External Email - Use Caution        

Hi again,
You pick the most probable label at each voxel. In a binary segmentation problem, that amounts to thresholding at 50%. By with more labels, it does not, eg if p(a)=p.4, p(b)=0.3 and p(c)=0.3, you pick a even though p(a)<0.5.
Cheers
E

Sent from my phone, please excuse brevity and typos

From: freesurfer-bounces@nmr.mgh.harvard.edu <freesurfer-bounces@nmr.mgh.harvard.edu> on behalf of Mark Wagshul <Mark.Wagshul@einstein.yu.edu>
Sent: Friday, May 4, 2018 12:24:36 AM
To: Freesurfer support list
Subject: Re: [Freesurfer] Extracting DTI/NODDI data from hippocampal subfields
 
        External Email - Use Caution       

Eugenio,

Yes, we are on the same page, thank you so much for the advice.

One followup question - is the threshold on the binary masks 50%?

Mark
_______________________
Mark Wagshul, PhD
Albert Einstein College of Medicine
Bronx, NY

Sent from my iPhone

> On May 3, 2018, at 3:47 AM, Iglesias Gonzalez, Eugenio <e.iglesias@ucl.ac.uk> wrote:
>
> Eugenio


_______________________________________________
Freesurfer mailing list
Freesurfer@nmr.mgh.harvard.edu
https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer


The information in this e-mail is intended only for the person to whom it is
addressed. If you believe this e-mail was sent to you in error and the e-mail
contains patient information, please contact the Partners Compliance HelpLine at
http://www.partners.org/complianceline . If the e-mail was sent to you in error
but does not contain patient information, please contact the sender and properly
dispose of the e-mail.