MEDL‐Net: A model‐based neural network for MRI reconstruction with enhanced deep learned regularizers

• Published in: Magnetic resonance in medicine Vol. 89; no. 5; pp. 2062 - 2075
• Main Authors: Qiao, Xiaoyu, Huang, Yuping, Li, Weisheng
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.05.2023
• Subjects: Acceleration; Algorithms; compressed sensing; deep learning; Image Processing, Computer-Assisted - methods; Image reconstruction; Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; model based; MRI reconstruction; Neural networks; Neural Networks, Computer; Optimization; Performance evaluation; deep learning; compressed sensing; model based; MRI reconstruction
• ISSN: 0740-3194; 1522-2594
• DOI: 10.1002/mrm.29575

Purpose To improve the MRI reconstruction performance of model‐based networks and to alleviate their large demand for GPU memory. Methods A model‐based neural network with enhanced deep learned regularizers (MEDL‐Net) was proposed. The MEDL‐Net is separated into several submodules, each of which consists of several cascades to mimic the optimization steps in conventional MRI reconstruction algorithms. Information from shallow cascades is densely connected to latter ones to enrich their inputs in each submodule, and additional revising blocks (RB) are stacked at the end of the submodules to bring more flexibility. Moreover, a composition loss function was designed to explicitly supervise RBs. Results Network performance was evaluated on a publicly available dataset. The MEDL‐Net quantitatively outperforms the state‐of‐the‐art methods on different MR image sequences with different acceleration rates (four‐fold and six‐fold). Moreover, the reconstructed images showed that the detailed textures are better preserved. In addition, fewer cascades are required when achieving the same reconstruction results compared with other model‐based networks. Conclusion In this study, a more efficient model‐based deep network was proposed to reconstruct MR images. The experimental results indicate that the proposed method improves reconstruction performance with fewer cascades, which alleviates the large demand for GPU memory.