<div dir="ltr">Massi,<div><br></div><div>It is not trivial to evaluate the quality of a registration process.</div><div><br></div><div>In practice, </div><div>you want to pick a criterion that is meaningful for your application.</div>
<div><br></div><div><br></div><div>For example, </div><div><br></div><div>Extracting surfaces and doing ICP, would be useful if the surfaces</div><div>of the anatomical structure are important for your application.</div><div>
<br></div><div>In some applications we care more about the internal structures than </div><div>about the surfaces.</div><div><br></div><div>In some applications you may be more interested in the quality</div><div>of the registration on the brain of the subject than or the neck,</div>
<div>(or the other way around, if you were planning a neck surgery...).</div><div><br></div><div>The overall recipe is to pick what could have been a good metric</div><div>for another registration process, and use this to evaluate the final</div>
<div>result of your initial registration.</div><div><br></div><div>Note that ITK has a set of classes for estimating distances between</div><div>surfaces, that have been used for evaluating either segmentations</div><div>
or registrations.</div><div><br></div><div>See</div><div><a href="https://github.com/InsightSoftwareConsortium/ITK/tree/master/Modules/Filtering/DistanceMap/include">https://github.com/InsightSoftwareConsortium/ITK/tree/master/Modules/Filtering/DistanceMap/include</a><br>
</div><div><br></div><div><br></div><div>You will find some articles on this topic as well in the Insight Journal:</div><div><br></div><div>For example:</div><div><br></div><div><span style="color:rgb(0,0,0);font-family:arial,helvetica,sans-serif;font-size:13.142857551574707px;line-height:10.285714149475098px;background-color:rgb(255,250,236)"> </span><a href="http://hdl.handle.net/1926/561" style="font-weight:bold;text-decoration:none;color:rgb(55,78,158);font-family:arial,helvetica,sans-serif;font-size:13.142857551574707px;line-height:10.285714149475098px">http://hdl.handle.net/1926/561</a><span style="color:rgb(0,0,0);font-family:arial,helvetica,sans-serif;font-size:13.142857551574707px;line-height:10.285714149475098px;background-color:rgb(255,250,236)"></span><br>
</div><div><br></div><div><br></div><div><br></div><div> Regards,</div><div><br></div><div> Luis</div><div><br></div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Fri, Jan 10, 2014 at 1:54 AM, Massinissa Bandou <span dir="ltr"><<a href="mailto:Massinissa.Bandou@usherbrooke.ca" target="_blank">Massinissa.Bandou@usherbrooke.ca</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi Luis Ibanez,<br>
Sorry for late reply, I performed a landmark transform (ladmarks are<br>
extracted with boxWidget) followed with a mutual information registration to<br>
optimize the result. I multiplied the matrix obtained from the 3D mutual<br>
information with one obtained from landmarks transform. As you can see,<br>
visually, the result seems good but *how I can be sure that my registration<br>
is good or not*? for example I had to perform a surface registration using<br>
ICP algorithm and I use to display a graph of the mean distance according to<br>
the number of iteration.<br>
<br>
<<a href="http://itk-users.7.n7.nabble.com/file/n33163/PET_CT_Result.png" target="_blank">http://itk-users.7.n7.nabble.com/file/n33163/PET_CT_Result.png</a>><br>
<br>
I'd appreciate your help!<br>
<br>
Massi<br>
<br>
<br>
<br>
--<br>
View this message in context: <a href="http://itk-users.7.n7.nabble.com/registration-using-Mutual-Information-tp32972p33163.html" target="_blank">http://itk-users.7.n7.nabble.com/registration-using-Mutual-Information-tp32972p33163.html</a><br>
<div class="HOEnZb"><div class="h5">Sent from the ITK - Users mailing list archive at Nabble.com.<br>
_____________________________________<br>
Powered by <a href="http://www.kitware.com" target="_blank">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>
Kitware offers ITK Training Courses, for more information visit:<br>
<a href="http://www.kitware.com/products/protraining.php" target="_blank">http://www.kitware.com/products/protraining.php</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>
Community mailing list<br>
<a href="mailto:Community@itk.org">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>
</div></div></blockquote></div><br></div>