ICoNIK: Generating Respiratory-Resolved Abdominal MR Reconstructions Using Neural Implicit Representations in k-Space
This work addresses motion artifacts in abdominal MRI, offering a domain-specific solution for medical imaging, though it appears incremental as it builds on existing neural representation techniques.
The paper tackled the challenge of motion-resolved reconstruction in abdominal MRI by proposing neural implicit representations in k-space, resulting in methods that outperform standard techniques and reduce motion blurring and undersampling artifacts.
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.