Abstract #1352

DeepResp: Deep Neural Network for respiration-induced artifact correction in 2D multi-slice GRE

Hongjun An¹, Hyeong-Geol Shin¹, Sooyeon Ji¹, Woojin Jung¹, Sehong Oh², Dongmyung Shin¹, Juhyung Park¹, and Jongho Lee¹

¹Department of Electrical and computer Engineering, Seoul National University, Seoul, Korea, Republic of, ²Division of Biomedical Engineering, Hankuk University of Foreign Studies, Gyeonggi-do, Korea, Republic of

Respiration-induced B₀ fluctuation can generate artifacts by inducing phase errors. In this study, a new deep-learning method, DeepResp, is proposed to correct for the artifacts in multi-slice GRE images without any modification in sequence or hardware. DeepResp is designed to extract the phase errors from a corrupted image using deep neural networks. This information was applied to k-space data, generating an artifact-corrected image. When tested, DeepResp successfully reduced the artifacts of in-vivo images, showing improvements in normalized-root-mean-square error (deep breathing: from 13.9 ± 4.6% to 5.8 ± 1.4%; natural breathing: from 5.2 ± 3.3% to 4.0 ± 2.5%).

This abstract and the presentation materials are available to members only; a login is required.

Join Here