Department of Electronic Information Engineering, Nanchang University, Nanchang 330031, China.
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 518055, China.
Magn Reson Imaging. 2020 Sep;71:55-68. doi: 10.1016/j.mri.2020.04.006. Epub 2020 Apr 27.
Magnetic Resonance (MR) images often suffer from noise pollution during image acquisition and transmission, which limits the accuracy of quantitative measurements from the data. Noise in magnitude MR images is usually governed by Rician distribution, due to the existence of uncorrelated Gaussian noise with zero-mean and equal variance in both the real and imaginary parts of the complex K-space data. Different from the existing MRI denoising methods that utilizing the spatial neighbor information around the pixels or patches, this work turns to capture the pixel-level distribution information by means of supervised network learning. A progressive network learning strategy is proposed via fitting the distribution of pixel-level and feature-level intensities. The proposed network consists of two residual blocks, one is used for fitting pixel domain without batch normalization layer and another one is applied for matching feature domain with batch normalization layer. Experimental results under synthetic, complex-valued and clinical MR brain images demonstrate great potential of the proposed network with substantially improved quantitative measures and visual inspections.
磁共振（MR）图像在采集和传输过程中经常受到噪声污染，这限制了数据定量测量的准确性。由于实部和虚部的复 K 空间数据中存在不相关的零均值和等方差的高斯噪声，因此幅度 MR 图像中的噪声通常由 Rician 分布控制。与利用像素或块周围的空间邻域信息的现有 MRI 去噪方法不同，这项工作通过有监督的网络学习来捕获像素级别的分布信息。通过拟合像素级和特征级强度的分布，提出了一种渐进式网络学习策略。所提出的网络由两个残差块组成，一个用于拟合无批量归一化层的像素域，另一个用于匹配具有批量归一化层的特征域。在合成、复数和临床 MR 脑图像下的实验结果表明，该网络具有很大的潜力，可以显著提高定量测量和视觉检查的效果。
