IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRI

📄 arXiv: 2311.12892v1 📥 PDF

作者: Ruimin Feng, Qing Wu, Jie Feng, Huajun She, Chunlei Liu, Yuyao Zhang, Hongjiang Wei

分类: eess.IV, cs.CV, cs.LG, physics.med-ph

发布日期: 2023-11-21

💡 一句话要点

提出IMJENSE以解决并行MRI重建中的图像质量问题

🎯 匹配领域: 支柱三：空间感知与语义 (Perception & Semantics)

关键词: 并行成像 磁共振成像 隐式神经表示 图像重建 深度学习 医学成像 稀疏采样

📋 核心要点

  1. 现有的并行MRI重建算法在从高度稀疏的k空间测量中恢复高质量图像时面临挑战，尤其是在缺乏充分采样的真实数据时。
  2. IMJENSE通过将MRI图像和线圈灵敏度建模为连续函数，利用隐式神经表示直接从稀疏k空间测量中学习参数，避免了对全采样数据的依赖。
  3. 实验结果表明，IMJENSE在仅使用4或8个校准线的情况下，能够在5倍和6倍加速下稳定重建图像，显示出显著的性能提升。

📝 摘要（中文）

并行成像是一种加速磁共振成像（MRI）数据采集的常用技术。尽管现有重建算法取得了一定成功，但从高度稀疏的k空间测量中可靠重建高质量图像仍然具有挑战性。本文提出了IMJENSE，一种基于隐式神经表示的扫描特定方法，旨在改善并行MRI重建。该方法将MRI图像和线圈灵敏度建模为空间坐标的连续函数，通过神经网络和多项式进行参数化。IMJENSE在极少的校准数据下表现出更高的稳定性，能够在5倍和6倍加速下成功重建图像，显示出其在并行MRI数据采集中的潜力。

🔬 方法详解

问题定义：本文旨在解决并行MRI重建中从高度稀疏的k空间测量中可靠重建高质量图像的难题。现有方法在缺乏充分采样的真实数据时，重建效果往往不理想。

核心思路：IMJENSE的核心思想是利用隐式神经表示，将MRI图像和线圈灵敏度建模为空间坐标的连续函数。通过神经网络和多项式参数化，IMJENSE能够直接从稀疏的k空间测量中学习这些参数，避免了对全采样数据的需求。

技术框架：IMJENSE的整体架构包括两个主要模块：一是通过神经网络建模MRI图像，二是通过多项式建模线圈灵敏度。整个流程从稀疏k空间测量开始，经过参数学习，最终输出重建的MRI图像。

关键创新：IMJENSE的主要创新在于其扫描特定的隐式神经表示方法，能够同时进行MRI图像和线圈灵敏度的联合估计。这一方法与传统的图像或k空间域重建算法本质上不同，提供了更强的连续表示能力。

关键设计：在设计上，IMJENSE采用了特定的损失函数来优化网络权重和多项式系数，确保在极少的校准数据下仍能实现高质量的图像重建。网络结构方面，使用了深度神经网络以捕捉复杂的空间特征。

📊 实验亮点

实验结果显示，IMJENSE在仅使用4或8个校准线的情况下，成功重建了5倍和6倍加速下的MRI图像，分别对应22.0%和19.5%的欠采样率。与传统的深度学习方法相比，IMJENSE在极少校准数据下表现出更高的稳定性和图像质量。

🎯 应用场景

IMJENSE的研究成果在医学成像领域具有广泛的应用潜力，尤其是在需要快速成像的场景中，如急诊医学和动态成像。该方法的高效性和稳定性将推动并行MRI技术的进一步发展，提升临床诊断的效率和准确性。

📄 摘要（原文）

Parallel imaging is a commonly used technique to accelerate magnetic resonance imaging (MRI) data acquisition. Mathematically, parallel MRI reconstruction can be formulated as an inverse problem relating the sparsely sampled k-space measurements to the desired MRI image. Despite the success of many existing reconstruction algorithms, it remains a challenge to reliably reconstruct a high-quality image from highly reduced k-space measurements. Recently, implicit neural representation has emerged as a powerful paradigm to exploit the internal information and the physics of partially acquired data to generate the desired object. In this study, we introduced IMJENSE, a scan-specific implicit neural representation-based method for improving parallel MRI reconstruction. Specifically, the underlying MRI image and coil sensitivities were modeled as continuous functions of spatial coordinates, parameterized by neural networks and polynomials, respectively. The weights in the networks and coefficients in the polynomials were simultaneously learned directly from sparsely acquired k-space measurements, without fully sampled ground truth data for training. Benefiting from the powerful continuous representation and joint estimation of the MRI image and coil sensitivities, IMJENSE outperforms conventional image or k-space domain reconstruction algorithms. With extremely limited calibration data, IMJENSE is more stable than supervised calibrationless and calibration-based deep-learning methods. Results show that IMJENSE robustly reconstructs the images acquired at 5$\mathbf{\times}$ and 6$\mathbf{\times}$ accelerations with only 4 or 8 calibration lines in 2D Cartesian acquisitions, corresponding to 22.0% and 19.5% undersampling rates. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.