<div dir="ltr">Hi Hana,<div><br></div><div>Deformable registration is always an ill-posed problem,</div><div>given that there are always a multiplicity of solutions.</div><div><br></div><div>The regularity terms help drive the optimizers towards a</div>
<div>subset of solutions that produce smooth displacement</div><div>fields. They are, however, not specific enough as to</div><div>produce a "correct" answer.</div><div><br></div><div>The goal with a deformable registration process, is to find</div>
<div>a displacement field that is "good enough" for a particular</div><div>application.</div><div><br></div><div>There is no real "right" nor "correct" answer to be found.</div><div><br></div>
<div><br></div><div> Best,</div><div><br></div><div><br></div><div> Luis</div><div><br></div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Sun, Feb 9, 2014 at 9:42 AM, Hana Cherif <span dir="ltr"><<a href="mailto:hanacherif62@gmail.com" target="_blank">hanacherif62@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div><div>Hello again ,, <br><br></div>I mean all the things that you have mentioned, but how about the numerical validation of this property!! I know that the regularity term imposes to the deformation field to be smooth, and it making the problem well posed no??? If what i say is true,, haw did this points verified in that model in ITK because i saw that only the similarity term was implemented !! <br>
<br></div>Hope that it is clear!! <br><br></div>Best regards !!<br><div><div><br><br></div></div></div><div class="gmail_extra"><br><br><div class="gmail_quote">2014-02-08 23:25 GMT+01:00 Luis Ibanez <span dir="ltr"><<a href="mailto:luis.ibanez@kitware.com" target="_blank">luis.ibanez@kitware.com</a>></span>:<div>
<div class="h5"><br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Hi Hana,<div><br></div><div>When you ask about the "verification of the regularity of the solution",</div>
<div><br></div><div>are you thinking about inspection of the deformation field ?</div><div>
maybe about visualization of the deformation field ?</div><div><br></div><div>or are you thinking about a more formal numerical validation ?</div><div><br></div><div> Thanks</div><div><br></div><div> Luis</div><div>
<br></div></div><div class="gmail_extra"><br><br><div class="gmail_quote"><div><div>On Sat, Feb 8, 2014 at 3:47 PM, Hana Cherif <span dir="ltr"><<a href="mailto:hanacherif62@gmail.com" target="_blank">hanacherif62@gmail.com</a>></span> wrote:<br>
</div></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div><div><div dir="ltr"><div><div><div>Hello all ,, <br><br></div><div>Another question please about the smoothness term (regularity term )<br>
</div><div><br></div>We
know all that the image registration's
methods implemented in ITK based on a variational approach ,, which
serves to minimize an energy includes two terms : similarity term which
measure similarities of the two images, and a regularity term which
ensure the regularity of that transformation. For me this two terms are essential, mainly in the processes of deformable registration !! My
question is how did the regularity of the solution is verified in the
model proposed in ITK ,, i mean the BSpline registration
(DeformableRegistration4) <br>
<br></div>Thanks in advance!!<span><font color="#888888"><br><br></font></span></div><span><font color="#888888">Hana <br><br></font></span></div>
<br></div></div>_______________________________________________<br>
Community mailing list<br>
<a href="mailto:Community@itk.org" target="_blank">Community@itk.org</a><br>
<a href="http://public.kitware.com/cgi-bin/mailman/listinfo/community" target="_blank">http://public.kitware.com/cgi-bin/mailman/listinfo/community</a><br>
<br></blockquote></div><br></div>
</blockquote></div></div></div><br></div>
</blockquote></div><br></div>