SubZero: Subspace Zero-Shot MRI Reconstruction

2023/11/28 by Yu, Heng, Arefeen, Yamin, Bilgic, Berkin
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2311.17251

Abstract

Recently introduced zero-shot self-supervised learning (ZS-SSL) has shown potential in accelerated MRI in a scan-specific scenario, which enabled high-quality reconstructions without access to a large training dataset. ZS-SSL has been further combined with the subspace model to accelerate 2D T2-shuffling acquisitions. In this work, we propose a parallel network framework and introduce an attention mechanism to improve subspace-based zero-shot self-supervised learning and enable higher acceleration factors. We name our method SubZero and demonstrate that it can achieve improved performance compared with current methods in T1 and T2 mapping acquisitions.

Related

• Dual-Domain Self-Supervised Learning for Accelerated Non-Cartesian MRI Reconstruction
• Self-Supervised Deep Active Accelerated MRI
• Self-Supervised Learning for MRI Reconstruction with a Parallel Network Training Framework
• SelfCoLearn: Self-supervised collaborative learning for accelerating dynamic MR imaging
• NLCG-Net: A Model-Based Zero-Shot Learning Framework for Undersampled Quantitative MRI Reconstruction