Nonlinear dipole inversion (NDI) enables robust quantitative susceptibility mapping (QSM).,NMR in Biomedicine

当前位置： X-MOL 学术 › NMR Biomed. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Nonlinear dipole inversion (NDI) enables robust quantitative susceptibility mapping (QSM).
NMR in Biomedicine ( IF 2.7 ) Pub Date : 2020-02-20 , DOI: 10.1002/nbm.4271
Daniel Polak _{1,

2,

3} , Itthi Chatnuntawech ₄ , Jaeyeon Yoon ₅ , Siddharth Srinivasan Iyer _{2,

6} , Carlos Milovic ₇ , Jongho Lee ₅ , Peter Bachert _{1,

8} , Elfar Adalsteinsson ₆ , Kawin Setsompop _{2,

9,

10} , Berkin Bilgic _{2,

9,

10}

Affiliation

Department of Physics and Astronomy, Heidelberg University, Heidelberg, Germany.
Department of Radiology, A. A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA.
Siemens Healthcare GmbH, Erlangen, Germany.
National Science and Technology Development Agency, National Nanotechnology Center, Pathum Thani, Thailand.
Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea.
Department of Electronical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
Department of Electrical Engineering, Pontificia Universidad Catolica de Chile, Santiago, Chile.
Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany.
Harvard Medical School, Boston, Massachusetts, USA.
Harvard-MIT Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.

High‐quality Quantitative Susceptibility Mapping (QSM) with Nonlinear Dipole Inversion (NDI) is developed with pre‐determined regularization while matching the image quality of state‐of‐the‐art reconstruction techniques and avoiding over‐smoothing that these techniques often suffer from. NDI is flexible enough to allow for reconstruction from an arbitrary number of head orientations and outperforms COSMOS even when using as few as 1‐direction data. This is made possible by a nonlinear forward‐model that uses the magnitude as an effective prior, for which we derived a simple gradient descent update rule. We synergistically combine this physics‐model with a Variational Network (VN) to leverage the power of deep learning in the VaNDI algorithm. This technique adopts the simple gradient descent rule from NDI and learns the network parameters during training, hence requires no additional parameter tuning. Further, we evaluate NDI at 7 T using highly accelerated Wave‐CAIPI acquisitions at 0.5 mm isotropic resolution and demonstrate high‐quality QSM from as few as 2‐direction data.

中文翻译：

非线性偶极子反演 (NDI) 可实现稳健的定量磁化率绘图 (QSM)。

具有非线性偶极子反演 (NDI) 的高质量定量磁化率绘图 (QSM) 是通过预先确定的正则化开发的，同时匹配最先进的重建技术的图像质量，并避免这些技术经常遇到的过度平滑问题。 NDI 足够灵活，可以从任意数量的头部方向进行重建，即使使用少至 1 方向的数据，其性能也优于 COSMOS。这是通过非线性前向模型实现的，该模型使用幅度作为有效先验，为此我们导出了一个简单的梯度下降更新规则。我们将此物理模型与变分网络 (VN) 协同结合，以利用 VaNDI 算法中深度学习的力量。该技术采用 NDI 的简单梯度下降规则，并在训练过程中学习网络参数，因此不需要额外的参数调整。此外，我们使用高度加速的 Wave-CAIPI 采集以 0.5 mm 各向同性分辨率评估 7 T 下的 NDI，并从少至 2 方向的数据证明了高质量的 QSM。

更新日期：2020-02-20

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11