Meeting Banner
Abstract #1426

Feasibility of myelin water fraction mapping with denoised 2D multi-echo GRE images based on deep learned reconstruction

Ho-Joon Lee1, Yeonah Kang1, Marc Lebel2, Jae Eun Song3, and Sung-Min Gho4
1Department of Radiology, Haeundae Paik Hospital, Busan, Republic of Korea, 2MR Collaboration and Development, GE Healthcare, Calagary, AB, Canada, 3Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea, 4MR Collaboration and Development, GE Healthcare, Seoul, Republic of Korea

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 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here