Medical Physics, Mater Misericordiae University Hospital, Dublin 7, Ireland; School of Medicine, University College, Dublin 4, Ireland.
School of Medicine, University College, Dublin 4, Ireland; Medical Physics and Bioengineering, St James's Hospital, Dublin 8, Ireland.
Phys Med. 2020 Mar;71:150-160. doi: 10.1016/j.ejmp.2020.02.002. Epub 2020 Mar 6.
Assessment of fluoroscopic image quality has not kept pace with technological developments in interventional imaging equipment. Access to 'for presentation' data on these systems has motivated this investigation into a novel quantitative method of measuring image quality. We have developed a statistical algorithm as an alternative to subjective assessment using threshold contrast detail detectability techniques. Using sets of uniformity exposed fluoroscopy frames, the algorithm estimates the minimum contrast necessary for conspicuity of a range of virtual target object areas A. Pixel mean value distributions in a central image region are Gaussian, with standard deviation σ Pixel binning produces background distributions with area A. For 95% confidence of conspicuity a target object must exhibit a minimum contrast of 3.29σ. A range of threshold contrasts are calculated for a range of virtual areas. Analysis on a few seconds of fluoroscopy data is performed remotely and no test object is required. In this study Threshold Index and Contrast Detail curves were calculated for different incident air kerma rates at the detector, different levels of electronic magnification and different types of image processing. A limited number of direct comparisons were made with subjective assessments using the Leeds TO.10 test object. Results obtained indicate that the statistical algorithm is not only more sensitive to changes in levels of detector dose rate and magnification, but also to levels of image processing, including edge-enhancement. Threshold Index curves thus produced could be used as an interventional system optimisation tool and to objectively compare image quality between vendor systems.
评估荧光透视图像质量的水平一直落后于介入影像设备的技术发展。为了获取这些系统的“用于演示”数据，我们研究了一种新的图像质量定量测量方法。我们开发了一种统计算法，以替代使用阈值对比度细节检测技术的主观评估。使用一组均匀曝光的透视框架，该算法估计了一系列虚拟目标区域 A 的可见度所需的最小对比度。中央图像区域中的像素平均值分布呈高斯分布，标准差为σ。像素分箱产生具有面积 A 的背景分布。为了达到 95%的可见度置信度，目标物体必须具有至少 3.29σ的对比度。对于一系列虚拟区域，计算了一系列阈值对比度。对几秒钟的荧光透视数据进行远程分析，无需测试物体。在这项研究中，对于不同的入射空气比释动能率在探测器上、不同的电子放大倍数和不同类型的图像处理，计算了阈值指数和对比度细节曲线。与使用利兹 TO.10 测试物体的主观评估进行了有限数量的直接比较。结果表明，统计算法不仅对探测器剂量率和放大倍数水平的变化更敏感，而且对图像处理水平也更敏感，包括边缘增强。因此，产生的阈值指数曲线可以用作介入系统优化工具，并客观比较不同供应商系统之间的图像质量。
