With advances in deep learning, feasibility has been investigated for myelin water fraction (MWF) reconstruction showing promising results, enabling fast reconstruction, however whether images denoised with deep learned reconstruction(DL) will improve MWF map quality has not been investigated. After denoising of multi-echo GRE magnitude images with a DL algorithm, data was fitted to a three-component magnitude model. Use of DL, shows better results as compared to conventionally generated maps (i.e. decreased NRMSE and mean fitting errors (WM), increased PSNR and SSIM). Gibb's ringing artifact was removed remarkably.
This abstract and the presentation materials are available to members only; a login is required.