[Brains-users] brain mask - problems with automatic definition

[Ronald Pierson]

Just thought I'd chime in - wanted to earlier, but have been too busy.

I think one of the main problems we run into is when the brain is in an
orientation that places part of the brain outside of where our probability
map says it should be.  Take a look at the sagittal window on the attachment
that Eugene sent last week.  Then, take a look at the midsagittal slice of
your typical scan.  Now, I can't tell for sure from your snapshots, but it
would appear to me that your brain is tilted back a fair amount compared to
our standard, average orientation.  Is that the case?  If so, then the
superior frontal lobe will be higher than normal, and the cerebellum lower
than normal inside the Talairach bounds, pushing them outside of the regions
where the ANN expects to find the brain.

Is this a consistent problem?  If so, maybe you are picking the AC and PC
different from us.  We pick the AC point to be just above the AC, and the PC
point just below it.  If you picked both of them in their centers, the head
would be rotated back further than our "typical" orientation.

We are currently developing new methods to remove the dependence on
Talairach bounds and to better handle the nonstandard brains and
orientations better.  Hopefully in the next 6 months or so we will release a
method for a good no-trim brains on >90% of the cases.

Ron Pierson



-----Original Message-----
From: brains-users-bounces at psychiatry.uiowa.edu
[mailto:brains-users-bounces at psychiatry.uiowa.edu] On Behalf Of Eugene Zeien
Sent: Monday, February 19, 2007 10:17 AM
To: Christoph Christmann
Cc: Brains-users at www.psychiatry.uiowa.edu
Subject: Re: [Brains-users] brain mask - problems with automatic definition

I have, in fact, had very similar problems.  "standard workup"
is not a part of my daily routine, but I needed to generate a
brain mask for a project.  Rather than ask a more experienced
person to create one, I decided "I can do this".  Then I
proceeded to do just about everything wrong. :-)  One by one,
I found the problems and fixed them.  Eventually (about 1 day)
I had the neural net making pretty brains.

The basic issue I see with your mask is:
The neural net is not finding the expected anatomical boundaries.  So,
the end result is merely the probability
mask where more than 50% of the subjects used to train the
neural net had a region identified as brain.

Why?  Well, there can be several causes.  
  incorrect talairach bounds
  over-inclusive blood traces which lead to
  bad segmentation
  incorrect image specified for the neural net's use

There may be other ways to confuse the neural net, but these
are the things I had done.  Of those problems, you've checked
three.  The only one left is if the segmented image has CSF
classified as blood.  So, load up the image, then
  Viewers->Tracker
and set the crosshairs in brains2 to somewhere in the
ventricles.  The values (poke around several places) should
be around 30.  If you see the values showing up as 0 or 1, then
something has gone wrong in the segmentation.  The values
outside the brain/head should be 0.  You should only find 1's
where major blood vessels exist.

On Mon, 2007-02-19 at 10:15 +0100, Christoph Christmann wrote:
> hi gene,
> 
> we always used proper talairach bounds. here, we just added the image 
> to some former work where we used the 'talairach box' lines for 
> different orientation purposes.
> 
> are there any further hints regarding the brain mask? dont you have 
> similar problems?
> 
> christoph
> 
> At Friday 16.02.2007 16:52, you wrote:
> >Christoph,
> >    Are the red lines on the images you sent the Talairach bounds?
> >If so, they are nowhere near the correct location.  Try re-defining
> >the talairach boundaries, then run the neural net again.
> >    I've attached a picture showing proper talairach boundaries.
> >The 2 points near the center are supposed to be the anterior and
> >posterior commissures.
> >gene
> >
> >On Fri, 2007-02-16 at 12:35 +0100, Christoph Christmann wrote:
> > > hi,
> > >
> > > the segmented image looks reasonable. I attach some pictures
> > > elucidating the actual situation. I am especially surprised that the
> > > cerebellum border is not found correctly although it seems to be
> > > obvious as you can see in the brain_mask_cor_seg.jpg file. You can
> > > see in the other two images, that T1 and T1 is realigned quite well
> > > (cost function < 0.45).
> > >
> > > If you would have any idea to use other programs to get the brain
> > > mask I would try this way, too. Actually, we started with BrainSuite
> > > but found it to be less precise, too - although in other regions.
> > > Maybe we end up with an SPM or FSL segmentation for the mask.
> > >
> > > Best regards
> > >
> > > Christoph
> >
> >
> 
_______________________________________________
Brains-users mailing list
Brains-users at www.psychiatry.uiowa.edu
http://www.psychiatry.uiowa.edu/mailman/listinfo/brains-users