0 ×

Waehlby Cell Clump Splitter

StreamableKNIME Image Types and Nodes version 1.7.0.201812031714 by University of Konstanz

Waehlby Cell Clump Splitter performs object split and merge by shape on a labeling. This may greatly improve quality of a labeling, especially for cell segmentation.

If your Image contains a lot of holes, you may want to consider preprocessing the input with the "Fill Holes" node or other kinds of hole filling.

The method used was mainly inspired by a paper by C. Waehlby, "Combining intensity, edge and shape information for 2D and 3D segmentation of cell nuclei in tissue sections", and the method use by CellCognition (cellcognition.org).

Options

Distance Merge Threshold
Objects closer than this distance threshold (in pixels) will be considered candidates for merging. Higher values usually result in longer computation times.
Gauss Size
Since this split and merge method performs gaussian convolution in it's preprocessing step, you may here enter the size parameter for it. Usually higher gauss size leads to less splitting, but longer computation times.
Size Merge Threshold
Objects which contain less pixels than "Size Merge Threshold" will be merged regardless of their shape, presuming there is another object close enough. Higher values may slightly result in longer computation duration.

Column Selection

Column Creation Mode

Mode how to handle the selected column. The processed column can be added to a new table, appended to the end of the table, or the old column can be replaced by the new result

Column Suffix
A suffix appended to the column name. If "Append" is not selected, it can be left empty.
Column Selection
Selection of the columns to be processed.

Input Ports

Table containing labeling and image columns. Which will be used can be chosen in the "Column Selection" tab.

Output Ports

Table containing or consiting of the refined labeling. The resulting table can be modified over the "Column Selection" tab.

Views

Image Viewer
Another, possibly interactive, view on table cells. Displays the selected cells with their associated viewer if it exists. Available views are:
- BigDataViewer
-- A viewer shown when the user selects an interval of rows and columns in the viewer. This viewer combines all images and labelings in the selected interval to one image by rendering them next to each other. Alternatively, the images and labelings can be layed over each other.
- Missing Value Viewer
-- An empty viewer that is shown when the input cell has no value to display.
- Combined View
-- A viewer shown when the user selects an interval of rows and columns in the viewer. This viewer combines all images and labelings in the selected interval to one image by rendering them next to each other. Alternatively, the images and labelings can be layed over each other.
- Image Viewer
-- This viewer renders the selected image-cell.
- Histogram Viewer
-- This viewer shows the histogram of the currently selected image.
- XML
-- XML tree
- Labeling View
-- View on a labeling/segmentation

Update Site

To use this node in KNIME, install KNIME Image Types and Nodes from the following update site:

Drag me!
Wait a sec! You want to explore and install nodes even faster? We highly recommend our NodePit for KNIME extension for your KNIME Analytics Platform.