Scan-Adaptive Dynamic MRI Undersampling Using a Dictionary of Efficiently Learned Patterns

TL;DR

This paper introduces a learning-based method for designing scan-adaptive undersampling patterns in dynamic cardiac MRI, significantly improving image quality and acceleration factors by tailoring sampling masks to individual scans.

Contribution

It proposes a novel framework that learns a dictionary of efficient undersampling patterns and selects optimal masks during inference, enhancing dynamic MRI reconstruction.

Findings

PSNR gains of 2-3 dB across datasets

Reduced NMSE and improved SSIM

Higher radiologist ratings of image quality

Abstract

Cardiac MRI is limited by long acquisition times, which can lead to patient discomfort and motion artifacts. We aim to accelerate Cartesian dynamic cardiac MRI by learning efficient, scan-adaptive undersampling patterns that preserve diagnostic image quality. We develop a learning-based framework for designing scan- or slice-adaptive Cartesian undersampling masks tailored to dynamic cardiac MRI. Undersampling patterns are optimized using fully sampled training dynamic time-series data. At inference time, a nearest-neighbor search in low-frequency $k$-space selects an optimized mask from a dictionary of learned patterns. Our learned sampling approach improves reconstruction quality across multiple acceleration factors on public and in-house cardiac MRI datasets, including PSNR gains of 2-3 dB, reduced NMSE, improved SSIM, and higher radiologist ratings. The proposed scan-adaptive sampling framework enables faster and higher-quality dynamic cardiac MRI by adapting $k$-space sampling to individual scans.