关于 ECT 图像 EM-ML 重建中停止规则的说明。

A note on stopping rules in EM-ML reconstructions of ECT images.

机构信息

Inst. of Stat. & Decision Sci., Duke Univ., Durham, NC.

出版信息

IEEE Trans Med Imaging. 1994;13(3):569-71. doi: 10.1109/42.310891.

Abstract

The use of the expectation-maximization algorithm to obtain pseudo-maximum likelihood estimates (i.e. the EM-ML algorithm) of radiopharmaceutical distributions based on data collected from emission computed tomography (ECT) systems is now a well developed area, as witnessed by a number of recent articles on that topic, including the detailed study of the relative performance of EM-ML and FBP reconstructions provided in J. Llacer et al. (ibid., vol. 12, p. 215-31, 1993). However, there remains considerable confusion in the field regarding appropriate stopping rules for EM-ML algorithms, and in this correspondence the author attempts to detail a shortcoming of one of the more recent and innovative stopping rule criteria. In particular, the author discusses the effect of total photon counts on stopping criteria based on cross-validation.

摘要

利用期望最大化算法（即 EM-ML 算法）从发射型计算机断层（ECT）系统采集的数据中获取放射性药物分布的伪最大似然估计，目前已经是一个发展成熟的领域，从近期发表的一些相关文章，包括 J. Llacer 等人提供的关于 EM-ML 和 FBP 重建相对性能的详细研究（同上，第 12 卷，第 215-31 页，1993 年）中可以看出。然而，在 EM-ML 算法的适当停止规则方面，该领域仍然存在相当大的混淆，在本通信中，作者试图详细说明最近提出的、具有创新性的停止规则标准之一的一个缺陷。具体来说，作者讨论了基于交叉验证的总光子计数对停止规则的影响。