College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua, China.
College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua, China.
Artif Intell Med. 2019 Jun;97:131-142. doi: 10.1016/j.artmed.2018.12.001. Epub 2019 Feb 1.
NeighShrink is an efficient image denoising algorithm for the reduction of additive white Gaussian noise. However, it does not perform well in terms of Rician noise removal for MRI (Magnetic Resonance Imaging). Allowing for the characteristics of squared-magnitude MR (Magnetic Resonance) images, which follow a non-central chi-square distribution, the CURE (Chi-Square Unbiased Risk Estimation) is used to determine an optimal threshold for NeighShrink. Therefore, we propose the NeighShrinkCURE denoising algorithm. Bilateral filtering and cycle spinning are used to further improve denoising performance. Experimental results show that the proposed algorithm is simple and efficient, and provides good noise reduction while preserving edges and details well. Compared with some similar MRI denoising algorithms, the proposed algorithm has improvements in PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity). Although running time of the proposed algorithm has some increment compared with some current MRI denoising algorithms, the comprehensive performance of the proposed algorithm is superior to several current MRI denoising algorithms.
NeighShrink 是一种用于减少加性高斯噪声的有效图像去噪算法。然而，它在 MRI（磁共振成像）中的瑞利噪声去除方面表现不佳。考虑到平方幅度磁共振（MR）图像的特点，它们遵循非中心卡方分布，因此使用 CURE（卡方无偏风险估计）来确定 NeighShrink 的最佳阈值。因此，我们提出了 NeighShrinkCURE 去噪算法。双边滤波和循环旋转用于进一步提高去噪性能。实验结果表明，所提出的算法简单高效，在很好地保留边缘和细节的同时提供了良好的降噪效果。与一些类似的 MRI 去噪算法相比，所提出的算法在 PSNR（峰值信噪比）和 SSIM（结构相似性）方面有所改进。虽然与一些现有的 MRI 去噪算法相比，所提出的算法的运行时间有所增加，但所提出的算法的综合性能优于几种现有的 MRI 去噪算法。
