Medical Image Analysis in Python_468 x 60 copy 2.png

medical.tar.gz

medical

In this course, you’ll learn the basics of medical image analysis using Python. You will learn to display and interpret X-ray and CT scans. This course uses relevant Python libraries and commands on medical images for format conversion, segmentation, and analyzing metadata. You can successfully complete this course with only a basic understanding of Python and no background in medical imaging.

Medical Image Analysis in Python

# An image before and after windowed() 


Let’s visualize the image before and after applying the `windowed()` function. In the code below, we can see the difference between the original image and the image after applying `windowed()`.


from matplotlib import pyplot as plt 
import nibabel
import numpy as np
filepath = 'volume_pt5/volume-44.nii' 
imagedata = nibabel.load(filepath) 
array = imagedata.get_fdata()
array = np.rot90(np.array(array))
def windowed(px, w, l):
        px_min = l - w//2
        px_max = l + w//2
        px[px<px_min] = px_min
        px[px>px_max] = px_max
        return (px-px_min) / (px_max-px_min)
f = plt.figure(figsize=(12,12)) 
ax = f.add_subplot(121)
ax2 = f.add_subplot(122)
ax.imshow(array[...,50].astype(np.float32),cmap=plt.cm.bone) 
ax.title.set_text('Original image') 
ax2.imshow(windowed(array[...,50].astype(np.float32), 150,30), cmap=plt.cm.bone)
ax2.title.set_text('Windowing image')

Let’s take a closer look at the code above.

* In **line 7**, `rot90()` rotates the array by 90 degrees in the plane specified by an axis (0 or 1).
* **Lines 8–13** define the windowed function.
* **Lines 17 and 19** show images before and after applying the `windowed()` function.

After applying windowing, the structures are more highlighted.
# Other kinds of windowing
We reviewed the recommended window settings. Let’s look at a few lesser-known options. For example, we can mix windowing by performing the functions below.
* We'll apply the `rainbow_bsb_window()` for other windowing options. 
* IIn this function, we’ll adjust the width and level to get a colorful image.
* In the code below, we can see the difference between the original and the colorful image after applying `rainbow_bsb_window()`. 







Learn to visualize the image before and after transformation.

__default

Visualize the Windowing

An image before and after windowed()