Home Messages Index
[Date Prev][Date Next][Thread Prev][Thread Next]
Author IndexDate IndexThread Index

[Fwd: Re: MARS - Models of Appearance, Registration and Segmentation Feedback]

  • To: Roy <roy@xxxxxxxxxxxxxxx>
  • Subject: [Fwd: Re: MARS - Models of Appearance, Registration and Segmentation Feedback]
  • From: Roy Schestowitz <r@xxxxxxxxxxxxxxx>
  • Date: Wed, 22 Feb 2006 05:41:21 +0000
  • Delivery-date: Wed, 22 Feb 2006 05:48:09 +0000
  • Envelope-to: r@schestowitz.com
  • Openpgp: id=74572E8E; url=http://schestowitz.com/PGP
  • Organization: MCC / Manchester University
  • Reply-to: s@xxxxxxxxxxxxxxx
  • User-agent: Mozilla Thunderbird 1.0.2 (X11/20050317)
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Hi,

> MARS - Models of Appearance, Registration and Segmentation
>
> <snip />
>
> I discover today this website, that seems to be a \'blog\' attempt to federate efforts around AAM activities, as an old-school newsgroup or mailing list would do with less convenience.


I set it up with PHP-Nuke (a one-click installation)  and was hoping,
but not truly expecting, for a bit of involvement. Comments require
registration with the site, which in turn helps the prevention of spam.
I am glad someone noticed the site! *smile*


> Unfortunately, I did not manage to see any comments posted for proposed topics. Does it means that discussions are held offline or under ICQ or so?


I think it just means that no-one wants to comment. *frown* I guess
comment in sites or blogs are becoming a rarity, with so many such sites
around.


> Also, I am working in 3D ASM applied in Brain MRI internal structures.


This sounds like the work of Tim Cootes and Rhodri Davies. The latter
work built optimal ASM's in 3-D automatically.


> Do you think I will be continuously off-topic, considering AAMs imposes different conditions (though some are in common)?


AAM's are a hog to build in 3-D and they pose many problems. We are
currently trying to build them automatically in 3-D, but there are a few
issues associated with meshes. They also take an obscene time to run and
are difficult to view, analyze and interact with.


> Segmentation is my final purpose, and Registration is usefull for my method, but from an end-user point of view... I am particularly interested in automatic annotation works, though I\'ve not seen anything on it for now...
>
> Best regards,


I am not sure about /full/ annotation and identification of structures.
However, the papers from Davies (see cache at:
http://72.14.207.104/search?q=cache:s55IxIVFNewJ:www.cfn.unimelb.edu.au/rhhd/+rhodri+davies&hl=en&gl=uk&ct=clnk&cd=5
) explain how to deal with shapes in 3-D and refine their model
representation.

Let me know how it goes...

With kind regards,

Roy
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.2-rc1-SuSE (GNU/Linux)

iD8DBQFD+/mBU4xAY3RXLo4RAm/SAKCNMaQ518MLjXPhpf+IhBCHgz9xNwCeKF36
NEfmfUAnTc7tpO2FHsCzOx4=
=tGTg
-----END PGP SIGNATURE-----

[Date Prev][Date Next][Thread Prev][Thread Next]
Author IndexDate IndexThread Index