<blockquote style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex" class="gmail_quote">Could you please share that document with me? The link does not work.<br></blockquote><div>Done.<br>
<br><blockquote style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex" class="gmail_quote">I have attached screenshots from the test outputs on my side. The<br>
translation along the "axial" direction is off in the "2" case.<br></blockquote><div>Indeed, exact same problem. <br><br><blockquote style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex" class="gmail_quote">
Excellent. Where is this code currently located? Would you like to<br>
work on this while I address the convergence issues?<br></blockquote><div>I have just started working on it, will start really coding tomorrow and push my code and my own Slicer repository first.<br>The plan sounds perfect to me otherwise.<br>
</div><br>Thank you very much for the quick review.<br>Michael.<br></div> <br></div><div class="gmail_quote">On Wed, Jul 25, 2012 at 5:29 PM, Matt McCormick <span dir="ltr"><<a href="mailto:matt.mccormick@kitware.com" target="_blank">matt.mccormick@kitware.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi Michael,<br>
<br>
Many thanks for the information.<br>
<div class="im"><br>
<br>
><br>
> From what I remember and what I just checked quickly:<br>
><br>
> The "itkImageToTubeRigidRegistration" is the re-factored and cleaned version<br>
> of the initial one given the exact same results while the<br>
> "itkImageToTubeRigidRegistration2" is a modified version of this previous<br>
> class.<br>
> This last one is supposed to be better as described here:<br>
> (<a href="https://docs.google.com/open?id=1psAY1BKx2pEfVPDF4S-xwHOuSP4Mrp7AxQXErgmmQvHthA-LvFauCEdfpQQs" target="_blank">https://docs.google.com/open?id=1psAY1BKx2pEfVPDF4S-xwHOuSP4Mrp7AxQXErgmmQvHthA-LvFauCEdfpQQs</a>).<br>
<br>
</div>Could you please share that document with me? The link does not work.<br>
<div class="im"><br>
> It is the one I would like to be the right one (I may have to go through an<br>
> other clean step however), nevertheless I was waiting for some feedbacks<br>
> first and as you are saying:<br>
><br>
>> Comparing the output of the tests, the registered tube resampled onto<br>
>> an image, the "2" result does not resemble the input image (as far as<br>
>> I can tell).<br>
><br>
> --> See Image enclosed.<br>
><br>
> I just have some trouble to explain this as the performance measurement on<br>
> the second metric seems to be more accurate and following a "more" coherent<br>
> curve and equations compared to the initial one (c.f. previous link &&<br>
> enclosed convergence curves). I was thinking about first making the read of<br>
> the ".tre" file to be able to make some visual comparisons; I am really open<br>
> to any explanations/ideas about why the results are that "bad" given the new<br>
> metric.<br>
<br>
</div>I have attached screenshots from the test outputs on my side. The<br>
translation along the "axial" direction is off in the "2" case.<br>
<br>
If you would like a second set of eyes, I can work on a piecewise<br>
integration of the second class.<br>
<div class="im"><br>
><br>
> Then, concerning the ability to read a ".tre" file into a viewer, It is<br>
> exactly what I am currently working on. I will create a specific module to<br>
> get the reading and representation done as well as the integration with a<br>
> MRML scene.<br>
> Thank you to let me know if the plan suits you and do not hesitate for any<br>
> comments/suggestions.<br>
<br>
</div>Excellent. Where is this code currently located? Would you like to<br>
work on this while I address the convergence issues?<br>
<br>
Thanks,<br>
Matt<br>
<div class="HOEnZb"><div class="h5"><br>
<br>
<br>
><br>
> Regards,<br>
> Michael J-L.<br>
><br>
><br>
><br>
> On Tue, Jul 24, 2012 at 3:28 PM, Danielle Pace <<a href="mailto:danielle.pace@kitware.com">danielle.pace@kitware.com</a>><br>
> wrote:<br>
>><br>
>> Unfortunately, there's no way to read a .tre into Slicer - that's<br>
>> something we've always wanted to do.<br>
>><br>
>> Stephen has a program to visualize .tre's - perhaps he can copy it for<br>
>> you, or perhaps there's a more generic ITK spatial object viewer.<br>
>><br>
>> -Danielle<br>
>><br>
>><br>
>> On Tue, Jul 24, 2012 at 2:11 PM, Matt McCormick<br>
>> <<a href="mailto:matt.mccormick@kitware.com">matt.mccormick@kitware.com</a>> wrote:<br>
>>><br>
>>> On Tue, Jul 24, 2012 at 5:44 PM, Stephen Aylward<br>
>>> <<a href="mailto:stephen.aylward@kitware.com">stephen.aylward@kitware.com</a>> wrote:<br>
>>> > Michael extended his vacation by one day. He should be back in the<br>
>>> > office tomorrow.<br>
>>><br>
>>> OK, great.<br>
>>><br>
>>> ><br>
>>> > Thanks for looking at this. My understanding is that the 2 classes<br>
>>> > are the correct ones; however, I really hate the "2" suffix. If the<br>
>>> > old ones were broken, they should be replaced - instead of using a<br>
>>> > numbering system.<br>
>>> ><br>
>>> > Perhaps beging by looking for the differences in the code and see if<br>
>>> > the "" versions can be replaced by the "2" version (nearly the same<br>
>>> > APIs, etc).<br>
>>><br>
>>> As far as I can tell, the Registration classes are nearly the same<br>
>>> apart from some cleanup. The Metric class underwent refactoring. The<br>
>>> best hint as to what is going on appears to be:<br>
>>><br>
>>> * The improvment implemented here is about<br>
>>> * the precomputation of the internal kernels proposed by Lange et al.:<br>
>>> * \link <a href="http://www.zib.de/lamecker/publications/cars2007.pdf" target="_blank">http://www.zib.de/lamecker/publications/cars2007.pdf</a><br>
>>><br>
>>> Comparing the output of the tests, the registered tube resampled onto<br>
>>> an image, the "2" result does not resemble the input image (as far as<br>
>>> I can tell).<br>
>>><br>
>>> Is there a way to visualize the tube spatial object directly? It is a<br>
>>> MetaIO ".tre" file containing a Scene, Group, and Tube ObjectType. I<br>
>>> assume Slicer should recognize it as a "Model", but it seems to think<br>
>>> it is a "Volume".<br>
>>><br>
>>> Thanks,<br>
>>> Matt<br>
>>><br>
>>><br>
>>> ><br>
>>> > s<br>
>>> ><br>
>>> > On Tue, Jul 24, 2012 at 1:04 PM, Matt McCormick<br>
>>> > <<a href="mailto:matt.mccormick@kitware.com">matt.mccormick@kitware.com</a>> wrote:<br>
>>> >> The test output of the "2" classes does not appear to be correct?<br>
>>> >><br>
>>> >> On Tue, Jul 24, 2012 at 4:18 PM, Matt McCormick<br>
>>> >> <<a href="mailto:matt.mccormick@kitware.com">matt.mccormick@kitware.com</a>> wrote:<br>
>>> >>> Hi Michael,<br>
>>> >>><br>
>>> >>> I am looking at the TubeTK itkImageToTubeRigidRegistration,<br>
>>> >>> itkImageToTubeRigidRegistration2, itkImageToTubeRigidMetric,<br>
>>> >>> itkImageToTubeRigidMetric2, and I am wondering if we replace the<br>
>>> >>> original classes with the "2" version, and concentrate on development<br>
>>> >>> there?<br>
>>> >>><br>
>>> >>> Thanks,<br>
>>> >>> Matt<br>
>>> >> _______________________________________________<br>
>>> >> Tubetk-developers mailing list<br>
>>> >> <a href="mailto:Tubetk-developers@tubetk.org">Tubetk-developers@tubetk.org</a><br>
>>> >> <a href="http://public.kitware.com/cgi-bin/mailman/listinfo/tubetk-developers" target="_blank">http://public.kitware.com/cgi-bin/mailman/listinfo/tubetk-developers</a><br>
>>> ><br>
>>> ><br>
>>> ><br>
>>> > --<br>
>>> ><br>
>>> > ==============================<br>
>>> > Stephen R. Aylward, Ph.D.<br>
>>> > Senior Director of Operations - North Carolina<br>
>>> > Kitware, Inc. - North Carolina Office<br>
>>> > <a href="http://www.kitware.com" target="_blank">http://www.kitware.com</a><br>
>>> > stephen.aylward (Skype)<br>
>>> > <a href="tel:%28919%29%20969-6990%20x300" value="+19199696990">(919) 969-6990 x300</a><br>
>>> _______________________________________________<br>
>>> Tubetk-developers mailing list<br>
>>> <a href="mailto:Tubetk-developers@tubetk.org">Tubetk-developers@tubetk.org</a><br>
>>> <a href="http://public.kitware.com/cgi-bin/mailman/listinfo/tubetk-developers" target="_blank">http://public.kitware.com/cgi-bin/mailman/listinfo/tubetk-developers</a><br>
>><br>
>><br>
>><br>
>><br>
>> --<br>
>> Danielle Pace, M.ESc.<br>
>> Research and Development Engineer<br>
>> Kitware Inc.,<br>
>> North Carolina Office<br>
>><br>
>> <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
>> <a href="tel:919-969-6990%20X%20319" value="+19199696990">919-969-6990 X 319</a><br>
>><br>
><br>
</div></div></blockquote></div><br>