Histographic Segmentation

1. Choose Tools > Histographic Segmentation on the menu bar.

   The Histographic Segmentation dialog appears.

2. Choose the dataset that you want to plot on the X axis in the X axis dataset drop-down menu.
3. Choose the dataset that you want to plot on the Y axis in the Y axis Y dataset drop-down menu.

   

   NOTE The 2D and 3D implementation of Sobel of the selected dataset is available by default for plotting on the Y axis.

4. Choose a mask in the Mask drop-down menu, if available and if required. If a mask is selected, only data points within the mask will be plotted.

   

   NOTE Click the Refresh button to update the list of available datasets and masks, if you added new data to the Data Properties and Settings panel while you were working in the Histographic Segmentation context.

5. Select the required number of bins — 64, 128, 256, or 512 — for the histogram, if required.

   

6. Click the Compute Histogram button. The datasets are plotted in the dialog.
7. Adjust the display of the histogram, if required.

   You can change the color map applied to the histogram, as well as display contour lines and adjust the opacity of the ROIs (see Modifying Histograms).

8. Create the required number of regions of interest (see Creating Regions of Interest).

1. Click the Options button in the Histographic Segmentation dialog.

   The Histogram Options dialog appears.

2. Select the required options, as described in the above table.
3. Do one of the following:
   • Click Apply to preview your changes.
   • Click OK to apply your changes and close the dialog.
   • Click Cancel to discard all changes and close the dialog.

The plot tools available in the Histographic Segmentation dialog let you pan and zoom the figure, as well as edit the titles and attributes for each axis. You can also save the figure to a number of different file formats.

1. Click the Create New ROI button in the Regions of interest box.
2. Add data points to the selected region of interest with the Brush tool.

   You can choose to work in the Histogram or Image domain or both (see Working in the Histogram or Image Domain).

3. Add the required data points to the selected region of interest as follows:
   • Use the scroll wheel on your mouse to change the brush size, if required.
   • Hold-down Left Ctrl (or your configured key) to add data points to the selected region of interest.
   • Hold down Left Shift (or your configured key) to remove data points from the selected region of interest.

     NOTE You can change slices while you work. Click the Refresh Preview button in the Image domain box to update the view of a new slice.

4. Create additional regions of interest, if required.
5. Export and and/or expand the regions of interest that you created (see Exporting Regions of Interest and Expanding Regions of Interest).

Options for working in the Histogram domain are available in the Histogram domain box, shown below.

Histogram domain box

Options for working in the Image domain are available in the Image domain box, shown below.

Image domain box

1. Check your segmentation on representative slices within the dataset with which you are working and then make any necessary adjustments, recommended.

   After you scroll through the dataset, you must click the Refresh Preview button to update the preview.

2. Click the Export Selected ROI button.
3. Enter a name for the selected data in the Export ROIs dialog, optional.

   If a name is not entered, then the names assigned in the Histographic Segmentation dialog will be retained with the designation Hist. Seg. appended at the beginning.

   If a name is entered, the new name plus the names assigned in the Histographic Segmentation dialog will be added to the new data.

4. Select the required export options as indicated below.
   • Choose Export selected ROIs one-by-one to export each selected region of interest as a new ROI.
   • Choose Export selected ROIs as a multi-ROI to export all selected regions of interest as a single multi-ROI.
5. Click the OK button.

   The exported region(s) of interest appear in the Data Properties and Settings panel (see ROI Properties and Settings and Multi-ROI Properties and Settings for information about working with regions of interest and multi-ROIs).

The watershed algorithm, whose name comes from an analogy with hydrology. has many applications in image processing, such as automated object segmentation or separation. Starting from user-defined markers, the watershed algorithm treats voxel values as a local topography (elevation). The algorithm then floods basins from the markers, until basins attributed to different markers meet on watershed lines that correspond to the desired segmentation.

This algorithm depends on the following inputs:

1. Labeled regions that are used as seed areas for the flooding. At the end of the process there will be as many separated objects as markers labeled differently.
2. An image that plays the role of the landscape height field or altitude map that controls the flood progression and finally the location of watershed separations.
3. A distance map that provides the priority map input for a watershed process.

Different applications can be achieved by carefully choosing the inputs.

1. Add the required regions of interest that define the inputs used for the expansion.

   NOTE You must create a least two regions of interest to use the watershed expansion scheme.

2. Check your segmentation on representative slices within the dataset and make any necessary adjustments, recommended.

   After you scroll through the dataset, you must click the Refresh Preview button to update the preview.

3. Select the required algorithm in the Expand ROIs drop-down list and then click the Start button.
4. Select the dataset that will provide the landscape for the segmentation in the Watershed dialog. The Sobel of the selected dataset is recommended, if available.

   

5. Select the Use mask option, if you want to limit the segmentation to only data points within the previously selected mask.
6. Select the required geometry — 6, 18, or 26 — in the Geometry box.

7. Click the OK button.

   New regions of interest generated from the seed points are added to the Data Properties and Settings panel (see ROI Properties and Settings).