An unsupervised method for MRI recovery: Deep image prior with structured sparsity

TL;DR

This paper introduces DISCUS, an unsupervised MRI reconstruction method that leverages deep image prior with structured sparsity, outperforming existing techniques in quality without needing fully sampled data.

Contribution

The paper presents DISCUS, a novel unsupervised MRI reconstruction approach that incorporates structured sparsity into deep image prior, enabling effective recovery from undersampled data.

Findings

DISCUS outperforms competing methods in simulated and real data

DISCUS achieves higher NMSE and SSIM scores

Expert assessments favor DISCUS reconstructions

Abstract

Objective: To propose and validate an unsupervised MRI reconstruction method that does not require fully sampled k-space data. Materials and Methods: The proposed method, deep image prior with structured sparsity (DISCUS), extends the deep image prior (DIP) by introducing group sparsity to frame-specific code vectors, enabling the discovery of a low-dimensional manifold for capturing temporal variations. \discus was validated using four studies: (I) simulation of a dynamic Shepp-Logan phantom to demonstrate its manifold discovery capabilities, (II) comparison with compressed sensing and DIP-based methods using simulated single-shot late gadolinium enhancement (LGE) image series from six distinct digital cardiac phantoms in terms of normalized mean square error (NMSE) and structural similarity index measure (SSIM), (III) evaluation on retrospectively undersampled single-shot LGE data from eight patients, and (IV) evaluation on prospectively undersampled single-shot LGE data from eight patients, assessed via blind scoring from two expert readers. Results: DISCUS outperformed competing methods, demonstrating superior reconstruction quality in terms of NMSE and SSIM (Studies I--III) and expert reader scoring (Study IV). Discussion: An unsupervised image reconstruction method is presented and validated on simulated and measured data. These developments can benefit applications where acquiring fully sampled data is challenging.