[Insight-users] ITK ROAD MAP 2005-2006 : Call for feedback

[Martin Kavec]

Hi Luis.

My reply comes a bit later, because I were to ISMRM annual meeting and I came 
with a pile of ideas what I would like to do with ITK and what, eventually,
other people could find useful. Last few years, MRI turns towards 
quantitative analysis of a scanner output. Many MRI-derived parameters are 
being put into the context of physiology and these parameters are being 
extensively studied in inter- and intra-institutional trials. In this regard, 
a lack of common platform for image analysis has been very often mentioned at 
the conference. In my view, ITK could find a niche in this field. Brief look 
at the ITK roadmap suggests that, indeed, this was considered, by including 
perfusion analysis.

I'll try to find a time to implement quantification of MR 
relaxation parameters, namely T1, T2 and ADC, just to have a practice in ITK 
development.

1. However, more advanced analysis, which I am interested in, such 
as Dynamic Contrast Susceptibily MRI (DCS-MRI), also known as the bolus 
tracking, is out of my reach. It would be great, if ITK would have 
implemented:

- singular value decomposition
- independent component analysis
- expectation-minimization,

These algorithms would thus allow for quantification of absolute/relative 
perfusion of human organs (brain, kidney, heart, ....), based on the central 
volume theorem.

2. Monte Carlo is often used in testing robustness of different algorithms in 
MRI, so it would be nice to have a framework for it in ITK as well.

3. Also implementation of hidden Markov random field would be useful. Some 
great segmentation algorithms giving superior results use it.

4. I am finding most of the ITK's Doxygen documentation too sparse. It is 
sometimes quite difficult to find needed method. Names of the methods and 
objects are generally descriptive, but not always help.

I find particularly useful plans for dicom query/retrieve implementation in 
the sketch of the roadmap. This would make possible to automate image 
analysis. It's really important.

I am starting to implement correction of geometric distortions in EPI based 
MRI and if it works fine, I'll obviously pass it to public. Also I have one 
student, and hopefully more to come, working on ITK implementation of some 
nice algorithms (feature preserving filtering), which I hope should not be 
problem to share.

So. That's what came across my mind. I hope it's not going to take you most of 
you time to implement, if you consider it.
:)

Thanks.

Martin

On Wednesday 11 May 2005 17:53, Luis Ibanez wrote:
> A first draft of the road map for ITK development/maintenance has
> been crafted for the period of September 2005 - September 2006.
>
>
> You will find this draft as a link to the Oversight Committee page
>
> http://www.itk.org/Wiki/ITK_Oversight_Committee
>
>
> More specifically at
>
>
> http://www.itk.org/Wiki/ITK_Roadmap_2005_2006
>
>
> The purpose of this road map is to plan for features and functionalities
> to be included in ITK in the near/medium term (1 to 2 years).
>
> The addition of these features should make of ITK a better tool for
> supporting your efforts in medical research, and development of medical
> applications.
>
> The road map also includes the maintenance tasks to be undertaken in
> ITK. This may involve refactoring of classes, deprecation of classes,
> additional testing, additional coverage, improvements on tutorials and
> so on.
>
>
> Please let us know of the features that you would like to see in ITK
> in the upcoming future, and what points of the toolkit you consider
> that can be improved in order to better server the community.
>
>
>
>     Thanks
>
>
>
>        Luis
>
>
>
>
>
>
>
>
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users

-- 
*********************************
Department of Electrical Engineering and Computer Science
University of Liege
Sart-Tilman, Bldg. B28
Liege B-4000
BELGIUM

Phone: +32 4 366-2870
*********************************