Hi - you're right that this should work well - we've never had a
problem with getting good results when feeding Brainweb output into
FAST.
If you'd like to upload your input image and tell us what FAST setting
you were using we can have a quick look.
Cheers.
On 5 Dec 2007, at 22:34, On Tsang wrote:
> Dear Hedok,
>
> Thank you for your reply. I have tried the 3% noise and 20% intensity
> nonuniformity T1w Brainweb image and obtained similar results. I used
> 3dSkullStrip to remove the skull first and then applied FAST with
> default
> parameters. Yet, I am still getting very high misclassifcation rate
> and the
> visual overlap is also quite poor.
>
> Please let me know if you have any suggestions. Thank you so much.
>
> Best Regards,
> On Tsang
>
> PS. I am using FAST version 3.53 and the latest version of AFNI
---------------------------------------------------------------------------
Stephen M. Smith, Professor of Biomedical Engineering
Associate Director, Oxford University FMRIB Centre
FMRIB, JR Hospital, Headington, Oxford OX3 9DU, UK
+44 (0) 1865 222726 (fax 222717)
[log in to unmask] http://www.fmrib.ox.ac.uk/~steve
---------------------------------------------------------------------------
|