EMSegment odd result

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

EMSegment odd result

inorton
Hi,

I followed the EMSegment Simple tutorial and got an odd-looking result (see screenshots) using the MR-head sample dataset as specified in the tutorial. This was repeated on 32 (Ubuntu 10.04) and 64-bit (SPL Fedora) versions of Slicer3-3.6.2-2010-11-03-linux-x86_64.

It looks like the atlas is significantly overfitted (see ss5).

Has anything changed since this tutorial was written?:
http://www.slicer.org/slicerWiki/images/d/d9/EMSegmenterTutorialSimpleMode-2010-Nov.pdf

Thanks,

-Isaiah

_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject

emsegment-ss.png (425K) Download Attachment
emseg-ss4.png (279K) Download Attachment
emseg-ss5.png (429K) Download Attachment
Reply | Threaded
Open this post in threaded view
|

Re: EMSegment odd result

Dominique Belhachemi
Hi Isaiah,

You are right, the registration step failed in this case. If you have a chance please try the Slicer-3-6 branch version or wait for the official Slicer3-3.6.3 version. The EMSegmenter will be using the CMTK extension (if it is installed) which gives you better results. The downside is that the registration step may take a few more hours. I am updating the tutorials appropriate.

Thanks
Dominique



On Wed, Feb 16, 2011 at 2:52 PM, Isaiah Norton <[hidden email]> wrote:
Hi,

I followed the EMSegment Simple tutorial and got an odd-looking result (see screenshots) using the MR-head sample dataset as specified in the tutorial. This was repeated on 32 (Ubuntu 10.04) and 64-bit (SPL Fedora) versions of Slicer3-3.6.2-2010-11-03-linux-x86_64.

It looks like the atlas is significantly overfitted (see ss5).

Has anything changed since this tutorial was written?:
http://www.slicer.org/slicerWiki/images/d/d9/EMSegmenterTutorialSimpleMode-2010-Nov.pdf

Thanks,

-Isaiah

_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
Reply | Threaded
Open this post in threaded view
|

Re: EMSegment odd result

madanrao
Hello Isaiah,

You can use Slicer3 versions: 3.2 and (even earlier) for EM segmenter.

Hope it helps.

AM Mohan Rao

On Thu, Feb 17, 2011 at 2:21 AM, Dominique Belhachemi <[hidden email]> wrote:
Hi Isaiah,

You are right, the registration step failed in this case. If you have a chance please try the Slicer-3-6 branch version or wait for the official Slicer3-3.6.3 version. The EMSegmenter will be using the CMTK extension (if it is installed) which gives you better results. The downside is that the registration step may take a few more hours. I am updating the tutorials appropriate.

Thanks
Dominique



On Wed, Feb 16, 2011 at 2:52 PM, Isaiah Norton <[hidden email]> wrote:
Hi,

I followed the EMSegment Simple tutorial and got an odd-looking result (see screenshots) using the MR-head sample dataset as specified in the tutorial. This was repeated on 32 (Ubuntu 10.04) and 64-bit (SPL Fedora) versions of Slicer3-3.6.2-2010-11-03-linux-x86_64.

It looks like the atlas is significantly overfitted (see ss5).

Has anything changed since this tutorial was written?:
http://www.slicer.org/slicerWiki/images/d/d9/EMSegmenterTutorialSimpleMode-2010-Nov.pdf

Thanks,

-Isaiah

_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject