Properties of Noise in Positron Emission Tomography Images Reconstructed with Filtered-Backprojection and Row-Action Maximum Likelihood Algorithm
Properties of Noise in Positron Emission Tomography Images Reconstructed with Filtered-Backprojection and Row-Action Maximum Likelihood Algorithm
复制标题
DOI：
10.1007/s10278-012-9511-5
复制
发表时间：
2013-06-01
影响因子：
4.4
通讯作者：
Robinson, D.
中科院分区：
文献类型：
--
作者：
Teymurazyan, A.;Riauka, T.;Robinson, D.
在正电子发射断层扫描（PET）图像中观察到的噪声水平使其几何解释变得复杂。可以采用旨在降低噪声的后处理技术来克服这个问题。然而，影响PET图像的噪声的详细特性通常不是众所周知的。通常，假设总体上噪声可以被表征为高斯。其他PET成像相关研究专门针对减少泊松或混合泊松+高斯模型所代表的噪声。任何降噪方法的有效性在很大程度上取决于对噪声特性的适当量化。这项工作研究了噪声的统计特性与GEMINI PET/CT扫描仪采集的PET图像。噪声测量已与圆柱体模注入C-11和良好的混合，以提供一个均匀的活动分布。使用标准临床协议获取图像，并使用滤波反投影（FBP）和行动作最大似然算法（RAMLA）重建。评价了采集数据的统计特性，并与五种噪声模型（泊松、正态、负二项、对数正态和伽马）进行了比较。实验数据的直方图用于计算累积分布函数并产生模型分布参数的最大似然估计。所获得的结果证实了泊松分布的RAMLA和FBP重建的PET数据的代表性差。我们表明，RAMLA重建PET图像中的噪声是非常好的特点是伽玛分布紧随其后的正态分布，而FBP产生可比符合正常和伽玛统计。
Noise levels observed in positron emission tomography (PET) images complicate their geometric interpretation. Post-processing techniques aimed at noise reduction may be employed to overcome this problem. The detailed characteristics of the noise affecting PET images are, however, often not well known. Typically, it is assumed that overall the noise may be characterized as Gaussian. Other PET-imaging-related studies have been specifically aimed at the reduction of noise represented by a Poisson or mixed Poisson + Gaussian model. The effectiveness of any approach to noise reduction greatly depends on a proper quantification of the characteristics of the noise present. This work examines the statistical properties of noise in PET images acquired with a GEMINI PET/CT scanner. Noise measurements have been performed with a cylindrical phantom injected with C-11 and well mixed to provide a uniform activity distribution. Images were acquired using standard clinical protocols and reconstructed with filtered-backprojection (FBP) and row-action maximum likelihood algorithm (RAMLA). Statistical properties of the acquired data were evaluated and compared to five noise models (Poisson, normal, negative binomial, log-normal, and gamma). Histograms of the experimental data were used to calculate cumulative distribution functions and produce maximum likelihood estimates for the parameters of the model distributions. Results obtained confirm the poor representation of both RAMLA- and FBP-reconstructed PET data by the Poisson distribution. We demonstrate that the noise in RAMLA-reconstructed PET images is very well characterized by gamma distribution followed closely by normal distribution, while FBP produces comparable conformity with both normal and gamma statistics.