Chen Geng, Zhang Pei, Wu Yafeng, Shen Dinggang, Yap Pew-Thian
Data Processing Center, Northwestern Polytechnical University, Xi'an, China; Department of Radiology and Biomedical Research Imaging Center (BRIC) University of North Carolina at Chapel Hill, NC, U.S.A.
Department of Radiology and Biomedical Research Imaging Center (BRIC) University of North Carolina at Chapel Hill, NC, U.S.A.
Neurocomputing (Amst). 2016 Feb 12;177:215-227. doi: 10.1016/j.neucom.2015.11.031.
Noise artifacts in magnetic resonance (MR) images increase the complexity of image processing workflows and decrease the reliability of inferences drawn from the images. It is thus often desirable to remove such artifacts beforehand for more robust and effective quantitative analysis. It is important to preserve the integrity of relevant image information while removing noise in MR images. A variety of approaches have been developed for this purpose, and the non-local means (NLM) filter has been shown to be able to achieve state-of-the-art denoising performance. For effective denoising, NLM relies heavily on the existence of repeating structural patterns, which however might not always be present within a single image. This is especially true when one considers the fact that the human brain is complex and contains a lot of unique structures. In this paper we propose to leverage the repeating structures from images to denoise an image. The underlying assumption is that it is more likely to find repeating structures from multiple scans than from a single scan. Specifically, to denoise a target image, multiple images, which may be acquired from different subjects, are spatially aligned to the target image, and an NLM-like block matching is performed on these aligned images with the target image as the reference. This will significantly increase the number of matching structures and thus boost the denoising performance. Experiments on both synthetic and real data show that the proposed approach, collaborative non-local means (CNLM), outperforms the classic NLM and yields results with markedly improved structural details.
磁共振（MR）图像中的噪声伪影增加了图像处理工作流程的复杂性，并降低了从图像得出的推断的可靠性。因此，通常希望事先去除此类伪影，以进行更稳健、有效的定量分析。在去除MR图像中的噪声时，保持相关图像信息的完整性非常重要。为此已经开发了多种方法，并且非局部均值（NLM）滤波器已被证明能够实现一流的去噪性能。为了实现有效的去噪，NLM严重依赖于重复结构模式的存在，然而，这些模式可能并不总是存在于单个图像中。当考虑到人类大脑复杂且包含许多独特结构这一事实时，情况尤其如此。在本文中，我们建议利用来自多幅图像的重复结构对一幅图像进行去噪。其基本假设是，从多次扫描中比从单次扫描中更有可能找到重复结构。具体而言，为了对目标图像进行去噪，将可能从不同受试者获取的多幅图像在空间上与目标图像对齐，并以目标图像为参考对这些对齐的图像执行类似NLM的块匹配。这将显著增加匹配结构的数量，从而提高去噪性能。对合成数据和真实数据的实验表明，所提出的协作非局部均值（CNLM）方法优于经典的NLM，并产生了结构细节明显改善的结果。
