[Insight-users] N3 algorithm with ITK

[Luis Ibanez]

Hi Radhika,

The N3 algorithm by Sled has not yet been implemented in ITK.
However, if any ITK user have done so and is willing to contribute 
his/her code to the toolkit we will be happy to add it.

The MRI inhomogeneity correction method currently available in ITK
is an implementation of the method by Styner et al. described in

"Parametric estimate of intensity inhomogeneities applied to MRI"
  Martin Styner, G. Gerig, Christian Brechbuehler, Gabor Szekely,
  IEEE TRANSACTIONS ON MEDICAL IMAGING; 19(3), pp. 153-165, 2000,
  (http://www . ia . unc . edu/public/styner/docs/tmi00 . pdf)

This paper by Styner makes the following mention to the Sled method:

   "A correction algorithm fully based on the histogram was proposed
    by Sled [20][21]. It requires a parametric model for the bias
    field but not a decomposition of the intensities into tissue
    classes.  The algorithm assumes that the histogram of an image
    represents the probability distribution of a given signal. The
    histogram of the undistorted image is estimated iteratively from
    the current histogram by estimating a parametric bias field with
    a histogram sharpening goal function".

where the citations [20] and [21] are:

[20] J.G. Sled, P. Zijdenbos and A.C. Evans
      "A comparison of retrospective intensity non-uniformity
       correction methods for MRI".
       Information Processing Medical Imaging
       Proc, 15th Int. Conf. IMPI'97, vol.1230, pp 459-464,1997.

[21] J.G. Sled, A.P. Zijdenbos and A.C. Evans.
      "A Nonparametric Method for Automatic Correction of
       Intensity Nonuniformity in MRI Data"
      IEEE Transactions on Medical Imaging, Vol 17, No 1. Feb 1998.


You will find an interesting list of Inhomogeneity correctoin tools
compiled by Finn A. Nielsen at the Technical University of Denmark

http://hendrix . imm . dtu . dk/staff/fnielsen/bib/Nielsen2001BibSegmentation/Nielsen2001BibSegmentation . html#SECTION00060000000000000000
(which includes both the Styner's and Sled's methods, among others).


The code for the N3 algorithm was made available by Sled at
McConnell Brain Imaging Centre, Montreal Neurological Institute

         http://www . bic . mni . mcgill . ca/software/N3/

It is implemented in Perl and the source code is available,
but I couldn't figure out any license terms stating what you
are allowed to do with the code.



Please let us know if you have further questions,


Thanks



    Luis



--------------------------------
Radhika Sivaramakrishna wrote:

> Has anyone written the N3 algorithm by Sled et al (MNI) for 
> inhomogeneity correction using ITK?
> 
> In Insight Applications, I find an algorithm for inhomogeneity. How does 
> this compare to N3?
> 
>  
> 
> Radhika
> 
>  
> 
> -----------------------------------------------------
> 
> Confidentiality Notice.
> 
> This email message is for the sole use of the intended recipient(s) and 
> may contain confidential and privileged information. Any unauthorized 
> review, use, disclosure or distribution is prohibited. If you are not 
> the intended recipient, please contact the sender by reply email and 
> destroy all copies of the original message. If you are the intended 
> recipient, please be advised that the content of this message is subject 
> to access, review and disclosure by the sender's Email System Administrator.
>