CEST MRI is influenced by fat signal, which can reduce the apparent CEST contrast or lead to pseudo‐CEST effects. Our goal was to develop a fat artifact correction based on multi‐echo fat–water separation that functions stably for 7 T knee MRI data.

Our proposed algorithm utilizes the full complex data and a phase demodulation with an off‐resonance map estimation based on the Z‐spectra prior to fat–water separation to achieve stable fat artifact correction. Our method was validated and compared to multi‐echo–based methods originally proposed for 3 T by Bloch–McConnell simulations and phantom measurements. Moreover, the method was applied to in vivo 7 T knee MRI examinations and compared to Gaussian fat saturation and a published single‐echo Z‐spectrum–based fat artifact correction method.

Phase demodulation prior to fat–water separation reduced the occurrence of fat–water swaps. Utilizing the complex signal data led to more stable correction results than working with magnitude data, as was proposed for 3 T. Our approach reduced pseudo‐nuclear Overhauser effects compared to the other correction methods. Thus, the mean asymmetry contrast at 3.5 ppm in cartilage over five volunteers increased from −9.2% (uncorrected) and −10.6% (Z‐spectrum–based) to −1.5%. Results showed higher spatial stability than with the fat saturation pulse.

Our work demonstrates the feasibility of multi‐echo–based fat–water separation with an adaptive fat model for fat artifact correction for CEST MRI at 7 T. Our approach provided better fat artifact correction throughout the entire spectrum and image than the fat saturation pulse or Z‐spectrum–based correction method for both phantom and knee imaging results.