Module: Mask for Patches ()

Description:

This is an experimental module from the Xtra Library: https://xtras.amira-avizo.com.

This module generates a binary image, the same size as the input, where patches of the specified size are shown around each of the input landmarks.

The primary intended use for this module is help preparing data for Deep Learning Training, by first marking areas of interest around specific points. To do so, first create a Landmark Set and use its editor to place the landmarks, or the Xtra module Random Landmarks.

Then, this module allows creating a binary mask. The intent is then to perform manual segmentation only within the selected area. This can be achieved using the Segmentation Editor, selecting the material and navigating with the buttons 'Next Selection' or 'Previous Selection'.

Finally, use the Xtra module Extract Patches, to extract patches both of the grayscale image and the manual segmentation, and use these as inputs for training Deep Learning models.

Connections:

Data [required]
Input image.

Landmarks [required]
Landmarks defining the center of the patches.

Console

Opens the Python Script Object console of the module as the active console window.

Mode

Choose between 2D and 3D patches.

Size of Patches [px]

Size of the image patches to be extracted, in number of voxels.