Physics-Guided Dual-Domain Network with Attention-Based Fusion for Portable MRI Reconstruction
Abstract
Portable low-field magnetic resonance imaging (MRI) systems have gained renewed interest owing to their cost effectiveness and point-of-care imaging capabilities. Yet, portable MRI systems suffer from relatively low signal-to-noise ratio and limited hardware capabilities. While previous works have proposed the use of deep learning based reconstruction methods to improve low-field image quality, these operated only in the image-domain. Unlike other imaging modalities, MRI directly acquires data in the Fourier-domain (k-space), and exploiting both k-space and image-domain information can improve reconstruction quality. Here, we introduce DUN-DD, a novel physics-guided 3D network for portable MRI reconstruction, with parallel dual-domain branches whose outputs are combined together via an attention-based fusion network. To demonstrate the performance of the proposed method, we present \textit{in vivo} reconstructions obtained from both emulated datasets as well as images acquired with a 47mT Halbach-based portable MRI system. Our results show that DUN-DD outperforms state-of-the-art classical, data-driven, and physics-guided methods on both emulated and real portable MRI acquisitions.
Cite
@article{arxiv.2602.19829,
title = {Physics-Guided Dual-Domain Network with Attention-Based Fusion for Portable MRI Reconstruction},
author = {Efe Ilıcak and Baris Imre and Chloé Najac and Ruben van den Broek and Beatrice Lena and Andrew Webb and Marius Staring},
journal= {arXiv preprint arXiv:2602.19829},
year = {2026}
}
Comments
Accepted to 2026 IEEE International Symposium on Biomedical Imaging (ISBI). Copyright 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses