<div dir="ltr">Hi, Matt,<div> Thanks for your response.<br><div> Basically, what I am trying to do is to speed up rigid or affine registration. After investigating ITK registration source code, I found that there are not too much to do with optimization procedure, or say, too difficult for me to improve the optimization part. Speeding up the calculation of the similarity metric could be a good choice for me. I took a look at the filter of <span style="color:rgb(0,0,0);font-size:14px">itkMeanSquaresImageToImageM</span><span style="color:rgb(0,0,0);font-size:14px">etric, and found it is already multi-thread coded. Do you think it is worth of rewriting it in CUDA? I don't think I am the first one to come up with this question. Anyone who did this job could mind to comment?</span></div></div></div><div class="gmail_extra"><br clear="all"><div><div class="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div>Cheers,</div><div dir="ltr"><br></div><div dir="ltr">Wu Qiu, Ph.D</div><div>Calgary Stroke program,</div><div>the University of Calgary,</div><div dir="ltr"><div>Email: <a href="mailto:qiu.wu.ch@gmail.com" target="_blank">qiu.wu.ch@gmail.com</a></div></div></div></div></div></div></div></div></div></div></div></div></div>
<br><div class="gmail_quote">2016-01-23 20:30 GMT-07:00 Matt McCormick <span dir="ltr"><<a href="mailto:matt.mccormick@kitware.com" target="_blank">matt.mccormick@kitware.com</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi Wu,<br>
<br>
This contribution would be very welcome! There are examples here [1]<br>
[2] [3] that could be consolidated with your registration code into an<br>
ITK module [4].<br>
<br>
Thanks,<br>
Matt<br>
<br>
[1] <a href="https://github.com/SimonRit/RTK" rel="noreferrer" target="_blank">https://github.com/SimonRit/RTK</a><br>
<br>
[2] <a href="http://www.insight-journal.org/browse/publication/802" rel="noreferrer" target="_blank">http://www.insight-journal.org/browse/publication/802</a><br>
<br>
[3] <a href="http://www.insight-journal.org/browse/publication/803" rel="noreferrer" target="_blank">http://www.insight-journal.org/browse/publication/803</a><br>
<br>
[4] <a href="http://itk.org/ITKSoftwareGuide/html/Book1/ITKSoftwareGuide-Book1ch9.html#x50-1430009" rel="noreferrer" target="_blank">http://itk.org/ITKSoftwareGuide/html/Book1/ITKSoftwareGuide-Book1ch9.html#x50-1430009</a><br>
<div><div class="h5"><br>
On Sat, Jan 23, 2016 at 10:23 PM, wu qiu <<a href="mailto:qiu.wu.ch@gmail.com">qiu.wu.ch@gmail.com</a>> wrote:<br>
> Hi,<br>
> I want to speed up or rewrite the calculation of registration metric used in<br>
> the rigid and affine registration, such as itkMeanSquaresImageToImageMetric,<br>
> using CUDA.<br>
> Anyone who has experiences could give me some clues or some examples I can<br>
> learn? Thanks.<br>
><br>
> Cheers,<br>
><br>
> Wu<br>
><br>
><br>
><br>
</div></div>> _______________________________________________<br>
> Community mailing list<br>
> <a href="mailto:Community@itk.org">Community@itk.org</a><br>
> <a href="http://public.kitware.com/mailman/listinfo/community" rel="noreferrer" target="_blank">http://public.kitware.com/mailman/listinfo/community</a><br>
><br>
</blockquote></div><br></div>