Each k-space segment in multishot diffusion-weighted MRI is affected by a different spatially varying phase which is caused by unavoidable motions and amplified by the diffusion-encoding gradients. A proper image reconstruction therefore requires phase maps for each segment. Such maps are commonly derived from two-dimensional navigators at relatively low resolution but do not offer robust solutions. For example, phase variations in diffusion-weighted MRI of the brain are often characterized by high spatial frequencies. To overcome this problem, an inverse reconstruction method for segmented multishot diffusion-weighted MRI is described that takes advantage of the full k-space data acquired from multiple receiver coils. First, the individual coil sensitivities are determined from the non-diffusion-weighted acquisitions by regularized nonlinear inversion. These coil sensitivities are then used to estimate accurate motion-associated phase maps for each segment by iterative linear inversion. Finally, the coil sensitivities and phase maps serve to reconstruct artifact-free images of the object by iterative linear inversion, taking advantage of the data of all segments. The efficiency of the new method is demonstrated for segmented diffusion-weighted stimulated echo acquisition mode MRI of the human brain.
(c) 2009 Wiley-Liss, Inc.