Sultan Muhammad Ahmad, Chen Chong, Liu Yingmin, Gil Katarzyna, Zareba Karolina, Ahmad Rizwan
Biomedical Engineering, Ohio State University, Columbus, OH, 43210, USA.
Electrical and Computer Engineering, The Ohio State University, Columbus, OH, 43210, USA.
MAGMA. 2025 May 15. doi: 10.1007/s10334-025-01257-z.
To propose and validate an unsupervised MRI reconstruction method that does not require fully sampled k-space data.
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.
DISCUS outperformed competing methods, demonstrating superior reconstruction quality in terms of NMSE and SSIM (Studies I-III) and expert reader scoring (Study IV).
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.
提出并验证一种无需全采样k空间数据的无监督MRI重建方法。
所提出的方法，即具有结构稀疏性的深度图像先验（DISCUS），通过将组稀疏性引入特定帧的编码向量来扩展深度图像先验（DIP），从而能够发现用于捕捉时间变化的低维流形。使用四项研究对DISCUS进行了验证：（I）对动态Shepp-Logan体模进行模拟以展示其流形发现能力，（II）使用来自六个不同数字心脏体模的模拟单激发延迟钆增强（LGE）图像序列，在归一化均方误差（NMSE）和结构相似性指数测量（SSIM）方面与基于压缩感知和DIP的方法进行比较，（III）对八名患者的回顾性欠采样单激发LGE数据进行评估，以及（IV）对八名患者的前瞻性欠采样单激发LGE数据进行评估，由两名专家读者进行盲法评分。
DISCUS优于竞争方法，在NMSE和SSIM方面（研究I - III）以及专家读者评分方面（研究IV）展示出卓越的重建质量。
提出了一种无监督图像重建方法，并在模拟和实测数据上进行了验证。这些进展可惠及获取全采样数据具有挑战性的应用。
