<font size="2">Dear Amardeep,<br><br>Please take a look at the Insight Journal publication:<br><br><a href="http://www.insight-journal.org/browse/publication/642">http://www.insight-journal.org/browse/publication/642</a><br>
<br>All the parameters that you mentioned below are completely explained in the context of the level-set PDE that was implemented. If you want to know more about the mathematics , the Insight paper further references the following papers:<br>
<br>1. T. Chan and L. Vese. An active contour model without edges. In Scale-Space Theories in Computer Vision, pages 141–151, 1999.<br>2. A. Dufour, V. Shinin, S. Tajbakhsh, N. Guillen-Aghion, J. C. Olivo-Marin, and C. Zimmer. Segmenting and tracking fluorescent cells in dynamic 3-d microscopy with coupled active surfaces. Image Processing, IEEE Transactions on, 14(9):1396–1410, 2005.<br>
<br>Finally, the parameter m_ReinitializationWeight which was added recently is by incorporating the method explained in the paper:<br></font><font face="Times New Roman" size="2"><span style="">3. Chunming Li, Chenyang Xu, Changfeng Gui, and<span style="">
</span>Martin D. Fox, "Level Set Evolution Without Re-initialization: A
New Variational Formulation",</span><i><span style="">
</span>CVPR 2005</i>.</font><br><br>In Insight/Examples/Review, we have placed fully commented example codes for using the filters -- both dense and sparse for the single phase cases.<br><br>Here, I explain the parameters once again:<br>
<br>1. CurvatureWeight - Penalize high curvatures of level set curve or surface. This also means that if your object to be segmented has small features on its boundaries, then they will be missed.<br>
2. AreaWeight - Hastens the movement of level-set to its final convergence. If you initialized in a mostly interior region, then this parameter must be negative to force the level-set to grow quickly and vice-versa.<br>
3. ReinitializationWeight - This is based on reference 3 above. It forces the level-set function to remain a signed distance function as it evolves. You can turn it off (set to 0) in the sparse-field methods since the sparse implementation is not based on a signed distance function. Only needs to be used in dense implementation.<br>
4. VolumeWeight - In tracking applications, this will weight the volume term for the object being tracked.<br><div class="h5">
5. Volume - The volume of the object being tracked in terms of pixels.</div><br><br>Kishore<br><br><br><br>Finally, please keep checking the CVS version of the code regularly for getting the latest updates.<br><br>Kishore<br>
<br><br><br><div class="gmail_quote">On Tue, Jul 28, 2009 at 5:40 AM, Amardeep Singh <span dir="ltr"><<a href="mailto:amar.singh@gmx.de">amar.singh@gmx.de</a>></span> wrote:<br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Hello everyone<br>
<br>
Unfortunately, I have not yet received an answer to my question on how to interpret the different parameters of<br>
the "Active Contours without edges" algorithm. Has anyone already used the filter and can share his understanding of<br>
the meaning of the parameters, please?<div class="im"><br>
Thanks a lot!<br>
<br>
Best regards<br>
Amardeep<br>
<br></div><font color="#888888">
Amardeep Singh wrote:<br>
</font><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><div><div></div><div class="h5">
Dear Kishore<br>
<br>
Thanks a lot for the bugfix. I can get the program to run with the newest fix.<br>
However, I would be interested in the parameters that you used in order to produce the result.<br>
Could you give me a little more insight in the meaning of some of the parameters, as well,please?<br>
Some are quite clear, but I couldn't find a correspondence for the others in the paper:<br>
1. CurvatureWeight: Penalize high curvature of level set?; where is this in the paper?<br>
2. AreaWeight: Penalize high area of level set surface<br>
3. ReinitializationWeight, in the code also called "SetReinitializationSmoothingWeight":<br>
What does this mean? Is it in the paper?<br>
4. VolumeWeight, in the code also called VolumeMatchingWeight:<br>
What does it mean? Is it in the paper?<br>
5. Volume: I guess that this the parameter of the volume parametrization, so it penalizes large volumes<br>
within the level set surface.<br>
<br>
Thank you very much!<br>
<br>
Best regards<br>
Amardeep<br>
<br>
Kishore Mosaliganti wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Hi Amardeep,<br>
<br>
Thanks for the format conversion and also for putting up your data. I was able to reproduce the problem at my end. Your images had a negative origin and revealed a bug in code. This has been corrected now in the latest CVS repository.<br>
<br>
Meanwhile, I have placed an example script and its output:<br>
<a href="http://bmi.osu.edu/%7Ekishore/Amardeep/" target="_blank">http://bmi.osu.edu/~kishore/Amardeep/</a> <<a href="http://bmi.osu.edu/%7Ekishore/Amardeep/" target="_blank">http://bmi.osu.edu/%7Ekishore/Amardeep/</a>><br>
<br>
Please try it out at your end and let me know how things work out.<br>
<br>
Kishore<br>
<br>
On Wed, Jul 22, 2009 at 5:41 AM, Amardeep Singh <<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a> <mailto:<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a>>> wrote:<br>
<br>
Dear Kishore<br>
<br>
I have converted the images to *.mhd, just like Alexander<br>
suggested. Does this solve the issue of<br>
opening the images for you?<br>
Please let me know if you still cannot use them.<br>
Thanks a lot for your help!<br>
<br>
Best regards<br>
Amardeep<br>
<br>
<br>
Oleksandr Dzyubak wrote:<br>
<br>
Hi Kishore,<br>
<br>
You probably have some box with ITK installed.<br>
If you do, you could compile examples from ITK which<br>
comes in separate package "InsightApplications" (if you have<br>
not done so yet).<br>
Once successfully compiled, under directory<br>
~/InsightApplications/ConvertBetweenFileFormats you can find<br>
the executable<br>
ConvertBetweenFileFormats.<br>
<br>
The rest is quite simple. If you want to use Paraview, do as below<br>
<br>
./ConvertBetweenFileFormats image.nii image.mhd<br>
<br>
The second operand could be change to whatever your favorite<br>
format is.<br>
<br>
Alex<br>
<br>
Kishore Mosaliganti wrote:<br>
<br>
Hi Amardeep,<br>
<br>
I am unable to open your images correctly or something is<br>
wrong.. What I saw was that the images was having 0s<br>
throughout.<br>
<br>
Can you write them in some other format that I can open in<br>
Paraview, for example?<br>
<br>
Thanks,<br>
Kishore<br>
<br>
On Tue, Jul 21, 2009 at 2:06 PM, Amardeep Singh<br>
<<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a> <mailto:<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a>><br>
<mailto:<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a> <mailto:<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a>>>> wrote:<br>
<br>
Dear Kishore<br>
Dear ITK Users<br>
<br>
I have now been trying to use the filter, but,<br>
unfortunately, I<br>
cannot get it to run. My initial level set and my<br>
feature image<br>
are overlapping perfectly (same orientation/position<br>
information<br>
in the headers), but when I run the example program<br>
"ScalarSinglePhase3DTest.cc", I get the following error<br>
(it is<br>
indeed printed out twice):<br>
Exception caught !<br>
<br>
itk::ExceptionObject (0x8152b00)<br>
Location: "virtual void<br>
itk::DataObject::PropagateRequestedRegion()"<br>
File:<br>
/asingh/workspace/InsightToolkit-3.14.0/Code/Common/itkDataObject.cxx<br>
Line: 397<br>
Description: Requested region is (at least partially)<br>
outside the<br>
largest possible region.<br>
<br>
<br>
Exception caught !<br>
<br>
itk::ExceptionObject (0x8149d88)<br>
Location: "virtual void<br>
itk::DataObject::PropagateRequestedRegion()"<br>
File:<br>
/asingh/workspace/InsightToolkit-3.14.0/Code/Common/itkDataObject.cxx<br>
Line: 397<br>
Description: Requested region is (at least partially)<br>
outside the<br>
largest possible region.<br>
<br>
My parameters are chosen arbitrarily:<br>
curvature weight: 0.1<br>
area weight: 0.1<br>
laplacian weight: 0.1<br>
volume weight: 0.1 (what does this mean?)<br>
volume: 0 (what does this mean?)<br>
overlap weight: 0<br>
<br>
For your convenience, I have made the images available<br>
under the<br>
following URL:<br>
<a href="http://www.doc.ic.ac.uk/%7Easingh/" target="_blank">http://www.doc.ic.ac.uk/~asingh/</a><br>
<<a href="http://www.doc.ic.ac.uk/%7Easingh/" target="_blank">http://www.doc.ic.ac.uk/%7Easingh/</a>><br>
<<a href="http://www.doc.ic.ac.uk/%7Easingh/" target="_blank">http://www.doc.ic.ac.uk/%7Easingh/</a>><br>
<br>
I have also put my code there.<br>
<br>
Does anyone have an idea, why it fails?<br>
<br>
Any comment is highly appreciated!<br>
<br>
<br>
Best regards<br>
Amardeep<br>
<br>
<br>
Kishore Mosaliganti wrote:<br>
<br>
Hi Amardeep,<br>
<br>
The names of the classes were changed when moving<br>
to the<br>
Review directory. Therefore, you will need to<br>
modify the main<br>
cxx that you downloaded from Insight Journal.<br>
<br>
Thanks,<br>
Kishore<br>
<br>
On Thu, Jul 16, 2009 at 11:17 AM, Amardeep Singh<br>
<<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a> <mailto:<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a>><br>
<mailto:<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a> <mailto:<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a>>><br>
<mailto:<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a><br>
<mailto:<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a>> <mailto:<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a><br>
<mailto:<a href="mailto:amar.singh@gmx.de" target="_blank">amar.singh@gmx.de</a>>>>> wrote:<br>
<br>
Dear ITK Users<br>
<br>
I would like to use the "Active Contours without<br>
edges"<br>
algorithm,<br>
which is available in<br>
the Review directory if I understood correctly.<br>
So, I am wondering where I can find an example<br>
about how to use<br>
the algorithm. I tried to run the<br>
"ScalarSinglePhase3DTest" example of the Insight<br>
Journal<br>
submission, but it failed to compile.<br>
The first error read:<br>
/applications/ScalarSinglePhase3DTest.cc:4:52:<br>
error:<br>
itkSparseMultiphaseLevelSetImageFilter.h: No<br>
such file or<br>
directory<br>
<br>
I am a little confused by the multitudes of<br>
implementations<br>
that<br>
are available with respect to this<br>
algorithm, at the moment (3 Insight Journal<br>
submission +<br>
Review).<br>
Can someone tell me where to start and how to<br>
get it running?<br>
Thanks a lot!<br>
<br>
Best regards<br>
Amardeep<br>
<br>
<br>
<br>
_____________________________________<br>
Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
<<a href="http://www.kitware.com" target="_blank">http://www.kitware.com</a>> <<a href="http://www.kitware.com" target="_blank">http://www.kitware.com</a>><br>
<<a href="http://www.kitware.com" target="_blank">http://www.kitware.com</a>><br>
<br>
<br>
Visit other Kitware open-source projects at<br>
<a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
<br>
Please keep messages on-topic and check the ITK<br>
FAQ at:<br>
<a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
<br>
Follow this link to subscribe/unsubscribe:<br>
<a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
<br>
<br>
<br>
------------------------------------------------------------------------<br>
<br>
_____________________________________<br>
Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a> <<a href="http://www.kitware.com" target="_blank">http://www.kitware.com</a>><br>
<br>
Visit other Kitware open-source projects at<br>
<a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
<br>
Please keep messages on-topic and check the ITK FAQ at:<br>
<a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
<br>
Follow this link to subscribe/unsubscribe:<br>
<a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
<br>
<br>
</blockquote>
_____________________________________<br>
Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
<br></div></div><div class="im">
Visit other Kitware open-source projects at<br>
<a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
<br>
Please keep messages on-topic and check the ITK FAQ at: <a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
<br>
Follow this link to subscribe/unsubscribe:<br>
<a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
<br>
</div></blockquote>
</blockquote></div><br>