训练神经网络进行扩散 MRI 中的 Gibbs 噪声和噪声去除。
Training a neural network for Gibbs and noise removal in diffusion MRI.
机构信息
Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University School of Medicine, New York, NY, USA.
NYU Tandon School of Engineering, Brooklyn, NY, USA.
出版信息
Magn Reson Med. 2021 Jan;85(1):413-428. doi: 10.1002/mrm.28395. Epub 2020 Jul 14.
PURPOSE
To develop and evaluate a neural network-based method for Gibbs artifact and noise removal.
METHODS
A convolutional neural network (CNN) was designed for artifact removal in diffusion-weighted imaging data. Two implementations were considered: one for magnitude images and one for complex images. Both models were based on the same encoder-decoder structure and were trained by simulating MRI acquisitions on synthetic non-MRI images.
RESULTS
Both machine learning methods were able to mitigate artifacts in diffusion-weighted images and diffusion parameter maps. The CNN for complex images was also able to reduce artifacts in partial Fourier acquisitions.
CONCLUSIONS
The proposed CNNs extend the ability of artifact correction in diffusion MRI. The machine learning method described here can be applied on each imaging slice independently, allowing it to be used flexibly in clinical applications.
目的
开发并评估一种基于神经网络的方法，用于去除 Gibbs 伪影和噪声。
方法
设计了一种卷积神经网络（CNN），用于去除扩散加权成像数据中的伪影。考虑了两种实现方式：一种用于幅度图像，另一种用于复数图像。这两个模型都基于相同的编解码器结构，并通过在合成非 MRI 图像上模拟 MRI 采集来进行训练。
结果
两种机器学习方法都能够减轻扩散加权图像和扩散参数图中的伪影。复数图像的 CNN 还能够减少部分傅里叶采集的伪影。
结论
所提出的 CNN 扩展了扩散 MRI 中伪影校正的能力。这里描述的机器学习方法可以独立地应用于每个成像切片，使其在临床应用中具有灵活性。
Zotero 插件