mlsanityData to 13 Oct 2026

Highly Accelerated MRI via Implicit Neural Representation Guided Posterior Sampling of Diffusion Models

arXiv 2407.02744 ↗First posted 3 Jul 2024eess.IV cs.CVcited by 5

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Reconstructing high-fidelity magnetic resonance (MR) images from under-sampled k-space is a commonly used strategy to reduce scan time. The posterior sampling of diffusion models based on the real measurement data holds significant promise of improved reconstruction accuracy. However, traditional posterior sampling methods often lack effective data consistency guidance, leading to inaccurate and unstable reconstructions. Implicit neural representation (INR) has emerged as a powerful paradigm for solving inverse problems by modeling a signal's attributes as a continuous function of spatial coordinates. In this study, we present a novel posterior sampler for diffusion models using INR, named DiffINR. The INR-based component incorporates both the diffusion prior distribution and the MRI physical model to ensure high data fidelity. DiffINR demonstrates superior performance on experimental datasets with remarkable accuracy, even under high acceleration factors (up to R=12 in single-channel reconstruction). Notably, our proposed framework can be a generalizable framework to solve inverse problems in other medical imaging tasks.

Key facts. Cited by 5 papers in the map (data through 13 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 39 of its 61 references that are in the map. First posted on arXiv 3 Jul 2024.

Builds on

39 of 61 references.

Closest ancestors · 10

Same direction, newest first

  1. 2023Self-Supervised MRI Reconstruction with Unrolled Diffusion Models29 Jun
  2. 2022SPIRiT-Diffusion: SPIRiT-driven Score-Based Generative Modeling for Vessel Wall imaging14 Dec
  3. 2022Self-Score: Self-Supervised Learning on Score-Based Models for MRI Reconstruction2 Sep
  4. 2022High-Frequency Space Diffusion Models for Accelerated MRI10 Aug
  5. 2022Adaptive Diffusion Priors for Accelerated MRI Reconstruction12 Jul
  6. 2022Towards performant and reliable undersampled MR reconstruction via diffusion model sampling8 Mar
  7. 2022Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstruction5 Mar
  8. 2022Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Models3 Feb
  9. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Models15 Nov
  10. 2021Score-based diffusion models for accelerated MRI8 Oct

Other references · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,712
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,686
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,183
  5. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,403
  6. 2018On the Spectral Bias of Neural Networkscited by 1,329
  7. 2017Deep Image Priorcited by 1,097
  8. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 508
  9. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 467
  10. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 432
  11. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 386
  12. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 342
17 more
  1. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 307
  2. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  3. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 285
  4. 2017Image reconstruction by domain transform manifold learningcited by 231
  5. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
  6. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistencycited by 181
  7. 2021NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstructioncited by 145
  8. 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problemscited by 131
  9. 2021A Structured Dictionary Perspective on Implicit Neural Representationscited by 100
  10. 2021Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fieldscited by 70
  11. 2022ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformercited by 52
  12. 2021Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fieldscited by 48
  13. 2021On Measuring and Controlling the Spectral Bias of the Deep Image Priorcited by 36
  14. 2022Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomographycited by 31
  15. 2023IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRIcited by 23
  16. 2021Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matchingcited by 18
  17. 2022One-shot Generative Prior in Hankel-k-space for Parallel Imaging Reconstructioncited by 12

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025SpINR: Neural Volumetric Reconstruction for FMCW Radarscited by 5
  2. 2025I-INR: Iterative Implicit Neural Representationscited by 2
  3. 2025Highly Undersampled MRI Reconstruction via a Single Posterior Sampling of Diffusion Modelscited by 2
  4. 2025SpINRv2: Implicit Neural Representation for Passband FMCW Radarscited by 1
  5. 2026DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024INFusion: Diffusion Regularized Implicit Neural Representations for 2D and 3D accelerated MRI reconstruction
  2. 2024Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution
  3. 2026Regularizing INR with diffusion prior self-supervised 3D reconstruction of neutron computed tomography data
  4. 2023Diffusion Modeling with Domain-conditioned Prior Guidance for Accelerated MRI and qMRI Reconstruction
  5. 2024Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data
  6. 2025Patch-Based Diffusion for Data-Efficient, Radiologist-Preferred MRI Reconstruction
  7. 2026Likelihood-Separable Diffusion Inference for Multi-Image MRI Super-Resolution
  8. 2024DPER: Diffusion Prior Driven Neural Representation for Limited Angle and Sparse View CT Reconstruction