Documentation/Nightly/Modules/KSliceInteractiveSegmenter

From Slicer Wiki
Revision as of 19:17, 19 September 2013 by Ikolesov (talk | contribs)
Jump to: navigation, search
Home < Documentation < Nightly < Modules < KSliceInteractiveSegmenter


For the latest Slicer documentation, visit the read-the-docs.





Introduction and Acknowledgements

This work is part of the National Alliance for Medical Image Computing (NA-MIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149. Information on NA-MIC can be obtained from the NA-MIC website.

Author: Ivan Kolesov, Georgia Institute of Technology
Author: Peter Karasev, Georgia Institute of Technology
Author: Patricio Vela, Georgia Institute of Technology
Author: Allen Tannenbaum, University of Alabama Birmingham
Contributor1: Steve Pieper, Isomics, Inc.
Contributor2: Karl Fritscher (BWH & MGH)





Module Description

This is the KSlice interactive segmentation method. It uses a data-driven automatic algorithm to process the majority of the volume. As the automatic segmentation runs and displays the current state, a human user can influence the algorithm’s behavior to more closely align with an expected result. In the end, the user has created an excellent segmentation result with a minimal amount of time and effort. Please see the references below for more details.








Tutorials

Step 1.) Add data volume to segment

LoadMeningioma.png


Step 2.) Go to the “Editor” module, select the volume loaded in Step 1 as the “Master Volume” in the “Create and Select Label Maps” drop-down menu

StartEditorMeningioma.png


Step 3.) Select the “KSlice” effect in the “Edit Selected Label Map” drop-down menu

KSliceEffect.png


Step 4.) Set the “Radius” parameter, the "Number of Iterations" and press the “Start Interactive Segmentor” button ( KSlice is now running in the background until the “Stop Interactive Segmentor” button is pressed)

StartBotMeningioma.png


Step 5.) Turn “On” all three slice views in the 3D Plane

TurnOnSlices3DMeningioma.png


Step 5.) Select the rectangle tool(or any other painting tool).

50px

and initialize KSlice in a 2D slice by drawing inside the structure of interest.

KSliceInitMeningioma.png


Step 6.) Press the “C” key to copy the current initialization in this 2D plane, then press the left/right arrow on the keyboard to move on to an adjacent slice, press the “V” key to paste the label, thereby initializing the current slice. Once this procedure has been repeated several times, we have intialized the surface to a cube in 3D.

KSliceInit3DCube.png


Step 7.) To evolve the 2D contour on a slice, hover the mouse over a 2D view plane, press “Q”.

KSlice2DEvolve.png


Step 9.) Hover mouse over the yellow, then green slices and repeat (as many times as desired) Steps 6-8

SegmentAllSlices.png



As necessary, take steps at any time in the process

Step 10.)(Used in any order) Press the “A” key to change drawing modes (between Draw/Delete label). Thus, if the user's expert knowledge of anatomy does not agree with the current segmentation results, he adds negative input by erasing a label. By deleting in the same area multiple times, the user input is accumulated and this guiding signal forces the changes to become persistent

DeleteLabel.png


Step 11.)(Used in any order) Alternatively, a user can press “A” again to return to drawing. If a contour is not reaching an area that is, in fact, part of the structure of interest, the user can add positive input by painting this area

DrawLabel.png


Step 12.)(Used in any order) Evolve the contour with the changed user input, and new initialization

EvolveAfterUserInput.png




Optional Visualization

Step 13.) (Optional) Turn on “Volume Rendering” of the label image in 3D (notice the parameters set for faster interaction). This will be updated during the evolution

VolumeRederingOn.png



Step 14.) Evolution in 3D is done by pressing the “W” key

Result3DSegmentation.png

Step 15.) Once satisfies with the segmentation, stop KSlice by clicking "Stop Interactive Segmentor"

StopKSlice.png



Panels and their use

There is one parameter to set: the radius that sets the band around the current initialisation in which image data is considered. A large radius means data from far lying regions influences the segmentation (this increases the computational complexity). A small radius ensures that only nearby pixels influence the contour (but set too small will require a better contour initialisation from the user)









References

  • Kolesov, I., Karasev, P., Muller, G., Chudy, K., Xerogeanes, J., and Tannenbaum, A., “Human supervisory control framework for interactive medical image segmentation,” in International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Computational Biomechanics for Medicine Workshop, Proceeding of the, 2011.
  • Karasev, P., Kolesov, I., Chudy, K., Muller, G., Xerogeanes, J., and Tannenbaum, A., “Interactive mri segmentation with controlled active vision,” in IEEE Conference on Decision and Control, Proceedings of the, IEEE, Dec. 2011.
  • Karasev, P., Kolesov, I., Fritscher, K., Vela, P., Mitchell, P., and Tannenbaum, A.. “Interactive Medical Image Segmentation using PDE Control Of Active Contours”. In: Medical Imaging, IEEE Transactions on (In Submission) (2013)
  • Xerogeanes, J., Mitchell, P. , Karasev, P., Kolesov, I. and Romine, S. . “An Anatomic and Morphologic Evaluation of the Quadriceps Tendon Using 3D MRI Reconstruction: Applications for ACL Autograft Choice and Procurement”. In: Journal of Bone and Joint Surgery (In Submission) (2013)


Information for Developers