<html><head><style type="text/css"><!-- DIV {margin:0px;} --></style></head><body><div style="font-family:times new roman, new york, times, serif;font-size:12pt"><div style="font-family: times new roman,new york,times,serif; font-size: 12pt;">Hi Luis,<br><br> Thank you for your reply. Well, the algorithm takes very long. It stops only because it reaches the 500th iteration (the limit). Yes, both are CT images.<br><br>I guess the lungs collapse because I do the registration in one step, instead of using Rigid registration as a precursor.<br><br>My dataset is as such :<br><br>Set 1 : 512 x 512 x 30 (resolution 0.68 x 0.68 x 1.0)<br>Set 2: 512 x 512 x 30 (resolution 1.0 x 1.0 x 1.0)<br><br>The ITK example file has a default spacing of (1, 1, 1) I guess and I had used this earlier, hence the result I guess. <br><br>I have since changed it. But the results are not good. The output image does not have default values in the middle, but the difference images are highly
speckled. I am not sure why this has happened. I have yet to run enough tests to make sur ethat I do not get any default values in the center slices.<br><br>Also, doesn't ITK automatically get the spacing information from the dicom files ? <br>I wrote a program to read dicom series, generate a .vtk file and rewrite teh dicom series.<br><br>While the output images of this dicom conversion match the input, the .vtk file has wrong spacing information (1, 1, 1) instead of (0.68, 0.68, 1). Hence I am also not able to view it in Volview.<br><br>What happens to the spacing information, is a mystery.<br><br>Any tips how I can solve this ?<br><br>Emma<br><br><br><div style="font-family: times new roman,new york,times,serif; font-size: 12pt;">----- Original Message ----<br>From: Luis Ibanez <luis.ibanez@kitware.com><br>To: Emma Ryan <eryanvtk@yahoo.com><br>Cc: insight-users@itk.org<br>Sent: Thursday, July 5, 2007 1:41:13 PM<br>Subject: Re: [Insight-users] Error in
Registration results<br><br><div><br>Hi Emma,<br><br><br><br> mm... it is hard to explain indeed.<br><br><br>Your intuition is correct regarding the fact that the<br>default pixel value "shouldn't" appear in the middle slices.<br><br>That being said, it is not "impossible" for the value to<br>appear there. The fact that it is appearing, is an indication<br>that one of the nodes in the BSplineGrid has a deformation so<br>large that it sends the point outside of the image physical<br>extent. In other words, the registration failed largely.<br><br>The extreme deformation that the two sliced display are also<br>a bad indication of the results of the registration. For<br>example, the first slice in your email has the lungs collapsed<br>towards the medial plane.<br><br>You should probably rerun the registration by using different<br>parameters for the optimizer. In particular you probably should<br>set the Bound values
for the parameters of the Transform.<br><br><br>BTW:<br><br>1) How many iterations did the algorithm *actually* ran ?<br><br>2) Where the two images of the same modality ?<br><br> The metric used in this example is MeanSquares,<br> so it pretty much assumes that the images are of<br> the same modality and with a very close distribution<br> of intensity values.<br><br><br><br> Regards,<br><br><br><br> Luis<br><br><br><br>-----------------<br>Emma Ryan wrote:<br>> Hi,<br>> <br>> I am trying to register 2 volumes. I use ITK example - <br>> DeformableRegistration7.cxx to do so. The default pixel values is 100. <br>> So any empty space is filled with this grey value. So it is <br>> understandable if the first slice shows this grey region since they are <br>> tyring to align
along the 'Z' direction. Also, if this grey value <br>> appears along the boundary of the images, it makes sense.<br>> <br>> But how does one explain the appearance of the default grey value <br>> (100) in the center slices. I have attached some images and labelled <br>> them with thier corresponding slice number.<br>> <br>> I thought the problem was with resampling, but that part of the code <br>> seems correct, besides I have used the example cpp file as is.<br>> <br>> I see some of these 'artifacts' in the center slices as well.<br>> Any clue ?<br>> <br>> Emma<br>> <br>> ------------------------------------------------------------------------<br>> Be a better Globetrotter. Get better travel answers <br>> <<a target="_blank"
href="http://us.rd.yahoo.com/evt=48254/*http://answers.yahoo.com/dir/_ylc=X3oDMTI5MGx2aThyBF9TAzIxMTU1MDAzNTIEX3MDMzk2NTQ1MTAzBHNlYwNCQUJwaWxsYXJfTklfMzYwBHNsawNQcm9kdWN0X3F1ZXN0aW9uX3BhZ2U-?link=list&sid=396545469%3Efrom">http://us.rd.yahoo.com/evt=48254/*http://answers.yahoo.com/dir/_ylc=X3oDMTI5MGx2aThyBF9TAzIxMTU1MDAzNTIEX3MDMzk2NTQ1MTAzBHNlYwNCQUJwaWxsYXJfTklfMzYwBHNsawNQcm9kdWN0X3F1ZXN0aW9uX3BhZ2U-?link=list&sid=396545469>from</a> <br>> someone who knows.<br>> Yahoo! Answers - Check it out.<br>> ------------------------------------------------------------------------<br>> <br>> <br>> ------------------------------------------------------------------------<br>> <br>> <br>> ------------------------------------------------------------------------<br>> <br>> _______________________________________________<br>> Insight-users mailing list<br>> Insight-users@itk.org<br>> <a target="_blank"
href="http://www.itk.org/mailman/listinfo/insight-users">http://www.itk.org/mailman/listinfo/insight-users</a><br></div></div><br></div></div><br>
<hr size=1><a href="http://us.rd.yahoo.com/evt=48250/*http://searchmarketing.yahoo.com/arp/sponsoredsearch_v9.php?o=US2226&cmp=Yahoo&ctv=AprNI&s=Y&s2=EM&b=50">Pinpoint customers </a>who are looking for what you sell.
</body></html>