MATLAB: How to validate the registration after use imregister with 3D images

3d imagesimregistervalidation

Hi!

I'm using imregister for register sets of MR images (512x512x28). After use imregister I'd like to check how good is the registration, but I can't do it graphically because imshowpair only allow 2D input images. My question is, does someone knows another equivalent function as imshowpair valid for 3D images? or if not, how can check that my registratios is good enough?

Thank you in advance

Best Answer

Why not apply imshow() to the difference image in some slice

imshow(registeredImage(:,:,slice)-targetImage(slice(:,:,slice)

You can do this for different slices (you don't have that many). There are also a number of 3D image viewers offered the File Exchange

http://www.mathworks.com/matlabcentral/fileexchange/?search_submit=fileexchange&query=3D+viewer&term=3D+viewer

Related Solutions

MATLAB: Imregister translation mode, suppress registration in second direction

One hack that I can think of (and I emphasize that it is only a hack) is to deliberately corrupt the images with bright horizontal line patterns and apply imregtform. That way, a strong gradient against shifts in the y-direction will be introduced into the registration cost function. I illustrate this in the example below where the true translation is [10,0.6], but with this technique the registration is forced to reach a translation estimate in which the y-component is greatly suppressed. It should work even better, however, in your case where the true translation really does have y=0.

%% Simulation
moving = dicomread('knee1.dcm');
fixed=imtranslate(moving,[10,0.6]);
[optimizer, metric] = imregconfig('monomodal');
%% Corrupt the images with bright horizontal lines
Mcorr=moving; Mcorr(1:2:end,:)=3000; 
Fcorr=fixed; Fcorr(1:2:end,:)=3000;
tform0 = imregtform(moving, fixed,'translation',optimizer,metric);
tform = imregtform(Mcorr,Fcorr,'translation',optimizer,metric);
base_tform = tform0.T, 
constrained_tform = tform.T

The results are

base_tform =
    1.0000         0         0
         0    1.0000         0
   10.0000    0.6000    1.0000
constrained_tform =
    1.0000         0         0
         0    1.0000         0
    9.9149    0.0033    1.0000

MATLAB: How to deblur an image after gauss filter and image registration

Use imregtform to perform the registration on the blurred images and to obtain the optimal tform. Then apply the tform to your original unblurred moving image.

Best Answer

Related Solutions

MATLAB: Imregister translation mode, suppress registration in second direction

MATLAB: How to deblur an image after gauss filter and image registration

Related Question