<br><br><div class="gmail_quote">---------- Forwarded message ----------<br>From: <b class="gmail_sendername">Josu Maiora</b> <span dir="ltr"><<a href="mailto:jmaiora@gmail.com">jmaiora@gmail.com</a>></span><br>Date: 2009/1/19<br>
Subject: Fwd: [Insight-users] File format for ICP<br>To: <a href="mailto:insight-users@itk.org">insight-users@itk.org</a><br><br><br><div><div></div><div class="Wj3C7c"><div class="gmail_quote">Hi,<div><br></div><div>I got the input files with <a href="http://public.kitware.com/Insight/Doxygen/html/classitk_1_1BinaryMask3DMeshSource.html" target="_blank">BinaryMask3DMeshSource</a> filter but the registration with ICP example fails -after 12 hours it was still running- . The files have 2000 nodes each. Is it a two large mesh? How could I tune the ICP algorithm?</div>
<div><br></div><div><br></div><div><br></div><div>Thanks,</div><div><br></div><div>Josu</div><div><br></div><div><br></div><div><br><div class="gmail_quote">
2009/1/2 Luis Ibanez <span dir="ltr"><<a href="mailto:luis.ibanez@kitware.com" target="_blank">luis.ibanez@kitware.com</a>></span><div><div></div><div><br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Hi Josu,<br><br>If you already have segmented the spinal canal,<br>then you could use the filter<br><br><a href="http://public.kitware.com/Insight/Doxygen/html/classitk_1_1BinaryMask3DMeshSource.html" target="_blank">http://public.kitware.com/Insight/Doxygen/html/classitk_1_1BinaryMask3DMeshSource.html</a><br>
<br>to extract the surface around each one of the segmented structures,<br>and then you could use the output of each filter as inputs to the<br>ICP examples in<br><br> Insight/Examples/Patented/<br><br>PS. Please note that the ICP patent has already expired.<br>
<br>Since the spinal canal is a long structure, I would expect it to <br>register easily using ICP.... as long as your segmentation have<br>not missed big portions of each.<br><br><br>Note also that, given the curvature of the spine, you may have<br>
to use Transforms that allow for deformations, (e.g. beyond<br>the Rigid and Affinee 3D) transform.<br><br><br> Regards,<br><br><br> Luis<br><br><br>------------------------------------------------------------------<div>
<div></div><div><br>
<div class="gmail_quote">On Fri, Jan 2, 2009 at 10:18 AM, Josu Maiora <span dir="ltr"><<a href="mailto:jmaiora@gmail.com" target="_blank">jmaiora@gmail.com</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 Luis,<div><br></div><div>I am trying to register segmented spinal canals. Could you give me an aproach to do that? </div><div><br></div><div>Thanks,</div><div>Josu<br><br><div class="gmail_quote">2008/12/31 Luis Ibanez <span dir="ltr"><<a href="mailto:luis.ibanez@kitware.com" target="_blank">luis.ibanez@kitware.com</a>></span><div>
<div></div><div><br>
<blockquote class="gmail_quote" style="border-left:1px solid rgb(204, 204, 204);margin:0pt 0pt 0pt 0.8ex;padding-left:1ex"><br>Hi Josu,<br><br>ICP requires two sets of points as input.<br><br>You seem to have two images.<br>
<br>Therefore, in order to use ICP you must first extract from each of your images<br>
a set of points representing the structure(s) that you want to register.<br>
<br>What anatomical structures are you trying to register ?<br><br> Please let us know,<br><br><br> Thanks<br><br><br> Luis<br><br><br>---------------------------------------------------------------------<br>
<div class="gmail_quote"><div><div></div><div>On Wed, Dec 31, 2008 at 6:01 AM, Josu Maiora <span dir="ltr"><<a href="mailto:jmaiora@gmail.com" target="_blank">jmaiora@gmail.com</a>></span> wrote:<br>
</div></div><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>
Hi all,<div><br></div><div>I am trying to use the ICP registration with two 3D segmented images. I have them in mhd or vtk format (I got them with SNAP) and I need to get a point set in a txt file to use that registration. Is it right?</div>
<div><br></div><div>And then, how could I get a point set with a reasonable number of points?</div><div><br></div><div>Thanks,</div><div><br></div><div>Josu</div><div><br></div><div>**************************************************************************</div>
<div>Josu Maiora</div><font color="#888888"><div>University of the Basque Country</div><div>**************************************************************************<br></div>
</font><br></div></div>_______________________________________________<br>
Insight-users mailing list<br>
<a href="mailto:Insight-users@itk.org" target="_blank">Insight-users@itk.org</a><br>
<a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
<br></blockquote></div><br>
</blockquote></div></div></div><br></div>
</blockquote></div><br>
</div></div></blockquote></div></div></div><br></div>
</div><br>
</div></div></div><br>