Simple Region Growing Segmentation

Overview

A simple region growing segmentation algorithm based on intensity statistics. To create a list of fiducials (Seeds) for this algorithm, click on the tool bar icon of an arrow pointing to a sphere fiducial to enter the ‘place a new object mode’ and then use the Markups module. This module uses the Slicer Command Line Interface (CLI) and the ITK filters CurvatureFlowImageFilter and ConfidenceConnectedImageFilter.

Panels and their use

Smoothing Parameters: Parameters to denoise the image prior to segmenting

  • Smoothing iterations (smoothingIterations): Number of smoothing iterations

  • Timestep (timestep): Timestep for curvature flow

Segmentation Parameters: Parameters to prescribe the region growing

  • Number of iterations (iterations): Number of iterations of region growing

  • Multiplier (multiplier): Number of standard deviations to include in intensity model

  • Neighborhood Radius (neighborhood): The radius of the neighborhood over which to calculate intensity model

  • Output Label Value (labelvalue): The integer value (0-255) to use for the segmentation results. This will determine the color of the segmentation that will be generated by the Region growing algorithm

  • Seeds (seed): Seed point(s) for region growing

IO: Input/output parameters

  • Input Volume (inputVolume): Input volume to be filtered

  • Output Volume (outputVolume): Output filtered

Contributors

Jim Miller (GE)

Acknowledgements

This command module was derived from Insight/Examples (copyright) Insight Software Consortium