Following their success in numerous imaging and computer vision applications, deep-learning (DL) techniques have emerged as one of the most prominent strategies for accelerated MRI reconstruction. These methods have been shown to outperform conventional regularized methods based on compressed sensing (CS). However, in most comparisons, CS is implemented with two or three hand-tuned parameters, while DL methods enjoy a plethora of advanced data science tools. In this work, we revisit ℓ 1 -wavelet CS reconstruction using these modern tools. Using ideas such as algorithm unrolling and advanced optimization methods over large databases that DL algorithms utilize, along with conventional insights from wavelet representations and CS theory, we show that ℓ 1 -wavelet CS can be fine-tuned to a level close to DL reconstruction for accelerated MRI. The optimized ℓ 1 -wavelet CS method uses only 128 parameters compared to >500,000 for DL, employs a convex reconstruction at inference time, and performs within <1% of a DL approach that has been used in multiple studies in terms of quantitative quality metrics.

中文翻译：

---

在深度学习时代重温 ℓ1-小波压缩感知 MRI

在众多成像和计算机视觉应用中取得成功之后，深度学习 (DL) 技术已成为加速 MRI 重建的最突出策略之一。这些方法已被证明优于基于压缩感知 (CS) 的传统正则化方法。然而，在大多数比较中，CS 是通过两个或三个手动调整参数实现的，而 DL 方法则享有大量高级数据科学工具。在这项工作中，我们重新审视 ℓ 1个 -使用这些现代工具的小波 CS 重建。使用 DL 算法利用的大型数据库上的算法展开和高级优化方法等思想，以及小波表示和 CS 理论的传统见解，我们表明 ℓ 1个 -小波 CS 可以微调到接近 DL 重建的水平，以加速 MRI。优化的 ℓ 1个 -wavelet CS 方法仅使用 128 个参数，而 DL 则使用 >500,000 个参数，在推理时采用凸重建，并且在定量质量指标方面已在多项研究中使用的 DL 方法的执行范围小于 1%。