[Insight-users] CMTK 1.0 Released

[Torsten Rohlfing]

Greetings, and apologies for the non-ITK topic.

As a one-time notice, I would like to let everyone know that we recently 
released version 1.0 of the Computational Morphometry Toolkit under the 
GPL, available in source and pre-compiled for selected platforms from 
http://www.nitrc.org/projects/cmtk/

The toolkit consists of a number of general purpose image processing 
libraries with a collection of command line tools as the primary front 
end, i.e., this is mainly intended for batch processing (but we are 
working on implementing Slicer plugin auto-detection).  All essential 
algorithms are implemented using SMP parallelism (POSIX threads and 
OpenMP), and some CPU hogs (groupwise registration) also come in 
distributed (MPI) variants.

The name CMTK is admittedly a bit misleading, because there are tools 
somewhat more general than morphometry, e.g., bias field correction, 
super-resolution volume reconstruction, label fusion (STAPLE), to name 
just a few. But what can you do, the child needs a name ;)

Note that CMTK is not meant to compete with ITK in any way -- but thanks 
to reading and writing Analyze, Nrrd, NIFTI, it will interface with ITK, 
FSL, etc. just fine.  A primary goal of releasing CMTK is to make 
available all software that I have been working on for, oh, ten years or 
so, and much of it actually predates ITK.  So in addition to making 
available tools that I felt were missing or hard to use in other 
software collections (not to mention any names), this provides access to 
the source code of virtually all tools that I have used in my academic 
papers over the years.

So feel free to take a peek and maybe take a tool or two for a spin! 
Documentation is still a bit sparse but improving.

Best,
   Torsten

-- 
Torsten Rohlfing, PhD          SRI International, Neuroscience Program
  Senior Research Scientist      333 Ravenswood Ave, Menlo Park, CA 94025
   Phone: ++1 (650) 859-3379      Fax: ++1 (650) 859-2743
    torsten at synapse.sri.com        http://www.stanford.edu/~rohlfing/

      "Though this be madness, yet there is a method in't"