[Insight-users] references

[Luis Ibanez]

Hi Zein,

Just a word of caution about these segmentation classes.

Even though the concept behind them is relatively simple,
they have proved to be very succesful in solving real
clinical segmentation problems.

The ConfidenceConnectedImageFilter (that Jim wrote), for
example, has been used for segmenting liver tumors in CT
and more recently lungs in CT.

One of the sad realities of image processing & publications
is that sometimes the methods that do the real job are not
complex enough to look good in a journal paper.

...unfortunately the reverse is also true...


    Luis


========================================================

Miller, James V (Research) wrote:
> The filters are not based on any published papers.  They represent a set 
> of simple algorithms based on the combination of an ImageFunction with a 
> ConditionalIterator. They start from a seed pixel and add pixels to the 
> segmentation that are "connected" to the seed pixel (using a flood fill 
> type algorithm) and satisfy a specified criterion (which may be based on 
> the seed pixel).
> 
>  
> 
>  
> 
>     -----Original Message-----
>     *From:* Zein Salah [mailto:salah@gris.uni-tuebingen.de]
>     *Sent:* Tuesday, November 05, 2002 12:09 PM
>     *To:* ITK Users
>     *Subject:* [Insight-users] references
> 
>     Hello all,
> 
>      
> 
>     I am searching for the references (literature, papers,...) for the
>     following filters:
> 
>      
> 
>     1. ConnectedThresholdImageFilter
> 
>     2. ConfidenceConnectedImageFilter
> 
>     3. NeighborhoodConnectedImageFilter
> 
>      
> 
>     can anybody guide me to the addresses of these filters, i.e. the
>     papers on which their implementation based.
> 
>      
> 
>     many thanks,
> 
>      
> 
>     Zein
> 
>      
> 
>      
> 
>     ->8<------------->8<------------->8<------------->8<------------->8<------------->8<-
>     Zein I. Salah
>     Universität Tübingen, WSI-GRIS
>     Sand 14
>     72076 Tübingen
>     Email: salah@gris.uni-tuebingen.de
>     <mailto:salah@gris.uni-tuebingen.de>  / zeinsalah@hotmail.com
>     <mailto:zeinsalah@hotmail.com>
>     Tel.: (07071) 29 75465 (GRIS) , (07071) 96 44 39 (privat)
>     Fax: (07071) 29 54 66
>