Motion-Robust Deep Reconstruction for Free-Breathing Cardiac Cine MRI

2026-05-20

AI Summary

This work addresses the challenge of streaking artifacts in highly accelerated free-breathing cardiac cine MRI caused by respiratory and other physiological motion, particularly critical for pediatric and non-compliant patients unable to perform breath-holds. The authors propose a novel approach combining k-space preprocessing with model-based deep reconstruction. By employing retrospective ECG binning and respiratory gating to exclude motion-corrupted data, and introducing a new Streak-Optimized Coil (SOC) compression technique that explicitly suppresses peripheral artifact sources while preserving cardiac signal, the method enables high-quality reconstruction. A memory-efficient unrolled network is then used, alternating ResNet-based proximal operators with conjugate gradient steps enforcing data consistency. Experiments on both volunteer and newly recruited patient datasets demonstrate significant improvements over baseline methods such as k-t SENSE and iGRASP, with superior quantitative metrics and visual quality confirming its clinical feasibility.

Abstract

Conventional cardiac cine MRI relies on breath-hold Cartesian acquisitions, which are vulnerable to motion artifacts and can be uncomfortable or infeasible, particularly for pediatric and other noncompliant patients who cannot reliably hold their breath. Free-breathing radial acquisitions can alleviate these limitations, but robust reconstruction at high acceleration remains challenging due to prominent streak artifacts. To address these limitations, we propose Cine-DL, a clinically oriented framework that couples targeted k-space preprocessing with fast, model-based deep reconstruction. In this pipeline, raw free-breathing radial data undergo retrospective cardiac binning and respiratory gating to resolve cardiac phases and discard motion-corrupted spokes. We then introduce Streak Optimized Coil Compression (SOC), which explicitly preserves cardiac signals while suppressing peripheral interference that typically drives the streak artifacts. The resulting 2D+t cine series is reconstructed with an unrolled network that alternates a ResNet proximal operator with physics-based data consistency updates solved via conjugate gradient. We further employ a memory-efficient training strategy that reduces peak memory usage. We evaluate Cine-DL on free-breathing volunteer data against established baselines (k-t SENSE and iGRASP) and demonstrate clinical translation via hospital deployment on newly acquired patient data. Our experiments show that Cine-DL consistently improves quantitative metrics and visual fidelity, supporting a practical route toward routine, time-sensitive clinical adoption of free-breathing cine MRI.

Problem

• cardiac cine MRI
• motion artifacts
• free-breathing
• radial acquisition
• streak artifacts

Innovation

• free-breathing cardiac MRI
• deep reconstruction
• streak artifact suppression
• unrolled network
• coil compression