用深度神经网络从稀疏数据快速重建高分辨率磁共振弹性图，提升成像速度与质量。
Accelerated MR Elastography Using Learned Neural Network Representation
- 将神经网络视为线性子空间的非线性扩展，用于重构欠采样k空间数据
- 单次螺旋采集即可实现2mm各向同性分辨率，1分钟完成扫描（总加速因子R=10）
- 适合需要快速、高精度弹性成像的临床研究和科研人员
为实现从高度欠采样数据中快速获得高分辨率磁共振弹性成像（MRE），且无需高质量训练数据，本文将深度神经网络表示建模为线性子空间模型的非线性扩展，并用于从欠采样k空间数据中重建MRE图像重复。通过多层级k空间一致性损失学习网络权重，并引入相位对比特性的幅值与相位先验，包括解剖结构相似性和波诱导谐波位移的平滑性。在3D梯度回波螺旋和多切片自旋回波螺旋MRE数据集上进行实验。相比传统基于线性子空间的方法，该非线性网络表示方法可生成更优重建图像，有效抑制噪声与伪影，在单个平面内每重复仅需一个螺旋臂（如1分钟内实现2mm各向同性分辨率，总加速因子R=10），其刚度估计结果与全采样数据相当。本工作验证了利用深度网络表示从高度欠采样数据中建模与重建MRE图像的可行性，是对子空间方法的非线性拓展。
原文摘要 · Abstract (English)
To develop a deep-learning method for achieving fast high-resolution MR elastography from highly undersampled data without the need of high-quality training dataset. We first framed the deep neural network representation as a nonlinear extension of the linear subspace model, then used it to represent and reconstruct MRE image repetitions from undersampled k-space data. The network weights were learned using a multi-level k-space consistent loss. To further enhance reconstruction quality, phase-contrast specific magnitude and phase priors were incorporated, including the similarity of anatomical structures and smoothness of wave-induced harmonic displacement. Experiments were conducted using both 3D gradient-echo spiral and multi-slice spin-echo spiral MRE datasets. Compared to the conventional linear subspace-based approaches, the nonlinear network representation method was able to produce superior image reconstruction with suppressed noise and artifacts from a single in-plane spiral arm per MRE repetition (e.g., 2mm isotropic resolution in 1 min with a total R=10), yielding comparable stiffness estimation to the fully sampled data. This work demonstrated the feasibility of using deep network representations to model and reconstruct MRE images from highly-undersampled data, a nonlinear extension of the subspace-based approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。