To improve the compressive sensing MRI (CS-MRI) approaches in terms of fine structure loss under high acceleration factors, we have proposed an iterative feature refinement model (IFR-CS), equipped with fixed transforms, to restore the meaningful structures and details. Nevertheless, the proposed IFR-CS still has some limitations, such as the selection of hyper-parameters, a lengthy reconstruction time, and the fixed sparsifying transform. To alleviate these issues, we unroll the iterative feature refinement procedures in IFR-CS to a supervised model-driven network, dubbed IFR-Net. Equipped with training data pairs, both regularization parameter and the utmost feature refinement operator in IFR-CS become trainable. Additionally, inspired by the powerful representation capability of convolutional neural network (CNN), CNN-based inversion blocks are explored in the sparsity-promoting denoising module to generalize the sparsity-enforcing operator. Extensive experiments on both simulated and in vivo MR datasets have shown that the proposed network possesses a strong capability to capture image details and preserve well the structural information with fast reconstruction speed.

中文翻译：

---

IFR-Net：用于压缩传感 MRI 的迭代特征细化网络

为了在高加速因子下改善压缩传感 MRI (CS-MRI) 方法的精细结构损失，我们提出了一种迭代特征细化模型 (IFR-CS)，配备固定变换，以恢复有意义的结构和细节。尽管如此，所提出的 IFR-CS 仍然存在一些局限性，例如超参数的选择、较长的重建时间和固定的稀疏变换。为了缓解这些问题，我们将 IFR-CS 中的迭代特征细化过程展开到一个监督模型驱动的网络，称为 IFR-Net。配备训练数据对，IFR-CS 中的正则化参数和最大特征细化算子都可以训练。此外，受卷积神经网络（CNN）强大的表征能力启发，在稀疏促进去噪模块中探索了基于 CNN 的反演块，以推广稀疏执行算子。对模拟和体内 MR 数据集的大量实验表明，所提出的网络具有很强的捕获图像细节的能力，并能以快速的重建速度很好地保留结构信息。