Voting

Class: NodeMaskVoting

Node Icon

This node performs pixelwise voting among an arbitrary number of input binary images, where each image represents a segmentation of the same region in the same frame of reference. The majority value is selected for each pixel in the output mask. If a pixel has the same number of votes for TRUE and FALSE, it is set to TRUE. For two binary masks, the output is equivalent to the Boolean OR operation.

Example workflows

STAPLE and voting workflow

Inputs

Masks

At least two binary images of the same size.

Type: Image4DBool, Required, Multiple (Minimum = 2)

Outputs

Vote

A binary mask with the same spatial properties as the input binary mask.

Type: Image4DBool

References

  1. T. Rohlfing and C. R. Maurer, Jr., “Multi - classifier framework for atlas - based image segmentation” Pattern Recognition Letters, 2005.
  2. Voting in SimpleITK

See also

Keywords:

Copyright © 2022, NONPI Medical AB