Available Features

This action allows user to manually modify the orientation and translation of the arbitrary slice.

Parameters

Compute the average voxels value in the neiborhoods of the selected voxel. Show results on the log console.

Parameters

Change the surface, wireframe or points colors of objects

Change the rendering option (surface, wireframe, points, label...) of the selected mesh(es).

Parameters

Rigid transformation of Components

Pick a mesh to retrieve point/cell information from the mesh

Center current mesh component in the world coordinates. When applied this action moves the barycenter of the mesh at world coordinate (0,0,0). Does not consider any frame transformation.

Parameters

Display basic mesh quality information (for more information: Knupp et al, The verdict geometric quality library).

This action generates a new volume image and converts the mesh into a volume representation (vtkImageData) where the foreground voxels are colored and the background voxels are black.

Parameters

Compute normals of surface mesh.

Extract the current selection

Tutorial action that retrieve pixel information from the image

Build a regular grid

Parameters

Build a sphere

Parameters

This action re-orients a medical image according to Dicom RCS (Reference Coordinates System).

Parameters

Add a dynamic property to the currently selected component.

Parameters

Add lots of dynamic property to the currently selected component.

Parameters

Demonstrates how to add an enum parameters in an action. Show the information on the log console.

Parameters

This action crops a part of an image volume. Use the GUI to select the volume to crop. You can choose either the min and the max coordinates of each axis (i,j,k), i.e., 6 points or use only two extreme 3D points (the origin of parallelepiped and its opposite diagonal point).

This action offers an interactive GUI to manages CamiTK extension files. If you don't have any CamiTK extension file yet, use the "New Extension File" action.

Parameters

Create a new CamiTK extension files from scratch. If you already have a CamiTK extension file, use the "Open Extension File" action.

Load all the CamiTK extensions that are currently registered by the user. This list contains the currently valid extensions that were registered (imported) in the application settings.

Unload all the CamiTK extensions that are currently registered by the user. This will remove them from memory, but not unregister them (they will be load again during the next launch). This requires a restart.

Choose a CamiTK Extension File to register, i.e., import in the application settings so that it will always be available when you launch the application.
Note that if you move the CamiTK Extension File, you'll have to register it again.

Parameters

Open the given extension in Visual Studio Code or Codium

Parameters

Unregister the given extension from the application settings so that it will not be available automatically anymore when you launch the CamiTK application.
This is is the opposite to registering the extension.

Parameters

Rebuild and reload the given extension. This requires a restart.

Parameters

Set the always verify or rebuild option. If this option is on: - Python virtual environment is systematically verified and missing package are installed to satisfy requirements - C++ extensions are systematically rebuild when loaded. This might increase the startup time but ensure the - Python virtual environment is valid - C++ last available source code version is used

Select the last top level component that was instantiated

Remove the last top level component that was instantiated without saving it

Clear the list of selected item

Set the working directory path to the test data dir (useful for test purpose)

Open data (component) from a file

Open data (component) from a given file

Parameters

Open a CamiTK workspace from a given file

Parameters

Save all the top-level of the selected components

Save the currently selected data under a different filename or format

Saves all the currently loaded data

Save the workspace

Close the currently selected components

Close all components, prompting for additional information if needed

Exit the application, prompting for additional information if needed

Sets the anatomical orientation information for a given Frame. This allows CamiTK to display the correct letters (R/L, I/S, A/P) or even custom ones for each axis, and to correctly orient the camera in the Axial/Sagittal/Coronal orientations

Parameters

Edit the selected Transformation. This action allows one to set directly the matrix values, to apply a rotation or a translation to the current value.

Show/Hide the 3D axes representation of the frame of reference of the selected component, i.e., its local coordinate system.

Parameters

Add a new Transformation between two frames

Parameters

Remove a Transformation if possible (e.g. not owned by any object outside TransformationManager)

Reset the Transformation of a Component: the Frame of the input Component is set to a new independent Frame. You can then add a Transformation between the new Frame and another one to define how it is related to other Components

Sets the Frame/Frames of the input Component from the Frame/Frames of another Component

Parameters

Demonstrate how to call one or more actions from another action (that is, implement a hard-coded action pipeline without modifying anything of the called actions).

Parameters

Toggle the redirection console window that shows log and std output.

Show a little dialog about the application

Change Language with a given .qm file

Parameters

Play along with logger parameters: level and other specifications.
Note: This action does only modify the log interaction temporarily. Please use the application preference dialog or the console tool buttons to save the logger parameter in settings.

The Canny edge detector is an edge detection operator that uses a multi-stage algorithm to detect a wide range of edges in images.
The filter steps are : * Preprocessing noise reduction using a gaussian convolution filtering. * Finding the intensity gradient of the image * Non-maximum suppression * Tracing edges through the image and hysteresis thresholding It was developed by John F. Canny in 1986. (source: Wikipedia).
This filter is widely used for edge detection since it is the optimal solution satisfying the constraints of good sensitivity, localization and noise robustness. (source: ITK Developer's Guide).

Parameters

A 2D or 3D edge detection using the Sobel operator.
This filter uses the Sobel operator to calculate the image gradient and then finds the magnitude of this gradient vector. The Sobel gradient magnitude (square-root sum of squares) is an indication of edge strength..

Parameters

The magnitude of the image gradient is extensively used in image analysis, mainly to help in the determination of object contours and the separation of homogeneous regions.
The Gradient Magnitude filter computes the magnitude of the image gradient at each pixel location using a simple finite differences approach. (source: ITK Developer's Guide)

Differentiation is an ill-defined operation over digital data.
In practice it is convenient to define a scale in which the differentiation should be performed. This is usually done by preprocessing the data with a smoothing filter.

It has been shown that a Gaussian kernel is the most choice for performing such smoothing. By choosing a particular value for the standard deviation (sigma) of the Gaussian, an associated scale is selected that ignores high frequency content, commonly considered image noise.

This filter computes the magnitude of the image gradient at each pixel location.

The computational process is equivalent to first smoothing the image by convolving it with a Gaussian kernel and then applying a differential operator.

The user selects the value of sigma. Internally this is done by applying an IIR filter that approximates a convolution with the derivative of the Gaussian kernel. Traditional convolution will produce a more accurate result, but the IIR approach is much faster, especially using large sigmas (Deriche1990,Deriche1993).

(source: ITK Developer's Guide)

Parameters

This filter is used for computing the partial derivative of an image.


Choose the order of the derivative:

• Zero order: no derivation
• First order derivative
• Second order derivative

• Derivative along X axis
• Derivative along Y axis
• Derivative along Z axis

Parameters

This filter computes the Laplacian of a scalar-valued image.

The Laplacian is an isotropic measure of the second spatial derivative of an image.

The Laplacian of an image highlights regions of rapid intensity change and is therefore often used for edge detection. Often, the Laplacian is applied to an image that has first been smoothed with a Gaussian filter in order to reduce its sensitivity to noise.

(source: ITK Developer's Guide)

Parameters

Computes the Laplacian of Gaussian (LoG) of an image by convolution with the second derivative of a Gaussian.

This filter is implemented using the recursive gaussian filters.

Parameters

This filter sharpens an image using a Laplacian filter .
Laplacian Sharpening highlights regions of rapid intensity change and therefore highlights or enhances the edges. The result is an image that appears more in focus.

The mean filter is commonly used for noise reduction.

This filter computes the value of each output pixel by finding the statistical mean of the neighborhood of the corresponding input pixel. The following figure illustrates the local effect of the mean filter in 2D case.
______________
| 28 | 26 | 50 |
|-----|-----|------|
| 27 | 25 | 29 | -> 30.22 -> 30
|-----|-----|------|
| 25 | 30 | 32 |
--------------------
Note that this algorithm is sensitive to the presence of outliers in the neighborhood.

The parameters are the size of the neighborhood along X, Y and Z directions.
The value on each direction is used as the semi-size of a rectangular box. For example in 2D a size of 1 in X direction and 2 in Y direction results in a 3x5 neighborhood.

Parameters

The median filter is commonly used as a reobust approach for noise reduction.
This filter is particularly efficient against salt-and-pepper noise. In other words, it is robust to the presence of gray-level outliers.
This filter computes the value of each output pixel as the statistical median of the neighborhood of values around the corresponding input pixel. The following figure illustrates the local effect of this filter in 2D case.
_____________
| 28 | 26 | 50 |
|----|-----|----|
| 27 | 25 | 29 | -> 28
|----|-----|----|
| 25 | 30 | 32 |
-----------------

The parameters are the size of the neighborhood along X, Y and Z directions. The value on each direction is used as the semi-size of a rectangular box. For example in 2D a size of 1 in X direction and 2 in Y direction results in a 3x5 neighborhood.

Parameters

Mathematical morphology has proved to be a powerful resource for image processing and analysis.

This filter implements classical mathematical morphology operators:

• erosion
• dilation
• opening
• closure

Parameters

Blurring is the traditional apporach for removing noise from images. It is usually implemented in the form of a convolution with a kernel. One of the most commonly used kernels is the Gaussian.

The classical methode of smoothing an image by convolution with a Gaussian kernel has the drawback that it is slow when the standard deviation sigma of the Gaussian is large.

The Recursive IIR (Infinite Impulse Rewponse) implements an approximation of convolution with the Gaussian. In practice, this filter requires a constant number of operations for approximating the convolution, regardless of the sigma value.

Parameters

Anisotropic diffusion methods are formulated to reduce noise (or unwanted detail) in images while preserving specific image features. For many applications, there is an assumption that light-dark transitions (edges) are interesting. Standard isotropic diffusion methods move and blur light-dark boundaries. Anisotropic diffusion methods are formulated to specifically preserve edges.

The numberOfIterations parameter specifies the number of iterations (time-step updates) that the solver will perform to produce a solution image. The appropriate number of iterations is dependent on the application and the image being processed. As a general rule, the more iterations performed, the more diffused the image will become.

The conductance parameter controls the sensitivity of the conductance term in the basic anisotropic diffusion equation. It affect the conductance term in different ways depending on the particular variation on the basic equation. As a general rule, the lower the value, the more strongly the diffusion equation preserves image features (such as high gradients or curvature). A high value for conductance will cause the filter to diffuse image features more readily. Typical values range from 0.5 to 2.0 for data like the Visible Human color data, but the correct value for your application is wholly dependent on the results you want from a specific data set and the number or iterations you perform.

The Gradient anisotropic diffusion implements an N-dimensional version of the classic Perona-Malik anisotropic diffusion equation for scal-valued images.

The Curvature anisotropic diffusion performs anisotropic diffusion on an image using a modified curvature diffusion equation (MCDE). MCDE does not exhibit the edge enhancing properties of classic anisotropic diffusion, which can under certain conditions undergo a negative diffusion, which enhances the contrast of edges. Equations of the form MCDE always undergo positive diffusion, with the conductance term only varying the stregth of that diffusion.

Parameters

Labels connected components of a binary image and order the labes with respect to the size of the connected components (i.e., the larges connected component has the label 1, the one a little smaller has the label 2, and so on...)

Parameters

initialize the acquisition device

start the 2D acquisition done with the device (i.e : running a acquisition in live mode...)

stop the 2D continuous acquisition performed by the device

start the 3D continuous acquisition performed by the device

stop the 3D continuous acquisition performed by the device

acquire one 2D ImageComponent by the device

acquire one 3D ImageComponent by the device

This filter creates a binary thresholded image that separates an image into foreground and background components.
The filter calculates the optimum threshold separating those two classes so that their combined spread (intra-class variance) is minimal (see http://en.wikipedia.org/wiki/Otsu%27s_method). Then the filter applies that threshold to the input image using an Itk binary fileter. The numberOfHistogram bins can be set for the Otsu Calculator. The insideValue and outsideValue can be set for the Itk binary filter. The filter produces a labeled volume.

The original reference is:
. Otsu, ''A threshold selection method from gray level histograms,'' IEEE Trans.Syst.ManCybern.SMC-9,62-66 1979.

Parameters

Creates a new binary image depending on the initial voxel value:

• If the initial value is between low and high thresholds (included), the new voxel value will be set to 255 (usually displayed as white)
• Otherwise the new voxel value is set to 0 (usually displayed as black)

If you want to select all the voxels that have a specific value x, set both thresholds to the value x.

Parameters

This filter segments volume images using region growing approach. It starts from a seed point that is considered to be inside the object to be segmented. The pixels neighboring this seed point are evaluated to determine if they should also be considered part of the object. If so, they are added to the region and the process continues as long as new pixels are added to the region. For connected threshold filter, the criterion is based on the intensity of the neighboring pixels. They are considered as part of the object if theyr value is between a lower and an upper threshold.

Generates a model from a mesh: mml, pml and corresponding lml are generated.

The current points selected by picking (Picked Selection) will be considered as fixed nodes.

Parameters

Show MML Simulation Dialog

Show the Axial Viewer Only

Show the Coronal Viewer Only

Show the Sagittal Viewer Only

Show the 3D Viewer Only

Show Classical Medical Image Viewer (Axial, Coronal, Sagittal and 3D in a 4 panels)

Show the Arbitrary Slice Viewer Only

This action demonstrates how to show the point data on a color scale

Parameters

This action reduce the number of triangles in a triangle mesh, forming a good approximation to the original geometry.

The algorithm proceeds as follows. Each vertex in the mesh is classified and inserted into a priority queue. The priority is based on the error to delete the vertex and retriangulate the hole. Vertices that cannot be deleted or triangulated (at this point in the algorithm) are skipped. Then, each vertex in the priority queue is processed (i.e., deleted followed by hole triangulation using edge collapse). This continues until the priority queue is empty. Next, all remaining vertices are processed, and the mesh is split into separate pieces along sharp edges or at non-manifold attachment points and reinserted into the priority queue. Again, the priority queue is processed until empty. If the desired reduction is still not achieved, the remaining vertices are split as necessary (in a recursive fashion) so that it is possible to eliminate every triangle as necessary.

To use this object, at a minimum you need to specify the parameter Decimation percentage. The algorithm is guaranteed to generate a reduced mesh at this level as long as the following four conditions are met:

• topology modification is allowed (i.e., the parameter Preserve topology is false);
• mesh splitting is enabled (i.e., the parameter Splitting is true);
• the algorithm is allowed to modify the boundaries of the mesh (i.e., the parameter Boundary vertex deletion? is true);
• the maximum allowable error (i.e., the parameter Maximum error) is set to 1.0e+38f (default value).

Parameters

Merge duplicate points, and/or remove unused points and/or remove degenerate cells.

Parameters

Fill a surfacic mesh with regularly spaced nodes by creating new nodes inside the mesh.

Parameters

Move the outside points along the normal in order to thicken a volumic mesh (works only with closed- centered- mesh).

Parameters

Extract Surface from Volumetric Mesh

Iterative Closest Point algorithm between two mesh.
At least two mesh components must be selected :

• The first one is the source mesh (the one to be registered)
• The second one is the target mesh

Parameters

Invert the mesh faces

This filter adjusts point positions using Laplacian smoothing.
It makes the cells better shaped and the vertices more evenly distributed.
The effect is to "relax" the mesh, making the cells better shaped and the vertices more evenly distributed. Note that this filter operates on the lines, polygons, and triangle strips composing an instance of vtkPolyData. Vertex or poly-vertex cells are never modified.

The algorithm proceeds as follows. For each vertex v, a topological and geometric analysis is performed to determine which vertices are connected to v, and which cells are connected to v. Then, a connectivity array is constructed for each vertex. (The connectivity array is a list of lists of vertices that directly attach to each vertex.) Next, an iteration phase begins over all vertices. For each vertex v, the coordinates of v are modified according to an average of the connected vertices. (A relaxation factor is available to control the amount of displacement of v). The process repeats for each vertex. This pass over the list of vertices is a single iteration. Many iterations (generally around 20 or so) are repeated until the desired result is obtained.

There are some special parameters used to control the execution of this filter. (These parameters basically control what vertices can be smoothed, and the creation of the connectivity array.) The Boundary smoothing paramerter enables/disables the smoothing operation on vertices that are on the "boundary" of the mesh. A boundary vertex is one that is surrounded by a semi-cycle of polygons (or used by a single line).

Another important parameter is Feature edge smoothing. If this ivar is enabled, then interior vertices are classified as either "simple", "interior edge", or "fixed", and smoothed differently. (Interior vertices are manifold vertices surrounded by a cycle of polygons; or used by two line cells.) The classification is based on the number of feature edges attached to v. A feature edge occurs when the angle between the two surface normals of a polygon sharing an edge is greater than the FeatureAngle ivar. Then, vertices used by no feature edges are classified "simple", vertices used by exactly two feature edges are classified "interior edge", and all others are "fixed" vertices.

Once the classification is known, the vertices are smoothed differently. Corner (i.e., fixed) vertices are not smoothed at all. Simple vertices are smoothed as before (i.e., average of connected vertex coordinates). Interior edge vertices are smoothed only along their two connected edges, and only if the angle between the edges is less than the EdgeAngle ivar.

The total smoothing can be controlled by the The Number of iterations which is a cap on the maximum number of smoothing passes.

Note that this action does not create a new component, but modify the selected one(s).

Parameters

Extract edges from a mesh

Create a new mesh from two input meshes (merge).

• If points are exactly at the same coordinates, they will be merged.
• If cells (tetras, triangles) are overlapped, only one is kept (Points must be exactly at the same coordinates).
• If a triangle is enclosed in a volume during the merging action, it will be removed.

The resulting mesh frame will be:

• the same as both input meshes if they both have the same frame,
• a new frame with a default identity transformation to world if both frames have an independent frame and a default identity transformation to world,
• the same as the first mesh otherwise.

Interactive Mesh Clipping in the 3D Viewer

Computes curvatures of a surface.

Parameters

Load a transformation from a file. The file should contains the 4x4 matrix values (4 lines of 4 values). See also the "Save Displacement From Transformation" action.

Export As MDL (an old legacy file format from early CAMI devices). This is kept for historical reason only.

Load Texture From BMP

Save the displacement from the last translation in a text file. Alternatively, load a transformation from a text file and apply it on the selected Mesh component.

Append several meshes in one mesh.

Parameters

Project the mesh contours onto an image in the 2D slice viewer

Parameters

This action demonstrates how to compute the barycenter of the currently selected mesh nodes

Parameters

The shaker motor. It shakes your mesh in all directions (once)!

Parameters

The shaker motor. It shakes your mesh in all directions!

Parameters

The shaker motor. It uses the shakerlib external library to move the mesh in all directions!

Parameters

Modify the LUT of an image components

Action to manage several pixel points in an image (coordinates and index).

Build meshes from each label in the target image using the marching cubes or flying edges method. The minimum voxel value is considered as the background value and no mesh is created for it. Warning: by default the created meshes are set as unmodified (you won't be warned when they are being closed without saving them).

Parameters

This action aims at exploring inner PML information (atoms, cells and components). Features a specific Qt explorer.

Generates a Structural Component from a given bounding box or current PML explorer selection

Parameters

Sets clicked XxYxZ cube of voxels (by CTRL + Mouse Left) to a new defined color value.

• A size of 1 (X, Y or Z) corresponds to one pixel in the considered slice.
• A size of 2 corresponds to 3 pixels in the slice, in the aim to always keep the picked pixel as the center.
  (Size 3-> 5pix; 4->7pix...)

Parameters

Marching cubes is a simple algorithm for creating a triangle mesh from an implicit function (one of the form f(x, y, z) = 0).
It works by iterating ("marching") over a uniform grid of cubes superimposed over a region of the function. If all 8 vertices of the cube are positive, or all 8 vertices are negative, the cube is entirely above or entirely below the surface and no triangles are emitted. Otherwise, the cube straddles the function and some triangles and vertices are generated. Since each vertex can either be positive or negative, there are technically 28 possible configurations, but many of these are equivalent to one another.

This action uses this algorithm to build a 3D surfacic mesh of the input image.

Parameters

Registration using Elastix

Note that elastix should be installed on your machine.

This action can only modifies the following three main parameters:

• Initialization: whether or not the initial translation between images should be estimated as the distance between their centers.
• Transformation model: determines what type of deformations between the fixed and moving image is handled. There are 6 models available in elastix. Only three different types are available in this action: translation only, affine transformation (includes translation, rotation, scaling and shearing, and the nonrigid (i.e., elastic) B-spline transformation (uses cubic multidimensional B-spline polynomial control points). See section "2.6 Transform" of the elastix manual.
• Similarity metrics: the similarity measure uses to compare the voxel values and find the best match during the registration. There are 5 different similarity measures available in elastix, the main one being: Mean Squared Difference (MSD) and Mutual Information (MI). See section "2.3 Metrics" of the elastix manual.

Parameters

Resamples the input image in two different ways:

• 1. Resamples the scalar type of the voxels unless new scalard type is SAME_AS_INPUT
• 2. Resamples the size of the voxels

Parameters

Restart the application after confirmation

Shows the Image Volume in 3D viewer

Toggle display of the axial slice in 3D

Toggle display of the coronal slice(s) in 3D

Toggle display of the sagittal slice(s) in 3D

Toggle display of the arbitrary slice(s) in 3D

This action generates a linear exploration of slice sagittal, coronal and axial viewers

Parameters

This action generates a random exploration of slice sagittal, coronal and axial viewers.

Parameters

Simple threshold filter based on vtkImageThreshold.
Creates a new binary image depending on the initial voxel value:

• If the initial value is between low and high thresholds (included), the new voxel value will be set to 'In Value' (e.g., 255 that is usually displayed as white)
• Otherwise the new voxel value is set to 'Out Value' (e.g., 0 that is usually displayed as black)

If you want to select all the voxels that have a specific value x, set both thresholds to the value x. You can replace the in values, the out values or both with the given values (note: replacing both, the default, will result in a binary image).

Parameters

Segment CT or MRI using TotalSegmentator.

If you use this tool please cite it as follows:
Wasserthal, J., Breit, H.-C., Meyer, M.T., Pradella, M., Hinck, D., Sauter, A.W., Heye, T., Boll, D., Cyriac, J., Yang, S., Bach, M., Segeroth, M., 2023. TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images. Radiology: Artificial Intelligence. DOI

TotalSegmentator is heavily based on nnUnet.

Parameters

Volume rendering of 3D medical image using ray casting
(Use Ctrl+R to render a selected image volume)

Parameters

Add a VTK 3D Widget to the 3D viewer.
Mouse interaction

• Left button: grab on the six face handles → slide the faces
• Left button: grab the center handle → move the entire box
• Shift+Left button: inside the box widget → Translation
• Right button: inside the box widget → up/down scaling
• Left mouse: pick a face (not a face handle) → rotate (if Rotation Enabled is ticked)

Parameters

Add a VTK Contour widget in a 2D viewer to interactively define a region contour. The contour follows the selected slice.

First select the 2D viewer and then click Apply to start the contour creation:

• Click Apply and then left click in the chosen viewer to add the first contour node
• Left Click: Add/select a point
• Right Click: Add final point
• Middle Click: Translate the contour
• Close Contour Widget: Join the start and end handles interactively
• Delete Contour Widget button: Delete the current contour widget. This will allow you to start again from scratch in any viewer you like. It will detach the generated mesh component and leave it in its current state without deleting it. Note: it is not possible to re-attach it later.
• Duplicate Contour WidgetSame as Delete Contour Widget but will create a new contour and mesh component from the current contour widget shape. This can be useful to use the current contour as the initialization for the next slice. Once the contour is duplicate, change the slice to move it to the next image slice

You may change the color and size an any time, click Apply to update the contour. You cannot change the viewer until you click on Delete Contour Widget (or close the generated Mesh Component).

Parameters