🤖 AI Summary
In accelerated MRI with undersampling, diagnostic reliability is compromised by degraded image quality, concurrent noise, and motion artifacts. To address this, we propose USArt—a novel deep learning framework that jointly models undersampled reconstruction and multi-class artifact correction (noise and motion). USArt employs a dual-branch collaborative architecture: one branch optimizes image fidelity, while the other suppresses artifacts. Specifically designed for Cartesian 2D brain MRI, it supports diverse undersampling patterns. Experiments demonstrate that, at up to 5× acceleration, USArt significantly improves signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), effectively eliminates artifacts, and maintains strong robustness across multiple degradation scenarios—including varying noise levels, motion magnitudes, and sampling patterns. To our knowledge, USArt is the first method to unify undersampling reconstruction and heterogeneous artifact correction in a single end-to-end trainable model. It establishes a new paradigm for rapid, high-fidelity clinical MRI acquisition.
📝 Abstract
MR data are acquired in the frequency domain, known as k-space. Acquiring high-quality and high-resolution MR images can be time-consuming, posing a significant challenge when multiple sequences providing complementary contrast information are needed or when the patient is unable to remain in the scanner for an extended period of time. Reducing k-space measurements is a strategy to speed up acquisition, but often leads to reduced quality in reconstructed images. Additionally, in real-world MRI, both under-sampled and full-sampled images are prone to artefacts, and correcting these artefacts is crucial for maintaining diagnostic accuracy. Deep learning methods have been proposed to restore image quality from under-sampled data, while others focused on the correction of artefacts that result from the noise or motion. No approach has however been proposed so far that addresses both acceleration and artefacts correction, limiting the performance of these models when these degradation factors occur simultaneously. To address this gap, we present a method for recovering high-quality images from under-sampled data with simultaneously correction for noise and motion artefact called USArt (Under-Sampling and Artifact correction model). Customized for 2D brain anatomical images acquired with Cartesian sampling, USArt employs a dual sub-model approach. The results demonstrate remarkable increase of signal-to-noise ratio (SNR) and contrast in the images restored. Various under-sampling strategies and degradation levels were explored, with the gradient under-sampling strategy yielding the best outcomes. We achieved up to 5x acceleration and simultaneously artefacts correction without significant degradation, showcasing the model's robustness in real-world settings.