Karbaschi Zohreh, Gifford Howard C
University of Houston, Department of Biomedical Engineering, Houston, Texas, United States.
J Med Imaging (Bellingham). 2018 Apr;5(2):025501. doi: 10.1117/1.JMI.5.2.025501. Epub 2018 Apr 5.
A principal difference between the channelized Hotelling (CH) and visual-search (VS) model observers is how they respond to noise texture in images. We compared the two observers in lesion-detection studies to evaluate linear and angular sampling parameters for CT. Simulated lung images were generated from a single two-dimensional mathematical torso phantom containing circular lesions of fixed radius and relative contrast. Projection datasets were produced for two detector pixel sizes and from 15 to 128 projections at 15 and 65 M counts per set. Filtered backprojection reconstructions were obtained with dimensions of [Formula: see text] and [Formula: see text]. A localization receiver operating characteristic study was conducted with two human observers, three single-feature VS observers, and a feature-adaptive VS observer. The effects of the sampling parameters on performance were similar for all of these observers. The CH observer, applied in location-known studies with and without background variability, was not affected by the variations in angular sampling. The two-stage VS framework was an effective modification of the CH observer for assessing the effects of noise texture on human-observer performance in this study.
通道化霍特林（CH）模型观察者和视觉搜索（VS）模型观察者之间的一个主要区别在于它们对图像中噪声纹理的响应方式。我们在病变检测研究中比较了这两种观察者，以评估CT的线性和角度采样参数。模拟肺部图像由单个二维数学躯干模型生成，其中包含固定半径和相对对比度的圆形病变。针对两种探测器像素尺寸以及每组15和65兆计数下从15到128个投影生成投影数据集。通过[公式：见原文]和[公式：见原文]尺寸获得滤波反投影重建图像。对两名人类观察者、三名单特征VS观察者和一名特征自适应VS观察者进行了定位接收器操作特性研究。所有这些观察者的采样参数对性能的影响相似。在有和没有背景变化的位置已知研究中应用的CH观察者不受角度采样变化的影响。在本研究中，两阶段VS框架是对CH观察者的有效改进，用于评估噪声纹理对人类观察者性能的影响。
