Harnessing Magnitude-Only and Complex Measurements for Improved Dynamic MRI Reconstruction with Learned Priors
2026-08-18 • Artificial Intelligence
Artificial IntelligenceComputer Vision and Pattern RecognitionMachine Learning
AI summaryⓘ
The authors explored a new way to improve MRI images by using not just the complex data usually collected, but also the magnitude (size) of the signals from MRI scans taken over time. They found that these magnitude measurements are consistent across time, which helps make better images without extra scanning. They created a deep learning method called C+Mag that uses this magnitude information to reconstruct MRI images more clearly and reduce artifacts. Tests showed their method produces sharper images and preserves important details better than traditional methods.
MRI reconstructionk-spacemagnitude measurementssteady-state dynamic MRIdeep learningADMMdata-fidelityphase informationundersamplingcine MRI
Authors
Mahdi Saberi, Yaşar Utku Alçalar, Merve Gülle, Chetan Shenoy, Mehmet Akçakaya
Abstract
MRI reconstruction methods for undersampled k-space data naturally utilize complex-valued measurements. Parallel developments in sparse phase retrieval have shown that magnitude-only measurements may provide complementary information for signal recovery. However, their use in MRI reconstruction remains largely unexplored, due to lack of practical settings where informative magnitude measurements can be obtained without additional scan time. In this work, we investigate the use of auxiliary k-space magnitude information for accelerated steady-state dynamic MRI reconstruction, and demonstrate strong consistency of k-space magnitudes across time-frames. Building on this observation, we propose $\mathbb{C}+\text{Mag}$, a magnitude-informed physics-driven deep learning reconstruction method. The proposed method employs an ADMM-based unrolling framework with a novel magnitude-aware data-fidelity formulation, where quadratically smoothed optimization and momentum-based updates are introduced to address the non-differentiability and non-convexity of the magnitude constraints. Experiments on retrospectively undersampled cine MRI and phase-contrast flow MRI datasets, as well as prospectively undersampled real-time cine MRI acquisitions, demonstrate improved artifact suppression, sharper anatomical recovery, and better preservation of phase information compared to conventional PD-DL methods, which is further supported through blinded expert reader evaluations.