Wu Xi, He Jin, Zhu Ming
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2014 Feb;31(1):7-12.
Because of the long acquisition time and spin-echo planar imaging sequence, diffusion weight magnetic resonance image (DWI) should be denoised effectively to ensure the follow-up applications. The commonly used denoising methods which induced from gray level image lack the use of the specific information from multiple magnitude directions. This paper, therefore, proposes a modified linear minimum mean square error (LMMSE) denosing method used for DWI. The proposed method uses the local information to estimate the parameter of the Rician noise and modifies the LMMSE using the information of multiple magnitude directions synthetically. The simulation and experiment of the synthetic DWI and real human brain DWI dataset demonstrate that the proposed method can more effectively remove the Rician noise compared to the commonly used denoising method and improve the robustness and validity of the diffusion tensor magnetic resonance image (DTI).
由于采集时间长以及自旋回波平面成像序列的原因，扩散加权磁共振图像（DWI）需要进行有效的去噪处理，以确保后续应用。从灰度图像衍生出的常用去噪方法缺乏对多幅度方向特定信息的利用。因此，本文提出一种用于DWI的改进线性最小均方误差（LMMSE）去噪方法。该方法利用局部信息估计莱斯噪声的参数，并综合多幅度方向的信息对LMMSE进行修正。对合成DWI和真实人脑DWI数据集的仿真与实验表明，与常用去噪方法相比，该方法能更有效地去除莱斯噪声，提高扩散张量磁共振图像（DTI）的鲁棒性和有效性。
