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

arXiv: https://arxiv.org/abs/2604.22557 · HTML: https://mlsanity.com/paper/2604.22557/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 41 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [Deep Learning Techniques for Inverse Problems in Imaging](https://mlsanity.com/paper/2005.06001/) (2020)
- [End-to-End Variational Networks for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2004.06688/) (2020)
- [From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models](https://mlsanity.com/paper/2310.08825/) (2023)
- [What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factors](https://mlsanity.com/paper/2203.01825/) (2022)
- [Are Natural Domain Foundation Models Useful for Medical Image Classification?](https://mlsanity.com/paper/2310.19522/) (2023)
- [CLIP in Medical Imaging: A Survey](https://mlsanity.com/paper/2312.07353/) (2023)
- [Depthwise Convolution is All You Need for Learning Multiple Visual Domains](https://mlsanity.com/paper/1902.00927/) (2019)
- [Recurrent Variational Network: A Deep Learning Inverse Problem Solver applied to the task of Accelerated MRI Reconstruction](https://mlsanity.com/paper/2111.09639/) (2021)
- [Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks](https://mlsanity.com/paper/2312.02366/) (2023)
- [HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction](https://mlsanity.com/paper/2203.08213/) (2022)
- [CMRxRecon: An open cardiac MRI dataset for the competition of accelerated image reconstruction](https://mlsanity.com/paper/2309.10836/) (2023)
- [Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction](https://mlsanity.com/paper/2309.13839/) (2023)
- [The state-of-the-art in Cardiac MRI Reconstruction: Results of the CMRxRecon Challenge in MICCAI 2023](https://mlsanity.com/paper/2404.01082/) (2024)
- [One-shot Localization and Segmentation of Medical Images with Foundation Models](https://mlsanity.com/paper/2310.18642/) (2023)
- [Data or Language Supervision: What Makes CLIP Better than DINO?](https://mlsanity.com/paper/2510.11835/) (2025)
- [Pretrained ViTs Yield Versatile Representations For Medical Images](https://mlsanity.com/paper/2303.07034/) (2023)
- [General Purpose Image Encoder DINOv2 for Medical Image Registration](https://mlsanity.com/paper/2402.15687/) (2024)
- [Navigating Data Scarcity using Foundation Models: A Benchmark of Few-Shot and Zero-Shot Learning Approaches in Medical Imaging](https://mlsanity.com/paper/2408.08058/) (2024)
- [Do Vision Foundation Models Enhance Domain Generalization in Medical Image Segmentation?](https://mlsanity.com/paper/2409.07960/) (2024)
- [Zero-shot Domain Generalization of Foundational Models for 3D Medical Image Segmentation: An Experimental Study](https://mlsanity.com/paper/2503.22862/) (2025)

## Abstract (arXiv)

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.