The Michigan Image Reconstruction Toolbox (MIRT) is a collection of open source algorithms for image reconstruction (and related imaging problems) written in Mathwork’s Matlab language. This software was developed at the University of Michigan by Jeff Fessler and his group. The toolbox includes the following. 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.