Dual-Domain Self-Supervised Learning for Accelerated Non-Cartesian MRI Reconstruction

TL;DR

This paper introduces a fully self-supervised method for accelerated non-Cartesian MRI reconstruction that does not require fully sampled data, enabling high-quality images from undersampled data, including challenging low-field clinical MRI scans.

Contribution

The proposed DDSS method is the first to leverage self-supervision in both k-space and image domains for non-Cartesian MRI reconstruction without fully sampled data.

Findings

High-quality reconstructions approaching supervised accuracy

Outperforms previous baseline methods

Effective on real-world low-field MRI data

Abstract

While enabling accelerated acquisition and improved reconstruction accuracy, current deep MRI reconstruction networks are typically supervised, require fully sampled data, and are limited to Cartesian sampling patterns. These factors limit their practical adoption as fully-sampled MRI is prohibitively time-consuming to acquire clinically. Further, non-Cartesian sampling patterns are particularly desirable as they are more amenable to acceleration and show improved motion robustness. To this end, we present a fully self-supervised approach for accelerated non-Cartesian MRI reconstruction which leverages self-supervision in both k-space and image domains. In training, the undersampled data are split into disjoint k-space domain partitions. For the k-space self-supervision, we train a network to reconstruct the input undersampled data from both the disjoint partitions and from itself. For the image-level self-supervision, we enforce appearance consistency obtained from the original undersampled data and the two partitions. Experimental results on our simulated multi-coil non-Cartesian MRI dataset demonstrate that DDSS can generate high-quality reconstruction that approaches the accuracy of the fully supervised reconstruction, outperforming previous baseline methods. Finally, DDSS is shown to scale to highly challenging real-world clinical MRI reconstruction acquired on a portable low-field (0.064 T) MRI scanner with no data available for supervised training while demonstrating improved image quality as compared to traditional reconstruction, as determined by a radiologist study.