Skip to main content
QUICK REVIEW

[论文解读] A Theoretically Guaranteed Deep Optimization Framework for Robust Compressive Sensing MRI

Risheng Liu, Yuxi Zhang|arXiv (Cornell University)|Nov 9, 2018
Advanced MRI Techniques and Applications参考文献 1被引用 4
一句话总结

该论文提出了一种理论保证的深度优化框架,用于鲁棒压缩感知磁共振成像(MRI),通过将设计的数值求解器与数据驱动架构相结合,利用最优条件检查机制确保收敛性,并显式建模Rician噪声以提升真实场景下的鲁棒性。该方法在高度欠采样的k空间数据下实现了最先进的重建精度、效率和抗噪能力。

ABSTRACT

Magnetic Resonance Imaging (MRI) is one of the most dynamic and safe imaging techniques available for clinical applications. However, the rather slow speed of MRI acquisitions limits the patient throughput and potential indi cations. Compressive Sensing (CS) has proven to be an efficient technique for accelerating MRI acquisition. The most widely used CS-MRI model, founded on the premise of reconstructing an image from an incompletely filled k-space, leads to an ill-posed inverse problem. In the past years, lots of efforts have been made to efficiently optimize the CS-MRI model. Inspired by deep learning techniques, some preliminary works have tried to incorporate deep architectures into CS-MRI process. Unfortunately, the convergence issues (due to the experience-based networks) and the robustness (i.e., lack real-world noise modeling) of these deeply trained optimization methods are still missing. In this work, we develop a new paradigm to integrate designed numerical solvers and the data-driven architectures for CS-MRI. By introducing an optimal condition checking mechanism, we can successfully prove the convergence of our established deep CS-MRI optimization scheme. Furthermore, we explicitly formulate the Rician noise distributions within our framework and obtain an extended CS-MRI network to handle the real-world nosies in the MRI process. Extensive experimental results verify that the proposed paradigm outperforms the existing state-of-the-art techniques both in reconstruction accuracy and efficiency as well as robustness to noises in real scene.

研究动机与目标

  • 解决基于深度学习的压缩感知MRI方法中因采用经验驱动架构而导致的理论收敛性保证缺失问题。
  • 通过在优化框架中显式建模噪声分布,提升对真实MRI采集中Rician噪声的鲁棒性。
  • 统一基于模型的数值求解器与数据驱动的深度架构,以提升重建性能。
  • 基于Kurdyka-Łojasiewicz(KŁ)性质与最优条件检查,建立非凸稀疏恢复在压缩感知MRI中的收敛性证明深度优化方案。

提出的方法

  • 在展开优化框架中,将设计的数值求解器(基于邻近梯度法)与可学习的深度架构相结合。
  • 采用最优条件检查机制,确保深度优化方案的理论收敛性。
  • 在数据保真项中显式建模Rician噪声,以提升对真实MRI采集噪声的鲁棒性。
  • 利用Kurdyka-Łojasiewicz(KŁ)不等式证明迭代算法序列的收敛性,建立理论保证。
  • 在稀疏编码域中采用非凸ℓp正则化(p ∈ (0,1))以促进稀疏性。
  • 将优化迭代过程展开为具有可学习参数的深度网络,同时通过解析约束保持收敛性。

实验结果

研究问题

  • RQ1能否设计一种具有理论收敛性保证的CS-MRI深度优化框架?
  • RQ2如何在深度CS-MRI框架中显式建模真实MRI采集中的Rician噪声,以提升鲁棒性?
  • RQ3基于模型的求解器与数据驱动架构的融合能否在重建质量和效率方面超越现有最先进方法?
  • RQ4使用非凸ℓp正则化(p ∈ (0,1))对深度CS-MRI中的重建精度和收敛性有何影响?

主要发现

  • 通过最优条件检查和KŁ性质,所提出的框架实现了深度优化方案的理论收敛性,解决了先前展开网络的关键局限性。
  • 显式建模Rician噪声显著提升了对真实世界MRI数据噪声的鲁棒性,优于忽略或近似噪声的方法。
  • 该方法在重建精度和计算效率方面均优于现有最先进的CS-MRI技术,尤其在高欠采样率下表现更优。
  • 在多种采样模式(笛卡尔、径向、高斯)上的大量实验表明,该方法在不同k空间采样方案下均保持一致的优越性。
  • 收敛性分析证明,迭代序列是柯西序列,因此收敛,验证了所提深度优化框架的稳定性。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。