@inproceedings{Zhang:2026:10.1007/978-3-032-09513-8_10,
author = {Zhang, H and Huang, J and Wu, Y and Dai, C and Wang, F and Zhang, Z and Yang, G},
doi = {10.1007/978-3-032-09513-8_10},
pages = {95--105},
title = {Lightweight Hypercomplex MRI Reconstruction: A Generalized Kronecker-Parameterized Approach},
url = {http://dx.doi.org/10.1007/978-3-032-09513-8_10},
year = {2026}
}

Download

TY  - CPAPER
AB  - Magnetic Resonance Imaging (MRI) is crucial for clinical diagnostics but is hindered by prolonged scan times. Current deep learning models enhance MRI reconstruction but are often memory-intensive and unsuitable for resource-limited systems. This paper introduces a lightweight MRI reconstruction model leveraging Kronecker-Parameterized Hypercomplex Neural Networks to achieve high performance with reduced parameters. By integrating Kronecker-based modules, including Kronecker MLP, Kronecker Window Attention, and Kronecker Convolution, the proposed model efficiently extracts spatial features while preserving representational power. We introduce Kronecker U-Net and Kronecker SwinMR, which maintain high reconstruction quality with approximately 50% fewer parameters compared to existing models. Experimental evaluation on the FastMRI dataset demonstrates competitive PSNR, SSIM, and LPIPS metrics, even at high acceleration factors (8× and 16×), with no significant performance drop. Additionally, Kronecker variants exhibit superior generalization and reduced overfitting on limited datasets, facilitating efficient MRI reconstruction on hardware-constrained systems. This approach sets a new benchmark for parameter-efficient medical imaging models. Code is available at:https://github.com/Whethe/HyperKron-MRI-Recon.
AU  - Zhang,H
AU  - Huang,J
AU  - Wu,Y
AU  - Dai,C
AU  - Wang,F
AU  - Zhang,Z
AU  - Yang,G
DO  - 10.1007/978-3-032-09513-8_10
EP  - 105
PY  - 2026///
SN  - 0302-9743
SP  - 95
TI  - Lightweight Hypercomplex MRI Reconstruction: A Generalized Kronecker-Parameterized Approach
UR  - http://dx.doi.org/10.1007/978-3-032-09513-8_10
ER  - 

Download