<div>Hi!</div>
<div> </div>
<div>Finally I am able to see the output image, but the registration result is not good enough! But I think that it will be better with your advices, so today I will try it.</div>
<div> </div>
<div>First I will try changing the metric (the interpolation that I used was Nearest Neighbor). And later, using Registration using masks constructed with Spatial objects, </div>
<div> </div>
<div>Thanks for your help!!<br><br> </div>
<div><span class="gmail_quote">On 12/7/05, <b class="gmail_sendername">Luis Ibanez</b> <<a href="mailto:luis.ibanez@kitware.com">luis.ibanez@kitware.com</a>> wrote:</span>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid"><br>Hi Marc,<br><br><br>1) When you started registering binary images,<br> Did you changed the Image Metric ?
<br><br> You probably should use a metric such as the<br><br><a href="http://www.itk.org/Insight/Doxygen/html/classitk_1_1KappaStatisticImageToImageMetric.html">http://www.itk.org/Insight/Doxygen/html/classitk_1_1KappaStatisticImageToImageMetric.html
</a><br><br> or the<br><br><a href="http://www.itk.org/Insight/Doxygen/html/classitk_1_1MatchCardinalityImageToImageMetric.html">http://www.itk.org/Insight/Doxygen/html/classitk_1_1MatchCardinalityImageToImageMetric.html
</a><br><br> that are intended for binary (or labeled) images.<br><br><br><br>2) Did you changed the interpolator ?<br><br> Once you use binary images you should only use<br> a Nearest Neighbor interpolator.<br><br>
<br><br><br>In any case,<br>I would suggest you that instead of registering the masks,<br>you could use the Masks in order to restrict the registration<br>method to use only the pixels in the Gray matter.<br><br><br>Please read the ITK Software Guide
<br><br> <a href="http://www.itk.org/ItkSoftwareGuide.pdf">http://www.itk.org/ItkSoftwareGuide.pdf</a><br><br>In particular Section 8.11.3:<br><br>"Registration using masks constructed with Spatial objects"
<br><br>in pdf-page 464.<br><br><br><br>The associated source code example can be found in<br><br> Insight/Examples/Registration/<br> ImageRegistration12.cxx<br><br><br><br>Note that, depending on the ImageMetric that you are using,
<br>you may want to extend (dilate) the Masks a bit in order to<br>make sure that a band of pixels *outside* of the gray matter<br>is also participating in the registration. The reason why<br>you need those pixels is that they will help to make your
<br>metric degrade when the two images are not well aligned.<br><br><br><br> Regards,<br><br><br><br> Luis<br><br><br><br>---------------<br>Marc Ruiz wrote:<br>> Hi!<br>><br>><br>><br>> I have registered two MRIs. The registration pipeline is first rigid and
<br>> then affine, and the results are ok.<br>><br>><br>><br>> But now I would try to register only the gray matter of these two<br>> images, because I am only interested in the registration of the cortex.
<br>> So, I have segmented the 2 images and now I am trying to do the same<br>> registration (rigid and affine) with two binary MRIs and with the same<br>> program and parameters.<br>><br>><br>><br>> The problem is that now I get the output image all white.
<br>><br>><br>><br>> First I thought it was only problem of the writer of the output image<br>> (the interpolation of the resample filter or something like that, due to<br>> the output is a binary image too), but I have applied the same
<br>> transformation (the one obtained from the registration of two gray<br>> matters) to a MRI and the transformation is bad done. So, I think it is<br>> problem of the registration…<br>><br>><br>><br>> So, some idea about the problem??
<br>><br>> 1) I have to change some parameters or the interpolation or…?<br>> 2) Which differences I have to think about to readapt the program?<br>> 3) Or some idea to register ok the gray matter?<br>><br>
> Thank you!!<br>><br>><br>> ------------------------------------------------------------------------<br>><br>> _______________________________________________<br>> Insight-users mailing list<br>>
<a href="mailto:Insight-users@itk.org">Insight-users@itk.org</a><br>> <a href="http://www.itk.org/mailman/listinfo/insight-users">http://www.itk.org/mailman/listinfo/insight-users</a><br><br></blockquote></div><br>