\__init__.py", line 53
    warnings.warn(msg)
UserWarning: 
This code is using an older version of pydicom, which is no longer 
maintained as of Jan 2017.  You can access the new pydicom features and API 
by installing `pydicom` from PyPI.
See 'Transitioning to pydicom 1.x' section at pydicom.readthedocs.org 
for more information.

Traceback (most recent call last):
  File "D:\Work\Script\__Project\s\try_load_nii_image_and_view_slice_3.py", line 25, in <module>
    show_slices([slice_0, slice_1, slice_2, slice_3])
  File "D:\Work\Script\__Project\s\try_load_nii_image_and_view_slice_3.py", line 9, in show_slices
    axes[i].imshow(slice.T, cmap="gray", origin="lower")
  File "D:\Program_Files_2\Python\lib\site-packages\matplotlib\__init__.py", line 1601, in inner
    return func(ax, *map(sanitize_sequence, args), **kwargs)
  File "D:\Program_Files_2\Python\lib\site-packages\matplotlib\cbook\deprecation.py", line 369, in wrapper
    return func(*args, **kwargs)
  File "D:\Program_Files_2\Python\lib\site-packages\matplotlib\cbook\deprecation.py", line 369, in wrapper
    return func(*args, **kwargs)
  File "D:\Program_Files_2\Python\lib\site-packages\matplotlib\axes\_axes.py", line 5671, in imshow
    im.set_data(X)
  File "D:\Program_Files_2\Python\lib\site-packages\matplotlib\image.py", line 690, in set_data
    .format(self._A.shape))
TypeError: Invalid shape (1, 256, 256) for image data

Answer 1

您的错误在于选择切片，请注意，如果您正在处理4D图像[x,y,z_Slice,time_Frame] 并且您想要选择不同的切片，您应该保留空间信息 x 和 y ，并选择一个切片和一个帧(如果您的图像是 4D 而不是 3D)

# slices 0 --> 3 from frame 0   

slice_0 = data[:, :, 0, 0]
slice_1 = data[:, :, 1, 0]
slice_2 = data[:, :, 2, 0]
slice_3 = data[:, :, 3, 0]