Scribd
Upload
17 views

Medicalimageanalysisinpython Sample

This document discusses analyzing medical images in Python. It shows how to load CT scan data from nii files, view different slices of the image volume, and explore metadata contained in DICOM files. It also demonstrates using windowing to highlight different tissue types by adjusting contrast levels and combining results. The goal is to help the reader get started visualizing and processing medical images programmatically.

Uploaded by

Maryam Berradi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
17 views

Medicalimageanalysisinpython Sample

This document discusses analyzing medical images in Python. It shows how to load CT scan data from nii files, view different slices of the image volume, and explore metadata contained in DICOM files. It also demonstrates using windowing to highlight different tissue types by adjusting contrast levels and combining results. The goal is to help the reader get started visualizing and processing medical images programmatically.

Uploaded by

Maryam Berradi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

MEDICAL IMAGE

ANALYSIS

IN PYTHON
by Renat Alimbekov

First edition
2021
from matplotlib import cm # color schemes for visualization
from matplotlib import pyplot as plt # library for visualization

We read the file using the load method, and to get the image, we need to use the
get_fdata function. We will work with the file volume_pt5 / volume-44.nii

filepath = 'volume_pt5/volume-44.nii'
imagedata=nibabel.load(filepath)
array = imagedata.get_fdata()

turn the image 90 degrees and look at the shape of the file contents.

array = np.rot90(np.array(array))
print(array.shape)

The output will be Height x Width x Depth - (512, 512, 119). Depth here means CT
slices. Let's visualize a 50 and 118 CT slice.

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)
ax2.imshow(array[...,118].astype(np.float32), cmap=plt.cm.bone)

Self-study task: visualize other CT slices

Explore of metadata

As I said before, DICOM files contain metadata in addition to the image. For example:
age, gender, study modality, name, body part and body position.

Let's try to explore our metadata. Let's start with what we already know, the file reads.

example = 'stage_2_images/ID_01fe90211.dcm'
Indeed, after applying Windowing, it highlights structures more.

We've reviewed the recommended window settings. Let's take a look at a few more
exotic options. For example, you can mix Windowing.

def rainbow_bsb_window(img):
brain_img = windowed(img, 40, 80)
subdural_img = windowed(img, 80, 200)
bone_img = windowed(img, 600, 2000)
combo = (brain_img*0.3 + subdural_img*0.5 + bone_img*0.2)
return combo

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(rainbow_bsb_window(array[...,50].astype(np.float32)))
ax2.title.set_text('Windowing image')

Self-study task: try other Windowing. Evaluate the result

You might also like