Scan-specific, Parameter-free Artifact Reduction in K-space (SPARK)

TL;DR

This paper introduces SPARK, a CNN-based method that enhances MRI image quality by reducing artifacts in k-space through a physics-informed, parameter-free approach that improves reconstruction at various acceleration rates.

Contribution

SPARK is a novel, parameter-free CNN technique that synergizes with physics-based MRI reconstructions to effectively suppress artifacts across different acceleration levels.

Findings

Suppresses artifacts at high acceleration

Preserves and improves detail at moderate acceleration

Robust across various reconstruction methods

Abstract

We propose a convolutional neural network (CNN) approach that works synergistically with physics-based reconstruction methods to reduce artifacts in accelerated MRI. Given reconstructed coil k-spaces, our network predicts a k-space correction term for each coil. This is done by matching the difference between the acquired autocalibration lines and their erroneous reconstructions, and generalizing this error term over the entire k-space. Application of this approach on existing reconstruction methods show that SPARK suppresses reconstruction artifacts at high acceleration, while preserving and improving on detail in moderate acceleration rates where existing reconstruction algorithms already perform well; indicating robustness. Introduction Parallel