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

2025-08-18

AI Summary

To address domain shift in multi-center cardiac MRI reconstruction caused by heterogeneous scanner configurations and imaging protocols, this paper proposes a hierarchical feature adaptation framework. Built upon a variational unrolling network, it introduces three complementary adapters—protocol-level, site-level, and universal—to disentangle sequence-specific, site-specific, and cross-site invariant biases, respectively. The method incorporates multi-scale structural similarity (SSIM) loss, frequency-domain enhancement, and contrast-adaptive weighting, while leveraging parameter-efficient fine-tuning for lightweight deployment. Evaluated on the CMRxRecon2025 benchmark—encompassing data from over five clinical sites, ten scanner models, and nine acquisition modalities—the approach significantly outperforms existing methods. It achieves state-of-the-art reconstruction fidelity and, for the first time, demonstrates zero-shot generalization to unseen clinical sites, markedly improving cross-site robustness and clinical deployability.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

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

Problem

• Addresses domain shift in multi-center cardiac MRI reconstruction
• Uses hierarchical adapters for protocol and scanner variations
• Enables generalization to unseen centers via invariant adaptations

Innovation

• Hierarchical feature adaptation for MRI reconstruction
• Parameter-efficient Protocol and Center-Level Adapters
• Universal Adapter for unseen center generalization