mlsanityData to 14 Oct 2026

Implicit Neural Networks with Fourier-Feature Inputs for Free-breathing Cardiac MRI Reconstruction

arXiv 2305.06822 ↗First posted 11 May 2023eess.IV cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Cardiac magnetic resonance imaging (MRI) requires reconstructing a real-time video of a beating heart from continuous highly under-sampled measurements. This task is challenging since the object to be reconstructed (the heart) is continuously changing during signal acquisition. In this paper, we propose a reconstruction approach based on representing the beating heart with an implicit neural network and fitting the network so that the representation of the heart is consistent with the measurements. The network in the form of a multi-layer perceptron with Fourier-feature inputs acts as an effective signal prior and enables adjusting the regularization strength in both the spatial and temporal dimensions of the signal. We study the proposed approach for 2D free-breathing cardiac real-time MRI in different operating regimes, i.e., for different image resolutions, slice thicknesses, and acquisition lengths. Our method achieves reconstruction quality on par with or slightly better than state-of-the-art untrained convolutional neural networks and superior image quality compared to a recent method that fits an implicit representation directly to Fourier-domain measurements. However, this comes at a relatively high computational cost. Our approach does not require any additional patient data or biosensors including electrocardiography, making it potentially applicable in a wide range of clinical scenarios.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 22 of its 46 references that are in the map. First posted on arXiv 11 May 2023.

Builds on

22 of 46 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  4. 2017Deep Image Priorcited by 1,098
  5. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 346
  6. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  7. 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 232
  8. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  9. 2021NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstructioncited by 146
  10. 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
  11. 2017Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstructioncited by 105
  12. 2019Time-Dependent Deep Image Prior for Dynamic MRIcited by 70
10 more
  1. 2021IREM: High-Resolution Magnetic Resonance (MR) Image Reconstruction via Implicit Neural Representationcited by 42
  2. 2019Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generatorscited by 40
  3. 2020Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximationcited by 39
  4. 2022Spatiotemporal implicit neural representation for unsupervised dynamic MRI reconstructioncited by 36
  5. 2022Neural Implicit k-Space for Binning-free Non-Cartesian Cardiac MR Imagingcited by 35
  6. 2020Deep Low-rank plus Sparse Network for Dynamic MR Imagingcited by 32
  7. 2021Dynamic imaging using a deep generative SToRM (Gen-SToRM) modelcited by 17
  8. 2019Extreme MRI: Large-Scale Volumetric Dynamic Imaging from Continuous Non-Gated Acquisitionscited by 12
  9. 2020Complementary Time-Frequency Domain Networks for Dynamic Parallel MR Image Reconstructioncited by 10
  10. 2022Scale-Agnostic Super-Resolution in MRI using Feature-Based Coordinate Networkscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 7; 2026: 3.

15 papers.

Sort:

By area:

  1. 2023Unsupervised reconstruction of accelerated cardiac cine MRI using Neural Fieldscited by 8
  2. 2024INFusion: Diffusion Regularized Implicit Neural Representations for 2D and 3D accelerated MRI reconstructioncited by 4
  3. 2024Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural Representationcited by 4
  4. 2025Dynamic-Aware Spatio-temporal Representation Learning for Dynamic MRI Reconstructioncited by 4
  5. 2025PISCO: Self-Supervised k-Space Regularization for Improved Neural Implicit k-Space Representations of Dynamic MRIcited by 4
  6. 2024Fully Unsupervised Dynamic MRI Reconstruction via Diffeo-Temporal Equivariancecited by 3
  7. 2025RSR-NF: Neural Field Regularization by Static Restoration Priors for Dynamic Imagingcited by 2
  8. 2024Enhancing Dynamic CT Image Reconstruction with Neural Fields and Optical Flowcited by 1
  9. 2025Accelerating multiparametric quantitative MRI using self-supervised scan-specific implicit neural representation with model reinforcementcited by 1
  10. 2025KP-INR: A Dual-Branch Implicit Neural Representation Model for Cardiac Cine MRI Reconstructioncited by 1
  11. 2025Self-supervised Deep Unrolled Model with Implicit Neural Representation Regularization for Accelerating MRI Reconstructioncited by 1
  12. 2025Compressive Imaging Reconstruction via Tensor Decomposed Multi-Resolution Grid Encodingcited by 0
3 more
  1. 2026MoE-dqINR: A Unified Mixture-of-Experts Implicit Neural Representation Framework for Scan-Specific Dynamic and Quantitative MRI Reconstructioncited by 0
  2. 2026Piecewise Dynamic Diffusion Regularization for Reconstruction of Cardiac Cine MRIcited by 0
  3. 2026Enhancing Implicit Neural Representations with Image Feature Embedding for Unsupervised Cardiac Cine MRI Reconstructioncited by 0