<html>
<head>
<style>
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
FONT-SIZE: 10pt;
FONT-FAMILY:Tahoma
}
</style>
</head>
<body class='hmmessage'>
Greetings, <BR>
<BR>
I had posted a question a while back about intensity-based registration for low-contrast images. Thank you Luis for providing some pointers. You had requested I post example images so that you and the rest of the community might suggest what metrics are best suited to try to do automatic registration. I was waiting until I was able to create my own images before I posted them. The following links show two images, one which is rotated 5 degrees with respect to the other (rotation about the image center). <BR>
<BR>
<META content="Microsoft SafeHTML" name=Generator>
<STYLE>
.ExternalClass .EC_hmmessage P
{padding:0px;}
.ExternalClass body.EC_hmmessage
{font-size:10pt;font-family:Tahoma;}
</STYLE>
<A href="http://www.hotlinkfiles.com/view/full/1600023_zwyje" target=_blank>http://www.hotlinkfiles.com/view/full/1600023_zwyje</A><BR> <BR><A href="http://www.hotlinkfiles.com/view/full/1600024_ujxkr" target=_blank>http://www.hotlinkfiles.com/view/full/1600024_ujxkr</A><BR>
<BR>
These images are part of 3D-tomographic datasets. I chose the two corresponding slices that showed the most contrast to post as an example. All other images have even less contrast than shown here. <BR>
<BR>
Bearing in mind that I am new to ITK, I was wondering whether someone could suggest a metric that would be good for automatically registering two 3D datasets of such images. I would be happy to post the full image-sets if that would be more helpful. I am trying to determine the shifts in the three axes as well as rotations about each axis. <BR>
<BR>
Any help that anybody can provide will be much appreciated. <BR>
<BR>
Vik<BR><BR>> <BR>> Hi Vikren,<BR>> <BR>> <BR>> 1) Yes, it is possible with ITK to compute the rigid transform that<BR>> will map the coordinate system of your fixed image into the<BR>> coordinate system of the moving image.<BR>> <BR>> <BR>> 2) Could you post screeshots of your low contract images in a public<BR>> web site ?<BR>> <BR>> Being able to see the images will help us a lot for recommending<BR>> you an image metric to use.<BR>> <BR>> <BR>> In the absence of being able to see your image, here are two<BR>> suggestions that come to mind:<BR>> <BR>> A) Normalized Correlation metric<BR>> <BR>> B) Passing your images through edge detection filters<BR>> and then using the results as the actual images to<BR>> register. (you will find several edge-detection<BR>> filters in ITK, you probably want to start with<BR>> a simple gradient magnitude filter).<BR>> <BR>> <BR>> C) Mutual information is still an option that you<BR>> could reconsider, and for which you may have to<BR>> adjust the parameters of number of bins and<BR>> number of samples.<BR>> <BR>> <BR>> <BR>> In general, you should be careful discarding a particular technique<BR>> based on having tried it once, with only a reduced set of parameters.<BR>> <BR>> It is not uncommon that for a fine-tunning exercise to be required<BR>> before you get acceptable results with a given technique.<BR>> <BR>> <BR>> <BR>> Regards,<BR>> <BR>> <BR>> Luis<BR>> <BR>> <BR>> ---------------------<BR>> Vikren Sarkar wrote:<BR>> > Greetings,<BR>> > <BR>> > <BR>> > <BR>> > I am new to ITK and am trying to use the registration algorithms to<BR>> > register two 3D x-ray image datasets. The problem is that all the<BR>> > images have very low contrast and the intensity-based algorithms<BR>> > fail when used with the mean square metric (I also tried mutual<BR>> > information with no success). I need to perform a rigid registration<BR>> > and am hoping someone with more experience could suggest a metric<BR>> > which would be appropriate for use with low contrast images.<BR>> > <BR>> > <BR>> > <BR>> > Alternatively, I am open to the idea of using control points which<BR>> > the user would input. I am most interested in the actual values of<BR>> > translation, rotation and scaling required for the registration than<BR>> > in the final registered datasets themselves. The reason is that we<BR>> > are investigating the use of those images in patient positioning<BR>> > prior to radiation delivery. Can someone please point me in the<BR>> > right direction as to whether this is possible using ITK? It is<BR>> > probably obvious that I am very new at this and I would appreciate<BR>> > any help and/or pointers. Thank you.<BR>> > <BR>> > <BR>> > <BR>> > Vik<BR>> > <BR><BR><BR><br /><hr />Time for vacation? WIN what you need. <a href='http://www.gowindowslive.com/summergiveaway/?ocid=tag_jlyhm' target='_new'>Enter Now!</a></body>
</html>