Low-Field Magnetic Resonance Image Quality Enhancement using Undersampled k-Space and Out-of-Distribution Generalisation

TL;DR

This paper introduces a novel deep learning framework that reconstructs high-quality, high-field-like MRI images from undersampled low-field k-space data, effectively handling out-of-distribution data and providing uncertainty quantification.

Contribution

It presents a unified approach combining low-field MRI reconstruction, quality enhancement, and uncertainty estimation using a dual-channel U-Net and ensemble methods.

Findings

Outperforms spatial-domain methods and baselines in image quality

Achieves high-quality images comparable to full high-field MRI

Demonstrates robustness on out-of-distribution data

Abstract

Low-field magnetic resonance imaging (MRI) offers affordable access to diagnostic imaging but faces challenges such as prolonged acquisition times and reduced image quality. Although accelerated imaging via k-space undersampling helps reduce scan time, image quality enhancement methods often rely on spatial-domain postprocessing. Deep learning achieved state-of-the-art results in both domains. However, most models are trained and evaluated using in-distribution (InD) data, creating a significant gap in understanding model performance when tested using out-of-distribution (OOD) data. To address these issues, we propose a novel framework that reconstructs high-field-like MR images directly from undersampled low-field MRI k-space, quantifies the impact of reduced sampling, and evaluates the generalisability of the model using OOD. Our approach utilises a k-space dual channel U-Net to jointly process the real and imaginary components of undersampled k-space, restoring missing frequency content, and incorporates an ensemble strategy to generate uncertainty maps. Experiments on low-field brain MRI demonstrate that our k-space-driven image quality enhancement outperforms the counterpart spatial-domain and other state-of-the-art baselines, achieving image quality comparable to full high-field k-space acquisitions using OOD data. To the best of our knowledge, this work is among the first to combine low-field MR image reconstruction, quality enhancement using undersampled k-space, and uncertainty quantification within a unified framework.