• Iterative and non-iterative algorithms for tomographic imaging (PET, SPECT, X-ray CT).
• Methods for magnetic resonance (MR) image reconstruction, including compensation for off-resonance effects (field inhomogeneity, susceptibility, etc.).
• Methods for MR RF pulse design, including MRI spectral-spatial pulse design for phase-precompensatory slice selection
• Iterative image restoration tools.
• Methods for B-spline based image registration with regularization to encourage the deformation to be invertible (diffeomorphic)
• A NUFFT Matlab toolbox that performs fast and accurate nonuniform FFT computations.

Downloading

• Via this link: http://www.eecs.umich.edu/~fessler/irt/irt you can access the individual files and directories.
  However, if you access them one-by-one, you will need to download many files to get much of anything to work.
• Instead, you should just download the entire package file via this link: http://www.eecs.umich.edu/~fessler/irt/fessler.tgz.

Installing
After downloading, move the tar file to a clean subdirectory before extracting its contents since it installs into the current directory.
Start with the readme file.

Notes
You may freely use and distribute this software as long as you retain the author's name (myself and/or my students) with the software, and if you make changes, please change the file name (like the GNU software license).

Although Matlab is an expensive commercial software package, the toolbox should also run on upcoming release of freemat, an open-source alternative to Matlab.

The code from Dan Yu for level-set based image reconstruction is here: http://www.eecs.umich.edu/~fessler/irt/yu.tar.gz. Unfortunately, that code is completely undocumented, so I cannot support it at all.

We welcome feedback, but do remember that this is open source software so you should study the code before sending bug reports.

The learnCT JAVA tutorial may be of interest too.