An unsupervised method for MRI recovery: Deep image prior with structured sparsity
arXiv:2501.01482 · doi:10.1007/s10334-025-01257-z
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.
Magn Reson Mater Phy (2025)
References in corpus (10)
- MoDL: Model Based Deep Learning Architecture for Inverse Problems
- Deep learning for undersampled MRI reconstruction
- Plug and play methods for magnetic resonance imaging (long version)
- Low-rank and Adaptive Sparse Signal (LASSI) Models for Highly Accelerated Dynamic Imaging
- Analytical model for the approximation of hysteresis loop and its application to the scanning tunneling microscope
- Attention-aware non-rigid image registration for accelerated MR imaging
- Dynamic imaging using Motion-Compensated SmooThness Regularization on Manifolds (MoCo-SToRM)
- Technical Report (v1.0)--Pseudo-random Cartesian Sampling for Dynamic MRI
- Surface Coil Intensity Correction for MRI
- Deep Image prior with StruCtUred Sparsity (DISCUS) for dynamic MRI reconstruction