Harnessing Magnitude-Only and Complex Measurements for Improved Dynamic MRI Reconstruction with Learned Priors
Researchers propose a new method for improving dynamic MRI reconstruction using both magnitude-only and complex measurements. They show that k-space magnitudes are consistent across time-frames, which is used to inform a deep learning-based reconstruction method. The proposed method, $ ext{C}+ ext{Mag}$, outperforms conventional methods in suppressing artifacts, recovering anatomy, and preserving phase information.
Researchers propose a new method for improving dynamic MRI reconstruction using both magnitude-only and complex measurements. They show that k-space magnitudes are consistent across time-frames, which is used to inform a deep learning-based reconstruction method. The proposed method, $ ext{C}+ ext{Mag}$, outperforms conventional methods in suppressing artifacts, recovering anatomy, and preserving phase information.
---
Why it matters: This work matters for engineers working on MRI reconstruction because it explores the potential of using magnitude-only measurements to improve image quality and reduce scan time. The proposed method can be used to accelerate dynamic MRI acquisitions, which is crucial for various medical applications.
Source: https://arxiv.org/abs/2608.18036
This article was originally published at: https://arxiv.org/abs/2608.18036