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

Veronika Spieker, Wenqi Huang, Hannah Eichhorn, Jonathan Stelter, Kilian Weiss +5 more
8/17/2023
eess.IVcs.CVcs.LG

No official code found. Best implementation: vjspi/ICoNIK (7 stars, last commit 2024-03-15).

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.

View on arXivView PDF

Code Implementations(1)

vjspi/ICoNIKCommunity100%
70PythonJul 25, 20232 years ago

Similar Papers

Self-Supervised k-Space Regularization for Motion-Resolved Abdominal MRI Using Neural Implicit k-Space Representation

86% match1 repo62024

SISMIK for brain MRI: Deep-learning-based motion estimation and model-based motion correction in k-space

84% match2023

B-FIRE: Binning-Free Diffusion Implicit Neural Representation for Hyper-Accelerated Motion-Resolved MRI

84% match2026

DoReMe: Dual optimization of Reconstruction and Motion estimation for self-navigated free-breathing abdominal MRI using Gaussian Splatting

82% match2026

Efficient MRI Parallel Imaging Reconstruction by K-Space Rendering via Generalized Implicit Neural Representation

82% match2 repos82023

Unsupervised Motion-Compensated Decomposition for Cardiac MRI Reconstruction via Neural Representation

81% match1 repo112025

Cite this paper

@article{spieker2023iconik,
  title  = {ICoNIK: Generating Respiratory-Resolved Abdominal MR Reconstructions Using Neural Implicit Representations in k-Space},
  author = {Veronika Spieker and Wenqi Huang and Hannah Eichhorn and Jonathan Stelter and Kilian Weiss and Veronika A. Zimmer and Rickmer F. Braren and Dimitrios C. Karampinos and Kerstin Hammernik and Julia A. Schnabel},
  year   = {2023},
  eprint = {2308.08830},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.08830v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.08830.svg)](https://codeofpaper.com/paper/2308.08830)

Discussion