基于可变有序子集的惩罚最小二乘算法

Penalized Least-squares Algorithm based Modified ordered Subsets

传统算法不能有效的抑制噪声且收敛速度慢。为了解决这些问题,在最小二乘算法中引入中值先验,并结合可变有序子集(MOS)技术用于PET图像重建,形成了基于可变有序子集的惩罚最小二乘算法(MOS-PLS-Median)。仿真结果表明,MOS-PLS算法相对于最小二乘(LS)等传统算法,不仅能够有效的抑制噪声,重建出质量更好的图像,而且较大地提高了收敛速度。

The traditional iterative reconstruction algorithms of positron emission tomography can not effectively suppress the noise and simultaneous iterative algorithms have slow convergence.In order to solve the problem,a median root prior is introduced into the least-squares algorithm,and combine with Modified Ordered Subsets（MOS） method in PET resonstruction,forming the penalized least-squares algorithm based modified ordered subsets（MOS-PLS-Median）.Compared with the other reconstruction algorithms such as LS,OS-PLS,the proposed algorithm not only availably suppress the noise,perverse the edge of the image,and reconstruct a higher quality image,but also enhance the convergence preferable.