Physics-Driven Zero-Shot MRI Reconstruction with Non-local Image Priors

• URL: http://arxiv.org/abs/2606.15110v1
• Date: Sat, 13 Jun 2026 04:57:19 GMT
• Title: Physics-Driven Zero-Shot MRI Reconstruction with Non-local Image Priors
• Abstract summary: ZS-SSL has emerged as a promising paradigm for accelerated Magnetic Resonance Imaging (MRI) reconstruction.<n>We propose a robust physics-driven framework that synergizes physical consistency with image-domain non-local priors.<n>Our approach achieves state-of-the-art performance, particularly under high acceleration factors.
• Score: 3.412182028038034
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Zero-Shot Self-Supervised Learning (ZS-SSL) has emerged as a promising paradigm for accelerated Magnetic Resonance Imaging (MRI) reconstruction, eliminating the reliance on fully-sampled external datasets. However, learning solely from a single under-sampled scan suffers from supervision scarcity and optimization instability, often leading to overfitting or artifacts. To address these challenges, we propose a robust physics-driven ZS-SSL framework that synergizes physical consistency with image-domain non-local priors. Our method introduces three core innovations: (1) a Coil Sensitivity Map (CSM)-Guided Dynamic Repository, which stabilizes the training trajectory by filtering physically inconsistent artifacts based on coil sensitivity constraints; (2) a SPIRiT-based regularization, which enforces k-space self-consistency via a learned correlation kernel and stochastic masking; (3) a Non-Local Self-Similarity (NSS) Pixel Bank, which leverages the high-fidelity reference established by the former modules to explicitly mine non-local anatomical similarities, thereby augmenting supervision in the image domain. Extensive experiments on the FastMRI dataset demonstrate that our approach achieves state-of-the-art performance, particularly under high acceleration factors, effectively bridging the gap between zero-shot learning and supervised methods. The code is available at https://github.com/Zolento/NS-SSL.

Related papers

• Implicit Neural Speckle Denoising [8.506200151475559]
  We introduce a training-free framework that combines a neural representation with an aperture-aware maximum-likelihood to recover dynamic, speckle-free imagery directly from noisy observations.<n>Results show improved spatial fidelity, temporal consistency, and varying speckle statistics relative to classical, unsupervised, and supervised observations.
  arXiv  Detail & Related papers  (2026-08-06T20:36:51Z)
• Self-Supervised Implicit CEST Reconstruction via Physics-Informed Lorentz Encoding [22.500041095230177]
  Lorentz (LE) is a physics-informed framework that formulates CEST reconstruction as a self-supervised reconstruction task via implicit continuous coordinate learning.<n>Experiments on in vivo human brain data demonstrate that LE significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-07-07T10:49:07Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Efficient Complex-Valued Vision Transformers for MRI Classification Directly from k-Space [4.973425214325723]
  Deep learning applications in Magnetic Resonance Imaging (MRI) predominantly operate on reconstructed magnitude images.<n>Standard neural network architectures rely on local operations (convolutions or grid-patches) that are ill-suited for the global, non-local nature of raw frequency-domain (k-Space) data.<n>We propose a novel complex-valued Vision Transformer (kViT) designed to perform classification directly on k-Space data.
  arXiv  Detail & Related papers  (2026-01-26T11:50:52Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data [11.174208209806073]
  Undersampling strategies can accelerate image acquisition, but they often result in image artifacts and degraded quality.<n>Recent diffusion models have shown promise for reconstructing high-fidelity images from undersampled data by learning powerful image priors.<n>We introduce a conditional denoising diffusion framework with iterative data-consistency correction.
  arXiv  Detail & Related papers  (2025-10-07T18:01:08Z)
• Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations [57.054499278843856]
  Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies.<n>Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs.<n>We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured fMRI data.
  arXiv  Detail & Related papers  (2025-10-05T12:35:01Z)
• PHASE-Net: Physics-Grounded Harmonic Attention System for Efficient Remote Photoplethysmography Measurement [63.007237197267834]
  Existing deep learning methods are mostly physiological monitoring and lack theoretical robustness.<n>We propose a physics-informed r paradigm derived from the Navier-Stokes equations of hemodynamics, showing that the pulse signal follows a second-order system.<n>This provides a theoretical justification for using a Temporal Conal Network (TCN)<n>Phase-Net achieves state-of-the-art performance with strong efficiency, offering a theoretically grounded and deployment-ready r solution.
  arXiv  Detail & Related papers  (2025-09-29T14:36:45Z)
• SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion [52.959716866316604]
  Camera-based 3D Semantic Scene Completion (SSC) is a critical task in autonomous driving systems.<n>We propose the Semantic-PHysical Engaged REpresentation (SPHERE) for camera-based SSC.<n>SPHERE integrates voxel and Gaussian representations for joint exploitation of semantic and physical information.
  arXiv  Detail & Related papers  (2025-09-14T09:07:41Z)
• Simulating Sinogram-Domain Motion and Correcting Image-Domain Artifacts Using Deep Learning in HR-pQCT Bone Imaging [0.0]
  We optimize a conventional sinogram-based method to simulate motion artifacts in HR-pQCT images.<n>We propose an Edge-enhanced Self-attention Wasserstein Generative Adversarial Network with Gradient Penalty (ESWGAN-GP) to address motion artifacts in both simulated (source) and real-world (target) datasets.
  arXiv  Detail & Related papers  (2025-09-13T19:43:05Z)
• PISCO: Self-Supervised k-Space Regularization for Improved Neural Implicit k-Space Representations of Dynamic MRI [10.397363299674508]
  We introduce a novel self-supervised k-space loss function at $mathL_mathrmPISCO.<n>The proposed loss function is based on the concept of parallel imaging-inspired self-consistency.<n>It achieves superior stability compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-01-16T09:18:59Z)
• Self-Consistent Nested Diffusion Bridge for Accelerated MRI Reconstruction [22.589087990596887]
  We focus on the underexplored task of magnitude-image-based MRI reconstruction.<n>Recent advancements in diffusion models, particularly denoising diffusion probabilistic models, have demonstrated strong capabilities in modeling image priors.<n>We propose a novel Self-Consistent Nested Diffusion Bridge (SC-NDB) framework that models accelerated MRI reconstruction.
  arXiv  Detail & Related papers  (2024-12-13T09:35:34Z)
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning [68.9515120904028]
  Limited-angle tomography of strongly scattering quasi-transparent objects is a challenging, highly ill-posed problem. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. We devised a recurrent neural network (RNN) architecture with a novel split-convolutional gated recurrent unit (SC-GRU) as the building block.
  arXiv  Detail & Related papers  (2020-07-21T11:48:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.