Segmentation Tools

This panel hosts different tools that are used for the image segmentation.

Back to Index --> User Guide --> Panels --> Segmentation Panel

 

Contents

 

The 3D ball

Makes selection as a spherical object in the 3D space with a radius taken from the Radius, px edit box. The Eraser, x edit box modifies increse of the 3D ball eraser, when holding the Clrl key.
A brief demonstration is available in the following video:
https://youtu.be/ZcJQb59YzUA?t=1s

Note! The depth of 3D ball is defined by the pixel dimensions,
see Dataset Parameters in Menu->Dataset->Parameters
Selection modifiers

  • None / ⇧ Shift+left mouse click, add 3D ball selection with the existing one
  • Ctrl + left mouse click, remove 3D ball selection from the current selection layer


 

The 3D lines

The 3D lines tool can be used to draw lines in 3D and arrange them as graphs or skeletons. The 3D lines composed of Nodes (Vertices) connected with Edges (a line that connect two nodes). Separated from each other sets of 3D lines organized into separate trees.
A demonstration is available on: https://youtu.be/DNRUePJiCbE

Modification of nodes is possible using mouse clicks. To increase flexibility, the clicks can be extended with key-modifiers, such as ⇧ Shift, Ctrl, Alt. Each action can be configured depending on needs. Please refer to a table below for various options.
Available actions

  • Add node, add a new node to the active tree; the new point will be connected to the active point (shown in red) of the tree
  • Assign active node, assign the closest node to position of the mouse click, as a new active node
  • Connect to node, connect active node to another existing node
  • Delete node, delete the closest node to position of the mouse click; the edges will be rearranged to prevent splitting of the tree
  • Insert node after active, insert a new node after the active node
  • Modify active node, change position of the active node
  • New tree, add a new node and assign it to a new tree, which is not connected to other trees
  • Split tree, delete the closest node to position of the mouse click and split the tree at this point
Use the [✓] Show lines checkbox to toggle visibility of the lines in the Image View panel.
Press the Table view button to start a window which tables that describe the 3D lines (see below).

Lines 3D View

Table with the list of trees
The upper table shows the list of trees and number of nodes that compose each tree. Each tree should have an unique name!

Right mouse click starts a popup menu with various options:
  • Rename selected tree..., rename selected in the table tree; tree name should be unique!
  • Find tree by node..., find a tree which has a node with provided index
  • Visualize in 3D selected tree(s), plot the selected trees in 3D
  • Save/export selected tree(s), export to MATLAB or save to a file the selected trees, see the Tools panel below for the list of available file formats
  • Delete selected tree(s), delete selected tree from the table
Space between the tables

  • Active tree, an index of the active tree
  • Active node, an index of the active node
  • Table, a combo box to select what should be shown in the lower table: Nodes or Edges
  • Field, a combo box to define an additional field that should be shown the lower table. By default, only the Radius and Weights fields are available
  • Auto jump, when selected, auto jump to the selected node
  • Auto refresh, automatically refresh the tables, may be quite slow with many nodes

Nodes table

The table shows list of nodes and offers multiple actions via a popup menu:

  • Jump to the node, jumps to the selected node and put it in the center of the Image View panel
  • Set as active node, makes the selected node active
  • Rename selected nodes..., assign a new name for the selected nodes
  • Show coordinates in pixels..., by default, the coordinates of the nodes are shown in the physical units of the dataset, i.e. with respect to the bounding box ; this action shows coordinate of the node in pixels
  • New annotations from nodes, generate a new annotations from the position of nodes
  • Add nodes to annotations, add selected nodes to the existing annotations
  • Delete nodes from annotations, delete selected nodes from the existing annotations
  • Delete nodes..., delete selected nodes

Edges table

The table shows list of edges; certain actions available via a popup menu:

  • Jump to the node, jumps to the selected node and put it in the center of the Image View panel
  • Set as active node, makes the selected node active

Tools panel

  • Load, load 3D lines from a file in matlab-compatible lines3d format
  • Save, export to MATLAB or save 3D lines to a file:
  • MATLAB format, *.lines3d, it is recommended to save the 3D lines in the matlab format!
  • Amira Spatial graph, *.am, Amira-compatible format in binary or ascii form
  • Excel format, *.xls, export Nodes and Edges tables to an Excel file
  • Refresh, refresh the tables shown in this window
  • Delete all, delete all 3D lines
  • Visualize in 3D, plot all trees in the 3D space
  • Settings, modify color and thickness of 3D lines


 

Annotations

A set of tools to add/remove annotations. Each annotation allows to mark specific location in the dataset, assign a label and a value to it

Brief demonstration is available in the following videos:
https://youtu.be/3lARjx9dPi0
https://youtu.be/6otBey1eJ0U

Addition and removal of annotations
  • left mouse click, add annotation to the position under the mouse cursor
  • Ctrl + left mouse click, remove annotation that is the closest to the position under the mouse cursor
Annotation panel widgets

  • The Annotation list button starts a window with the list of existing annotations. It is possible to load and save annotations to the main MATLAB workspace or to a file (matlab and excel formats). See more below.
  • The Delete All button removes all annotations
  • Precision edit box - specify number of digits after decimal point
  • [✓] Show prompt checkbox, when ticked a dialog asking for label and value appear after addition of each annotation, otherwise the dialog is not shown and the label and field values are taken from the previously added annotation
  • [✓] Focus on Value checkbox, when ticked, the first parameter during visualization of annotations is value and the second parameter is label.
  • The Display as combobox - enables way how the annotations are displayed in the Image View panel.
      The following modes are available:
    • Marker, show only location of the annotation using a cross-marker
    • Label, show marker and label for each annotation
    • Value, show marker and value for each annotation
    • Label + Value, show marker, label and value for each annotation

List of annotations window

  • The List of annotations table shows a list of annotations.
      The right mouse button click calls an additional popup menu that allows to
    • Jump to annotation, moves the image so that the selected annotation is in the middle of the Image View panel
    • Add annotation, manually add annotation to the list, position of the first and second fields are defined by the [✓] Value eccentric checkbox of the Annotation panel, see above
    • Rename selected annotations, rename names of the selected annotations
    • Batch modify selected annotations, modify annotation values or coordinates using a provided expression
    • Count selected annotations, calculate occurance of each annotation in the list of selected annotations. The results are displayed in the MATLAB command window and copied to the system clipboard
    • Copy selected annotations to clipboard, the selected annotations are copied to the system clipboard as a text string ready to be pasted to Excel
    • Convert selected annotations to Mask..., generate 2D/3D Mask spots centered at each annotation marker. The size of the spot can either be fixed or scaled from the value field of the selected annotations
    • Crop out patches around selected annotations, 2D/3D patch of the predefined size is generated when this operation is used
    • Export selected annotations, export selected annotations in the MATLAB format, landmarks for Amira (Note! only the coordinates are exported to Amira!), PSI format for Amira and Excel
    • Export selected annotations to Imaris, export selected annotations to Imaris (Note! please first export the dataset!)
    • Order, subitems of the Order entry can be used to move annotations towards the top or the bottom of the list
    • Delete annotation, delete selected annotations from the list
  • The Load button, press to import annotations from the main MATLAB workspace or load them from a file
  • The Save button, press to export annotations to the main MATLAB workspace or to save them as a file in MATLAB, Comma-separated CSV format, Excel formats or as landmarks for Amira ( Note! only the coordinates are exported!), or PSI format for Amira
  • The Precision editbox, modify precision of the value field in the table and for the visualization in the Image View panel
  • The [✓] Auto jump checkbox - when enabled, the image in the Image View panel is automatically shifted, thereby placing the selected annotation at the center of the image
  • The Sort table allows to sort annotations based on their Name, Value, X, Y, Z, T
  • The Settings provides configuration of additional settings:
    • Show annotations for extra slices, extra slices to display annotation, when this value 0 annotations only belonging to the current slice are displayed, when a positive number from -value to +value depth
    • Annotation size, size of the annotation marker from 8 to 20pt
  • The Refresh table button updates the list of annotations
  • The Delete all button removes all annotations


 

The Brush tool

Use brush to make selection. The brush size is regulated with the Radius, px edit box
A brief demonstration is available in the following videos:
https://youtu.be/VlTCxVAUxFc https://youtu.be/ZcJQb59YzUA?t=37s


Objects from different image slices may be connected using the Interpolation function (shortcut i or via Menu->Selection->Interpolate), see more in the Selection menu section.
Brush mouse controls

  • Ctrl + Mouse wheel, change brush size
  • None / ⇧ Shift + left mouse click, paint with brush
  • Ctrl + left mouse click, start eraser. The brush radius in the eraser mode could be amplifier using the Eraser, x edit box.

Widgets of the brush panel

Radius, define radius of the brush tool in pixels
Eraser, x, define radius size multiplier when brush is in the eraser mode
Interpolation settings, press to start a dialog that allows to modify the interpolation settings. The settings can also be modified from the Preference dialog and the type can be switched using a dedicated button in the toolbar.
The [✓] Watershed checkbox, when ticked, pixels of the image are clustered using the watershed algorithm and can be selected as clusters (see the following section)
The [✓] SLIC checkbox, , when ticked, pixels of the image are clustered using the SLIC algorithm and can be selected as clusters (see the following section)


Superpixels with the Brush tool

The Superpixels mode can be initiated by selecting the Watershed or SLIC checkbox. In the Superpixels mode the brush tool selects not individual pixels but rather groups of pixels (superpixels). While drawing the selection of the last superpixel can be undone by pressiong the Ctrl+Z shortcut.

The superpixels are calculated using the

  • SLIC (Simple Linear Iterative Clustering, good for objects with distinct intensities) algorithm written by Radhakrishna Achanta et al., 2015 , Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland.
  • Watershed (good for objects with distinct boundaries).

The two additional edit boxed (N, Compact/Invert) offer possibility to modify the size of generated superpixels (see below). The values in the N edit box can be changed using the Ctrl+Alt + mouse wheel or Ctrl+Alt+⇧ Shift + mouse wheel shortcuts.

References:

  • Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine S?sstrunk, SLIC Superpixels Compared to State-of-the-art Superpixel Methods, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, num. 11, p. 2274 - 2282, May 2012.
  • Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine S?sstrunk, SLIC Superpixels, EPFL Technical Report no. 149300, June 2010.

The set of superpixels is individual for each magnification (especially in the SLIC mode). It is possible to define size of superpixels (the N edit box, default value 220 for SLIC, for Watershed use lower numbers) and compactness (the Compact edit box; higher compactness gives more rectangularly shaped superpixels). In the Watershed mode the Compact edit box is called Invert; when objects have dark boundaries over bright backround number in the Invert edit box should be 1 (or higher), if the objects have bright boundaries over dark background this number should be 0.

During drawing the boundaries of the superpixels for the SLIC mode are shown using the drawregionboundaries.m function written by Peter Kovesi Centre for Exploration Targeting, School of Earth and Environment, The University of Western Australia.

Note 1! The Superpixels mode is sensitive to the [✓] Adapt. checkbox in the Selection panel. When the [✓] Adapt. checkbox is selected the superpixels are selected based on the mean value of the initial selection plus/minus standard deviation within the same area multiplied by the factor specified in the Adapt. editbox of the Selection panel.

Note 2! While drawing the value in the Adapt. editbox may be changed using the mouse wheel.

Note 3! The function relies on slicmex.c that should be compiled for your operating system. Please refer to the Microscopy Image Browser System Requirements section for details.



 

The Black and White Thresholding tool

Makes black and white thresholding of the current image slice or the whole dataset (depending on status of the [✓] 3D and [✓] 4D checkboxes).

A brief demonstration is available in the following video:
https://youtu.be/ZcJQb59YzUA?t=4m37s
Parameters and controls

Use the Low and High sliders and edit boxes to provide threshold values tha will be used to select pixels with intensities between these values.
If the Masked area check box is selected the thresholding is performed only for the masked areas of the image, which is very convenient for local black and white thresholding.
Right mouse click above the threshold sliders opens a popup menu that allows to set precision for the slider movement.
The [✓] Adaptive checkbox starts adaptive threshoding with the Sensitivity and Width parameters modified by the scroll bars.

Usage notes
When doing thesholding for large 3D/4D datasets it is recommended to:

  • start in 2D mode by unchecking [✓] 3D and [✓] 4D checkboxes
  • adjust parameters using the currently shown slice
  • when parameters are chosen, tick [✓] 3D or [✓] 4D checkbox
  • select Low or High editbboxe and hit Enter to apply thresholding values for the whole dataset


 

Drag & Drop material

Shift MIB layers (selection, mask, model) to left/right/up/down direction. The tool allows to move individual 2D/3D objects as well as complete contents of the layers in 2D and 3D.

A combobox offers possibility to choose the layer to be moved. Mouse click or use of the buttons in the panel move the selected layer left/right/up/down by the specified number of pixels.

A brief demonstration is available in the following video:
https://youtu.be/NGudNrxBbi0

Mouse and key controls

Start by Modifier [✓] 3D checkbox Action
Left mouse click over an objectCtrlUncheckedMove the selected object in 2D
Left mouse click over an objectCtrlCheckedMove the selected 3D object. Note! Only for MATLAB version 2017b and newer
Left mouse click⇧ ShiftUncheckedMove all objects on the shown slice, i.e. 2D movement
Left mouse click⇧ ShiftCheckedMove all objects on all slices, i.e. 3D movement
Left/Right/Up/Down buttons-UncheckedMove all objects on the shown slice by the specified number of pixels, i.e. 2D movement
Left/Right/Up/Down buttons-CheckedMove all objects on all slices by the specified number of pixels, i.e. 3D movement


 

The Lasso tool

Selection with a lasso, rectangle, ellipse or polyline tools.
A brief demonstration is available in the following video:
https://youtu.be/OHFdGj9uBro
How to use:

  • Press and release left mouse button above the image to initialize the lasso tool
  • Press and hold left mouse button and drag the mouse to select an area
  • Release the left mouse button to finish the selection process
  • Modify selected area, if needed
  • Accept selection using double left mouse button click

Modes:

  • Add, a new selection is added to the existing one
  • Subtract, a new selection is subtracted from the existing one

The Lasso tool works also in 3D.



 

The Magic Wand + Region Growing tool

Selection of pixels with the _mouse button_ based on their intensities. The intensity variation is calculated from the intensity of the selected pixel and two threshold values from the |Variation| edit boxes.

A brief demonstration is available in the following video:
https://youtu.be/ZcJQb59YzUA?t=1m50s
Widgets and parameters

  • Variation editboxes, specify variation of image intensities relative to the clicked value
  • Connect 8 specifies the 8 (26 for 3D) connected neighbourhood connectivity
  • Connect 4 specifies the 4 (6 for 3D) connected neighbourhood connectivity
  • Radius allows defining an effective range for the magic wand

The Magic Wand works also in the 3D mode (the 3D switch in the Selection panel).


Selection modifiers for the Magic wand tool

  • left mouse click, will replace the existing selection with the new one.
  • ⇧ Shift + left mouse click, will add new selection to the existing one.
  • Ctrl + left mouse click, will remove new selection from the current.


 

The Membrane Click Tracker tool

This tool tracks membrane-type objects by using 2 mouse clicks that define start and end point of the membrane domain.

A brief demonstration for 2D is available in the following video:
https://youtu.be/ZcJQb59YzUA?t=3m14s
A brief demonstration for 3D is available in the following video:
https://youtu.be/ZcJQb59YzUA?t=2m22s
How to use

  • Ctrl + left mouse click to define the starting point of a membrane fragment (before MIB version 2.651 the ⇧ Shift + left mouse click combination was used)</li>
  • Left mouse click to trace the membrane from the starting point to the clicked point</li>

Additional parameters

  • The Scale edit box - during the tracing the image gets enhanced by taking into account intensities of the starting and ending points img(img>min([val1 val2])-diff([val1 val2])*options.scaleFactor) = maxIntensity;
  • The Width edit box - defines a width of the resulting trace
  • The [✓] BlackSignal checkbox defines whether the signal is Black on White, or White on Black
  • The [✓] Straight line checkbox - when checked, the points are connected with a straight line

Note! When the 3D switch in the Selection panel is enabled the Membrane Click Tracker tool connects points (linearly) in the 3D space (this may be very usefull for tracing microtubules). Alternatively for microtunules, consider 3D lines tool


Reference and compilation

The membrane is traced with help of Accurate Fast Marching function http://www.mathworks.se/matlabcentral/fileexchange/24531-accurate-fast-marching by Dirk-Jan Kroon, 2011, University of Twente.

Note! It is highly recommended to compile the corresponding function (see details in the Membrane Click Tracker section of the System Requirements page ), otherwise the function is very slow!



 

Object Picker

This mode allows fast selection of objects from the |Mask| or |Model| layers. When the |Mask| and |Model| radio buttons define the target layer for selection.

A brief demonstration is available in the following video:
https://youtu.be/mzILHpbg89E
Works also in 3D (select the 3D check box in the Selection panel).

Note! The 3D mode requires calculating statistics for the objects. Please select the material in the Select from list box and press the Recalc. Stats button (the button becomes available when the Mask->Mask statistics... or Menu->Models->Model statistics....
Possible Object Picker selection modes

  • 1. Left mouse click, selects object from the Mask/Model layers with a single mouse click.
    Note 1! Separation of objects is sensitive to the connected neighbourhood connectivity parameter from the Magic Wand tool; Note 2! In the 3D mode the function uses object statistics that is generated by pressing the Recalc. Stats button. If the Mask/Model layers have been changed press the Recalc. Stats button again.
  • 2. Lasso: selects object with lasso tool (Press first None/⇧ Shift/Ctrl + Right mouse button, then hold the left mouse button while moving mouse around). Can also make selection for the whole dataset if the [✓] 3D checkbox in the Selection panel is checked.
  • 3. Rectangle or Ellipse: these tools work in similar to the lasso tool manner but give rectangle or ellipsoid selection. Works also in 3D.
  • 4. With the Polyline option the selection is done by drawing a polygon shape point by point. Start drawing with the right mouse button and finish with a double click or the right mouse click. Works also in 3D.
  • 5. Use Brush to select some of the masked/model areas. Size of the Brush tool is defined in the Brush editbox.
  • 6. Mask within selection with the left mouse click on the image make a new selection that is an intersection of the existing selection and the mask/model layer. With Ctrl+ mouse click the new selection is Selection -minus- Mask. This action is sensitive to the [✓] 3D checkbox state in the Selection panel.

Selection modifiers

  • None/⇧ Shift + left mouse click, will add selection with the existing one
  • Ctrl + left mouse click, will remove selection from the current


 

The Spot tool

Adds a spot - a circular object with a mouse click

A brief demonstration is available in the following video:
https://youtu.be/AlCzjKuyJww
Widgets and parameters

Use the Radius, px edit box to specify the radius of the spot.
*Eraser, x*, specifies magnifier for the spot eraser tool

Works also in 3D.

Selection modifiers
  • None/⇧ Shift + left mouse click, will add new spot to the existing ones
  • Ctrl + left mouse click, will remove selection from the current

Back to Index --> User Guide --> Panels --> Segmentation Panel