View source for Documentation/4.3/Modules/FastGrowCut

<noinclude>{{documentation/versioncheck}}</noinclude>
<!-- ---------------------------- -->
{{documentation/{{documentation/version}}/module-header}}
<!-- ---------------------------- -->






<!-- ---------------------------- -->
{{documentation/{{documentation/version}}/module-section|Introduction and Acknowledgements}}
{{documentation/{{documentation/version}}/module-introduction-start|{{documentation/modulename}}}}
{{documentation/{{documentation/version}}/module-introduction-row}}

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 [http://www.na-mic.org/ NA-MIC website].<br>

Author: Liangjia Zhu, Stony Brook University<br>
Contributor: Ivan Kolesov, Stony Brook University<br>
Contributor: Yi Gao, University of Alabama Birmingham<br>
Contributor: Peter Karasev, Georgia Institute of Technology<br>
Contributor: Ron Kikinis, BWH <br>
Contributor: Allen Tannenbaum, Stony Brook University<br>
Contact: Liangjia Zhu, <email>liangjia.zhu@stonybrook.edu</email><br>

<!--Contributor2: FIRSTNAME LASTNAME, AFFILIATION<br> -->
<!--Contact: FIRSTNAME LASTNAME, <email>john@doe.org</email><br> -->

{{documentation/{{documentation/version}}/module-introduction-row}}

<!--{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|[[File:GeorgiaTech_Logo.svg]]
|{{collaborator|logo|spl}}|{{collaborator|longname|spl}}   <-Replace this logo with yours
}} -->


{{documentation/{{documentation/version}}/module-introduction-end}}







<!-- ---------------------------- -->
{{documentation/{{documentation/version}}/module-section|Module Description}}

This is a fast implementation of the GrowCut method. It supports multi-label segmentation and user online interactions. Please see the references below for more details.

<!--Here comes a description what the module is good for. Explain briefly how it works and point to the [[documentation/{{documentation/version}}/Modules/{{documentation/modulename}}#References|references]] giving more details on the algorithm.
If you are documenting a CLI, the description should be extracted from the corresponding XML description. This could be done automatically using the following wiki template:<pre>{{documentation/{{documentation/version}}/module-description}}
{{documentation/{{documentation/version}}/module-description}} -->








<!-- ---------------------------- -->
<!-- {{documentation/{{documentation/version}}/module-section|Use Cases}}
N/A -->






<!-- ---------------------------- -->
{{documentation/{{documentation/version}}/module-section|Tutorials}}


Step 1.) Add data volume to segment

[[File:LoadMeningioma.png|500px]]


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

[[File:StartEditorMeningioma.png|500px]]


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

[[File:FastGrowCutEffect.png|50px]]


Step 4.) Press the “Start Fast GrowCut” button ( FastGrowCut is now running in the background until the “Stop FastGrowCut” button is pressed)

[[File:StartBotMeningioma.png|500px]]


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

[[File:TurnOnSlices3DMeningioma.png|500px]]

Step 6.) Initialize the segmentation using fast GrowCut
* (a) go to PaintEffect to draw seed regions (label 1 for foreground and 2 for background), then press 'G' to run fast GrowCut.
[[File:FGCSeed.png|500px]] [[File:FGCSeg1.png|500px]]

* (b) If not satified, press 'S' to toggle between seed image and segmentation result. Edit on the seed image to reduce over/under segmentaions. 
[[File:FGCSeed2.png|500px]]

* (c) Once finished editing on the seed image, press 'G' to run fast GrowCut again. 
[[File:FGCSeg2.png|500px]]

The steps 6 (b) and (c) may be repeated a couple of times until satisfied.

<!-- ---------------------------- -->
{{documentation/{{documentation/version}}/module-section|Multi-Label Segmentation Examples}}
The module supports multi-label segmentations. Two examples are shown below.

* Brain ventricle and tumor segmentation
[[File:FGC_Brain_Seed.png|500px]]

1) Seed image

[[File:FGC_Brain_Seg.png|500px]]

2) Segmentation results

* Heart chamber segmentation
[[File:FGC_Heart_Seed.png|500px]]

1) Seed image

[[File:FGC_Heart_Seg.png|500px]]

2) Segmentation results

<!-- ---------------------------- -->
{{documentation/{{documentation/version}}/module-section|Similar Modules}}

<!-- ---------------------------- -->
{{documentation/{{documentation/version}}/module-section|References}}
* Liangjia Zhu, Ivan Kolesov, Yi Gao, Ron Kikinis, Allen Tannenbaum. An Effective Interactive Medical Image Segmentation Method Using Fast GrowCut, International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Interactive Medical Image Computing Workshop, 2014 (submitted).
<!-- ---------------------------- -->
{{documentation/{{documentation/version}}/module-section|Information for Developers}}
{{documentation/{{documentation/version}}/module-developerinfo}}


<!-- ---------------------------- -->
{{documentation/{{documentation/version}}/module-footer}}
<!-- ---------------------------- -->