Improving high frequency image features of deep learning reconstructions via k‐space refinement with null‐space kernel
Sign Up to like & getrecommendations! Published in 2022 at "Magnetic Resonance in Medicine"
DOI: 10.1002/mrm.29261
Abstract: Deep learning (DL) based reconstruction using unrolled neural networks has shown great potential in accelerating MRI. However, one of the major drawbacks is the loss of high‐frequency details and textures in the output. The purpose… read more here.
Keywords: high frequency; space kernel; space; null space ... See more keywords