ICoNIK: Generating Respiratory-Resolved Abdominal MR Reconstructions Using Neural Implicit Representations in k-Space

TL;DR

This paper introduces NIK and ICoNIK, neural implicit representations in k-space, to improve motion-resolved abdominal MRI reconstructions by reducing blurring and artefacts, leveraging continuous signal generation and informed correction.

Contribution

The work presents a novel neural implicit representation approach in k-space for motion-resolved MRI, incorporating an informed correction layer to enhance reconstruction quality.

Findings

Outperforms standard motion-resolved reconstruction techniques

Reduces motion artefacts and blurring in abdominal MRI

Provides continuous signal generation in k-space

Abstract

Motion-resolved reconstruction for abdominal magnetic resonance imaging (MRI) remains a challenge due to the trade-off between residual motion blurring caused by discretized motion states and undersampling artefacts. In this work, we propose to generate blurring-free motion-resolved abdominal reconstructions by learning a neural implicit representation directly in k-space (NIK). Using measured sampling points and a data-derived respiratory navigator signal, we train a network to generate continuous signal values. To aid the regularization of sparsely sampled regions, we introduce an additional informed correction layer (ICo), which leverages information from neighboring regions to correct NIK's prediction. Our proposed generative reconstruction methods, NIK and ICoNIK, outperform standard motion-resolved reconstruction techniques and provide a promising solution to address motion artefacts in abdominal MRI.