Get Started

Apply a mask

Although masks are binary, they can be applied to images to filter out pixels where the mask is False.

NumPy's where() function is a flexible way of applying masks. It takes three arguments:

np.where(condition, x, y)

condition, x and y can be either arrays or single values. This allows you to pass through original image values while setting masked values to 0.

Let's practice applying masks by selecting the bone-like pixels from the hand x-ray (im).

This is a part of the course

“Biomedical Image Analysis in Python”

View Course

Exercise instructions

  • Create a Boolean bone mask by selecting pixels greater than or equal to 145.
  • Apply the mask to your image using np.where(). Values not in the mask should be set to 0.
  • Create a histogram of the masked image. Use the following arguments to select only non-zero pixels: min=1, max=255, bins=255.
  • Plot the masked image and the histogram. This has been done for you.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Import SciPy's "ndimage" module
____

# Screen out non-bone pixels from "im"
mask_bone = ____
im_bone = np.where(____, ____, ____)

# Get the histogram of bone intensities
hist = ____

# Plot masked image and histogram
fig, axes = plt.subplots(2,1)
axes[0].imshow(im_bone)
axes[1].plot(hist)
format_and_render_plot()
Edit and Run Code