[Brains-users] Some questions regarding segmentation

[christma at zi-mannheim.de]

Dear Eugene, dear Ronald,

I used carefully coregistered T1 and T2 images for 
segmentation and the cran.box. I got no masks at all. Then I 
lightened up the T1 images and the T2 images (with image 
math addition). In the following segmentation with the cran.
box I got good kappas

Kappa summary:  gm:  0.9906;  wm:  0.9954;  csf:  1.0000;  
vb:  0.9792;

Unfortunenately, the qualification was wrong. I attach an 
example. 

The next step was to use the brain.box. Here I got good 
kappas, too.

Kappa summary:  gm:  0.9711;  wm:  0.9684;  csf:  1.0000;  
vb:  0.9976;

In the end this segmentation was quite good as can be seen 
in the other attached picture.

Thanks again a lot for the help. 

Christoph 
**********************************************************************************************
IMPORTANT: The contents of this email and any attachments are confidential. They are intended for the 
named recipient(s) only.
If you have received this email in error, please notify the system manager or the sender immediately and do 
not disclose the contents to anyone or make copies thereof.
*** eSafe scanned this email for viruses, vandals, and malicious content. ***
**********************************************************************************************
-------------- next part --------------
A non-text attachment was scrubbed...
Name: wrong_seg_sm.jpg
Type: image/jpeg
Size: 172136 bytes
Desc: not available
Url : http://www.nitrc.org/pipermail/brains-users/attachments/20060125/016a745d/wrong_seg_sm.jpg
-------------- next part --------------
A non-text attachment was scrubbed...
Name: good_segm.jpg
Type: image/jpeg
Size: 181068 bytes
Desc: not available
Url : http://www.nitrc.org/pipermail/brains-users/attachments/20060125/016a745d/good_segm.jpg