Are Natural-Domain Foundation Models Effective for Accelerated Cardiac MRI Reconstruction?

• URL: http://arxiv.org/abs/2604.22557v1
• Date: Fri, 24 Apr 2026 13:52:25 GMT
• Title: Are Natural-Domain Foundation Models Effective for Accelerated Cardiac MRI Reconstruction?
• Abstract summary: We investigate whether natural-domain foundation models can serve as effective image priors for accelerated cardiac MRI reconstruction.<n>We show that while task-specific state-of-the-art reconstruction models such as E2E-VarNet achieve superior performance in standard in-distribution settings, foundation-model-based approaches remain competitive.
• Score: 9.952061326734741
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The emergence of large-scale pretrained foundation models has transformed computer vision, enabling strong performance across diverse downstream tasks. However, their potential for physics-based inverse problems, such as accelerated cardiac MRI reconstruction, remains largely underexplored. In this work, we investigate whether natural-domain foundation models can serve as effective image priors for accelerated cardiac MRI reconstruction, and compare the performance obtained against domain-specific counterparts such as BiomedCLIP. We propose an unrolled reconstruction framework that incorporates pretrained, frozen visual encoders, such as CLIP, DINOv2, and BiomedCLIP, within each cascade to guide the reconstruction process. Through extensive experiments, we show that while task-specific state-of-the-art reconstruction models such as E2E-VarNet achieve superior performance in standard in-distribution settings, foundation-model-based approaches remain competitive. More importantly, in challenging cross-domain scenarios, where models are trained on cardiac MRI and evaluated on anatomically distinct knee and brain datasets--foundation models exhibit improved robustness, particularly under high acceleration factors and limited low-frequency sampling. We further observe that natural-image-pretrained models, such as CLIP, learn highly transferable structural representations, while domain-specific pretraining (BiomedCLIP) provides modest additional gains in more ill-posed regimes. Overall, our results suggest that pretrained foundation models offer a promising source of transferable priors, enabling improved robustness and generalization in accelerated MRI reconstruction.

Related papers

• Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction [52.32112533846212]
  MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions.<n>We address this limitation by moving reconstruction to discrete multi-scale latent space and posing it as autoregressive next-acceleration-scale prediction.<n>We show that our approach delivers improved reconstruction performance across diverse sampling patterns under extreme undersampling.
  arXiv  Detail & Related papers  (2026-05-19T04:40:50Z)
• CRUNet-MR-Univ: A Foundation Model for Diverse Cardiac MRI Reconstruction [2.695455737934403]
  Deep learning has attracted increasing interest in the field of Cardiac MRI reconstruction.<n>CMR scans exhibit wide variability in image contrast, sampling patterns, vendors, anatomical structures, and scanner types.<n>Most existing models are designed to handle only a single or nar row subset of these variations, leading to performance degradation when faced with distribution shifts.
  arXiv  Detail & Related papers  (2026-01-07T22:23:56Z)
• On The Role of K-Space Acquisition in MRI Reconstruction Domain-Generalization [0.0]
  We show that the benefits of learned k-space sampling can extend beyond the training domain, enabling superior reconstruction performance under domain shifts.<n>We propose a novel method that enhances domain robustness by introducing acquisition uncertainty during training-stochastically perturbing k-space trajectories to simulate variability across scanners and imaging conditions.
  arXiv  Detail & Related papers  (2025-12-06T18:49:46Z)
• Region-Aware Reconstruction Strategy for Pre-training fMRI Foundation Model [0.7771985426812056]
  We introduce an ROI-guided masking strategy to selectively mask semantically coherent brain regions during self-supervised pretraining.<n>We show that our method achieves a 4.23% improvement in classification accuracy for distinguishing healthy controls from individuals diagnosed with ADHD.<n>Our results demonstrate that masking anatomical regions during model pretraining not only enhances interpretability but also yields more robust and discriminative representations.
  arXiv  Detail & Related papers  (2025-11-01T08:12:00Z)
• Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction [65.67001243986981]
  We propose MindHier, a coarse-to-fine fMRI-to-image reconstruction framework built on scale-wise autoregressive modeling.<n>MindHier achieves superior semantic fidelity, 4.67x faster inference, and more deterministic results than the diffusion-based baselines.
  arXiv  Detail & Related papers  (2025-10-25T15:40:07Z)
• Self-supervised Deep Unrolled Model with Implicit Neural Representation Regularization for Accelerating MRI Reconstruction [19.419634295527974]
  Accelerating MRI reconstruction addresses this issue by reconstructing high-fidelity MR images from undersampled k-space measurements.<n>This paper proposes a novel zero-shot self-supervised reconstruction method named UnrollINR, which enables scan-specific MRI reconstruction without external training data.
  arXiv  Detail & Related papers  (2025-10-08T03:40:40Z)
• Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport [58.6869774515413]
  This paper introduces imaging Knowledge-Informed Dynamic Optimal Transport (KIDOT), a novel dynamic optimal transport framework.<n>KIDOT learns from unpaired data by modeling reconstruction as a continuous evolution path from measurements to images, guided by an imaging knowledge-informed cost function and transport equation.<n>Experiments on MRI and CT reconstruction demonstrate KIDOT's superior performance.
  arXiv  Detail & Related papers  (2025-05-23T09:05:10Z)
• Re-Visible Dual-Domain Self-Supervised Deep Unfolding Network for MRI Reconstruction [48.30341580103962]
  We propose a novel re-visible dual-domain self-supervised deep unfolding network to address these issues.<n>We design a deep unfolding network based on Chambolle and Pock Proximal Point Algorithm (DUN-CP-PPA) to achieve end-to-end reconstruction.<n> Experiments conducted on the fastMRI and IXI datasets demonstrate that our method significantly outperforms state-of-the-art approaches in terms of reconstruction performance.
  arXiv  Detail & Related papers  (2025-01-07T12:29:32Z)
• Phy-Diff: Physics-guided Hourglass Diffusion Model for Diffusion MRI Synthesis [45.074243735766]
  We propose a physics-guided diffusion model to generate high-quality dMRI. Our model introduces the physical principles of dMRI in the noise evolution in the diffusion process. Our experiment results show that our method outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-06-05T07:09:19Z)
• DPER: Diffusion Prior Driven Neural Representation for Limited Angle and Sparse View CT Reconstruction [45.00528216648563]
  Diffusion Prior Driven Neural Representation (DPER) is an unsupervised framework designed to address the exceptionally ill-posed CT reconstruction inverse problems. DPER adopts the Half Quadratic Splitting (HQS) algorithm to decompose the inverse problem into data fidelity and distribution prior sub-problems. We conduct comprehensive experiments to evaluate the performance of DPER on LACT and ultra-SVCT reconstruction with two public datasets.
  arXiv  Detail & Related papers  (2024-04-27T12:55:13Z)
• Double-Flow GAN model for the reconstruction of perceived faces from brain activities [13.707575848841405]
  We proposed a novel reconstruction framework, which we called Double-Flow GAN.<n>We also designed a pretraining process that uses features extracted from images as conditions for making it possible to pretrain the conditional reconstruction model from fMRI.<n>Results showed that the proposed method is significant at accurately reconstructing multiple face attributes, outperforms the previous reconstruction models, and exhibited state-of-the-art reconstruction abilities.
  arXiv  Detail & Related papers  (2023-12-12T18:07:57Z)
• Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models [75.52575380824051]
  We present a learning method to optimize sub-sampling patterns for compressed sensing multi-coil MRI. We use a single-step reconstruction based on the posterior mean estimate given by the diffusion model and the MRI measurement process. Our method requires as few as five training images to learn effective sampling patterns.
  arXiv  Detail & Related papers  (2023-06-05T22:09:06Z)
• Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution Reconstruction [68.80715727288514]
  We show how to unfold an iterative MGDUN algorithm into a novel model-guided deep unfolding network by taking the MRI observation matrix. In this paper, we propose a novel Model-Guided interpretable Deep Unfolding Network (MGDUN) for medical image SR reconstruction.
  arXiv  Detail & Related papers  (2022-09-15T03:58:30Z)
• A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstruction [50.1787181309337]
  We propose a convolutional long short-term memory (Conv-LSTM) based recurrent neural network (RNN), or ConvLR, to reconstruct interventional images with golden-angle radial sampling. The proposed algorithm has the potential to achieve real-time i-MRI for DBS and can be used for general purpose MR-guided intervention.
  arXiv  Detail & Related papers  (2022-03-28T14:03:45Z)
• MRI Reconstruction Using Deep Energy-Based Model [21.748514538109173]
  We propose a novel regularization strategy to take advantage of self-adversarial cogitation of the deep energy-based model. In contrast to other generative models for reconstruction, the proposed method utilizes deep energy-based information as the image prior in reconstruction to improve the quality of image.
  arXiv  Detail & Related papers  (2021-09-07T05:24:55Z)

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.