Unsupervised correction network for Nyquist ghost artifact and geometry distortion in echo planar imaging
Lists
Only you see this
Abstract
We propose a new correction scheme using a deep neural network with unsupervised learning to correct Nyquist ghosts and geometry distortions occurring in EPI. The proposed scheme includes NGAC-net and GDC-net. First, the NGAC-net estimates the phase error of k-space with the help of a ghost formulation operator and correlation loss. The NGAC-net produces two Nyquist ghost corrected images obtained by dual-polarity phase-encoding gradients. The GDC-net is trained to estimate the frequency-shift map using the two output images from the NGAC-net. Afterwards, an MR image generation operator utilizes the estimated frequency-shift map to obtain the geometry distortion corrected images.
BibTeX
@inproceedings{kim2023unsupervised,
author = {Jeewon Kim and Kinam Kwon and Seohee So and Byungjai Kim and Wonil Lee and HyunWook Park},
title = {{Unsupervised correction network for Nyquist ghost artifact and geometry distortion in echo planar imaging}},
booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
year = {2023},
doi = {10.58530/2022/0167},
}Loading related content...