Saved in:
Bibliographic Details
Main Authors: Xu, Ruru, Oksuz, Ilkay
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.13026
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918126595080192
author Xu, Ruru
Oksuz, Ilkay
author_facet Xu, Ruru
Oksuz, Ilkay
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2508_13026
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HierAdaptMR: Cross-Center Cardiac MRI Reconstruction with Hierarchical Feature Adapters
Xu, Ruru
Oksuz, Ilkay
Computer Vision and Pattern Recognition
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
title HierAdaptMR: Cross-Center Cardiac MRI Reconstruction with Hierarchical Feature Adapters
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.13026