Eddy current induced geometric distortions can only be accurately corrected in brain diffusion-weighted echo-planar (DW-EP) images for b-values less than approximately 300 s mm(-2) using the iterative cross-correlation (ICC) algorithm. This is due to the difference in signal intensity of the cerebrospinal fluid (CSF) compartment in the diffusion-weighted and baseline T-2-weighted echo-planar (T2W-EP) images. At larger values of b, image misalignment artefacts can, however, be removed by directly correlating CSF-suppressed T2W-EP images with non-CSF-suppressed and CSF-suppressed DW-EP images. Separate phantom experiments can also be performed to provide eddy current calibration data. Here the ability of these methods to remove eddy current induced artefacts from DW-EP images collected in volunteer diffusion tensor imaging (DTI) experiments is investigated. Monte Carlo simulations show that in order for the ICC algorithm to produce accurate estimates of the eddy current induced distortions at b-values greater than 1000 s mm(-2), the degree of CSF suppression should be greater than approximately 80%. This condition is typically met for FLAIR inversion times between 0.5 and 0.8 of the spin-lattice relaxation time of CSF. In volunteer studies the most complete image realignment was provided by direct correlation of CSF-suppressed T2W-EP and DW-EP images acquired in the FLAIR DTI experiment. These results indicate that although calibration data obtained from brain or phantom images can significantly reduce eddy current induced distortions, the optimum image realignment achievable using post-processing methods is likely to be that obtained by direct image warping techniques. (C) 2001 Elsevier Science Inc. All rights reserved.