# Beyond Training from Scratch: Foundation Models for Data-Efficient and Generalizable Cardiac MRI Reconstruction

arXiv: https://arxiv.org/abs/2610.08109 · HTML: https://mlsanity.com/paper/2610.08109/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 12 of 12)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [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)
- [Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity](https://mlsanity.com/paper/2305.08252/) (2023)
- [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)
- [LORAKI: Autocalibrated Recurrent Neural Networks for Autoregressive MRI Reconstruction in k-Space](https://mlsanity.com/paper/1904.09390/) (2019)
- [CMRxRecon: An open cardiac MRI dataset for the competition of accelerated image reconstruction](https://mlsanity.com/paper/2309.10836/) (2023)
- [Less Could Be Better: Parameter-efficient Fine-tuning Advances Medical Vision Foundation Models](https://mlsanity.com/paper/2401.12215/) (2024)
- [One-shot Localization and Segmentation of Medical Images with Foundation Models](https://mlsanity.com/paper/2310.18642/) (2023)
- [Reference-based Magnetic Resonance Image Reconstruction Using Texture Transformer](https://mlsanity.com/paper/2111.09492/) (2021)

## Abstract (arXiv)

Cardiac magnetic resonance imaging reconstruction aims to recover high-quality images from undersampled acquisitions, enabling faster scans while preserving diagnostic fidelity. Recent reconstruction methods are typically trained from scratch and often require large amounts of task-specific data, limiting their robustness under data scarcity and distribution shifts. In this work, we investigate whether pretrained vision foundation models can serve as effective priors for accelerated cardiac MRI reconstruction. We propose a reconstruction framework that integrates frozen and parameter-efficiently adapted visual encoders, including CLIP, BiomedCLIP, and DINOv2, within a transformer-based reconstruction architecture. Extensive experiments on the CMRxRecon2023 and CMRxRecon2024 benchmarks demonstrate that pretrained representations consistently outperform a transformer trained from scratch across multiple acceleration factors. We further evaluate performance under limited supervision and cross-dataset transfer, showing that foundation models provide superior data efficiency and generalization. While frozen representations are particularly effective in extreme low-data regimes, Low-Rank Adaptation (LoRA) yields additional gains when moderate amounts of training data are available. Among the evaluated backbones, DINOv2 achieves the strongest overall performance. These findings highlight the potential of vision foundation models as robust and transferable priors for cardiac MRI reconstruction.