<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:10pt"><div>Hi Everybody,<br><br>I am a newbie to ITK community. I have couple of questions and I would be thankful if anybody answers:<br><br>-
Is there any fluid registration method implemented in ITK, either LDDMM
(Prof. Miller et al.) or fast diffeomorphism (Prof. Ashburner) ? If
not, is there any plan to implement such methods?<br><br>- As far as I know (so far) this paper and corresponding code is the only diffeomorphic registration method implemented in ITK:<br><font size="2"><br>"Diffeomorphic Demons Using ITK's Finite Difference Solver Hierarchy</font>" <br>by: <a href="http://www.insight-journal.org/midas/search.php?authorfirst=Tom&authorlast=Vercauteren" target="_blank">Tom Vercauteren</a>, <a href="http://www.insight-journal.org/midas/search.php?authorfirst=Xavier&authorlast=Pennec" target="_blank">Xavier Pennec</a>, <a href="http://www.insight-journal.org/midas/search.php?authorfirst=Aymeric&authorlast=Perchant" target="_blank">Aymeric Perchant</a>, <a href="http://www.insight-journal.org/midas/search.php?authorfirst=Nicholas&authorlast=Ayache" target="_blank">Nicholas Ayache</a><br>Jun-2007<br><br>I
found it very interesting and tried it over traditional "C" example
which is commonly used as a bench mark for fluid methods. My
understanding is that this is not a large deformation method. I got
following results after trying many parameters and different update
strategies:<br><br>Fixed image:<br><a target="_blank" href="http://www.4shared.com/file/55079305/f6267afa/fixed.html"><span class="yshortcuts" id="lw_1216014058_0">http://www.4shared.com/file/55079305/f6267afa/fixed.html</span></a><br>Moving Image:<br><a target="_blank" href="http://www.4shared.com/file/55079348/ecfbc343/moving.html"><span class="yshortcuts" id="lw_1216014058_1">http://www.4shared.com/file/55079348/ecfbc343/moving.html</span></a><br><br>--------------------<br>Diffeomorphic Demon update:<br>../DemonsRegistration -f fixed.nii -m moving.mha -a 0 -o Out_Diff.mha -v -i 200x4x4 -l6<br>Result: <br><a target="_blank" href="http://www.4shared.com/file/55082051/db2be42f/Out_Diff.html"><span class="yshortcuts" id="lw_1216014058_2">http://www.4shared.com/file/55082051/db2be42f/Out_Diff.html</span></a><br>------------------<br>Basic ITK Update:<br> ../DemonsRegistration -f fixed.nii -m moving.mha -a 1 -o Out_ITK.mha -v -i 300x30x30 -l
5<br>Result:<br><a target="_blank" href="http://www.4shared.com/file/55082650/a8a1a80b/Out_ITK.html"><span class="yshortcuts" id="lw_1216014058_3">http://www.4shared.com/file/55082650/a8a1a80b/Out_ITK.html</span></a><br>-------------------<br>Thirion Update:<br>../DemonsRegistration -f fixed.nii -m moving.mha -a 2 -o Out_Thr.mha -v -i 300x30x30 -l 10<br>Result:<br><a target="_blank" href="http://www.4shared.com/file/55080214/66a0c941/Out_Thr.html"><span class="yshortcuts" id="lw_1216014058_4">http://www.4shared.com/file/55080214/66a0c941/Out_Thr.html</span></a><br><br>to see warped grids and determinant of Jacobians for each method, please
visit:<br><a target="_blank" href="http://www.4shared.com/dir/8238152/7295688e/Registration_Results.html"><span class="yshortcuts" id="lw_1216014058_5">http://www.4shared.com/dir/8238152/7295688e/Registration_Results.html</span></a><br><br>Unlike basic ITK which produce negative <span style="border-bottom: 1px dashed rgb(0, 102, 204); cursor: pointer;" class="yshortcuts" id="lw_1216014058_6">Jacobian</span>
(but good registration), both Diff. Demon and Thirion methods yiled
non-negative Jacobian. However, Thirion got much better registration
result with lower residual than Diff. Demon. In addition, no matter how
small step size is, in the Multi-resolution 1 and 2 (in Diff. Demon) it
increases MSE instead of decreasing it. I know that the step size I
used for Diff. Demon is very aggresive but even with default step size
it increases MSE in the Multi-res 1& 2. <br><br>I was wondering whether I am making a mistake or in general Thirion
update works better while procuding diffeomorphic transformation? I
mean, I think the advange of Diff. Demon is that it gaurantees to
produce Diffeomorphic transformation but does it necessarily sacrify accuracy?
or I am making a mistake somewhere? Do you think that combined method (sometimes Thirion sometimes Diff.
Demon) works better? Or this method is not essentially proper for large
deformation?<br><br>Any comment is appreciated.<br><br>Sincerely,<br>Kaveh<br><br></div></div><br>
</body></html>