# HierAdaptMR: Cross-Center Cardiac MRI Reconstruction with Hierarchical Feature Adapters

arXiv: https://arxiv.org/abs/2508.13026 · HTML: https://mlsanity.com/paper/2508.13026/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 18 Aug 2025.

## Builds on (most cited first, 9 of 9)

- [Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction](https://mlsanity.com/paper/1712.01751/) (2017)
- [Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction](https://mlsanity.com/paper/2309.13839/) (2023)
- [Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI](https://mlsanity.com/paper/2403.10064/) (2024)
- [Complementary Time-Frequency Domain Networks for Dynamic Parallel MR Image Reconstruction](https://mlsanity.com/paper/2012.11974/) (2020)
- [Towards Modality- and Sampling-Universal Learning Strategies for Accelerating Cardiovascular Imaging: Summary of the CMRxRecon2024 Challenge](https://mlsanity.com/paper/2503.03971/) (2025)
- [Statistical Distance-Guided Unsupervised Domain Adaptation for Automated Multi-Class Cardiovascular Magnetic Resonance Image Quality Assessment](https://mlsanity.com/paper/2409.00375/) (2024)
- [HyperCMR: Enhanced Multi-Contrast CMR Reconstruction with Eagle Loss](https://mlsanity.com/paper/2410.03624/) (2024)
- [An All-in-one Approach for Accelerated Cardiac MRI Reconstruction](https://mlsanity.com/paper/2411.10787/) (2024)
- [UPCMR: A Universal Prompt-guided Model for Random Sampling Cardiac MRI Reconstruction](https://mlsanity.com/paper/2502.14899/) (2025)

## Built on by (most cited first, 1 of 1)

- [SDUM: A Scalable Deep Unrolled Model for Universal MRI Reconstruction](https://mlsanity.com/paper/2512.17137/) (2025)

## Abstract (arXiv)

Deep learning-based cardiac MRI reconstruction faces significant domain shift challenges when deployed across multiple clinical centers with heterogeneous scanner configurations and imaging protocols. We propose HierAdaptMR, a hierarchical feature adaptation framework that addresses multi-level domain variations through parameter-efficient adapters. Our method employs Protocol-Level Adapters for sequence-specific characteristics and Center-Level Adapters for scanner-dependent variations, built upon a variational unrolling backbone. A Universal Adapter enables generalization to entirely unseen centers through stochastic training that learns center-invariant adaptations. The framework utilizes multi-scale SSIM loss with frequency domain enhancement and contrast-adaptive weighting for robust optimization. Comprehensive evaluation on the CMRxRecon2025 dataset spanning 5+ centers, 10+ scanners, and 9 modalities demonstrates superior cross-center generalization while maintaining reconstruction quality. code: https://github.com/Ruru-Xu/HierAdaptMR