Neighborhood Connected CLP

From user's Wiki!
Jump to: navigation, search
Neighborhood Connected Threshold Segmentation

General Information

  • Type: CLP
  • Category: Segmentation
  • Author: Xavi Planes
  • Contributor: Xavi Planes
  • Contact:
  • Description: Label pixels that are connected to a seed and lie within a neighborhood. NeighborhoodConnectedImageFilter labels pixels with ReplaceValue that are connected to an initial Seed AND whose neighbors all lie within a Lower and Upper threshold range. Read More....



Label Type Flag / Index Default value / Channel Description
Parameters to denoise the image prior to segmenting
Smoothing iterations integer --smoothingIterations 5 Number of smoothing iterations
Timestep double --timestep 0.0625 Timestep for curvature flow
Parameters to prescribe the region growing
Radius integer-vector --radius 5 Radius of the neighborhood used for a mask.
Lower double --lower 0 Set Upper and Lower Threshold inputs as values
Upper double --upper 1000 Set Upper and Lower Threshold inputs as values
Output Label Value integer --labelvalue 2 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 point coordinateSystem="ras" multiple="true" --seed 0,0,0 Seed point(s) for region growing
Input Volume image index 0 input Input volume to be filtered
Output Volume image index 1 output Output Volume


Sample Data:Atrial Fibrillation

In this example, the heart is segmented but the regions that are small are not included, because the radius has been set to 15:

Neighborhood Connected Threshold Segmentation


Source code: C++ Source code and XML description

Go back to Users