Unified measurement of observer performance in detecting and localizing target objects on images
Unified measurement of observer performance in detecting and localizing target objects on images
复制标题
DOI：
10.1118/1.597758
复制
发表时间：
1996-10-01
期刊：
影响因子：
3.8
通讯作者：
Swensson, RG
中科院分区：
文献类型：
--
作者：
Swensson, RG
本文综述了用于测量观测器性能的方法，并提出了一个简单的通用模型，用于在灰度图像背景下发现和报告目标物体。该模型为各种图像解释任务中检测和定位性能的组合测量提供了基础，无论是由人类观察者还是通过实现的计算机算法。该模型假设：(1)观察者的检测响应和目标位置的首选都取决于图像上的“最可疑”发现，(2)当且仅当其位置被选为最可疑时，才会发生对实际目标的正确（首选）定位，以及(3)目标的存在不会改变任何其他（正常）图像发现所产生的怀疑程度。这些假设的形式化将ROC曲线与“定位响应”（LROC）曲线联系起来，ROC曲线测量了区分包含目标和没有目标的图像的能力，而“定位响应”（LROC）曲线测量了检测和正确定位这些图像中实际目标的联合能力。为该模型的双参数“二正态”版本开发的最大似然统计程序同时拟合了来自观察者图像评级和一组图像解释目标定位的ROC和LROC曲线。该模型的应用被说明（并与标准的ROC分析相比较），使用来自放射科医生的评分和定位数据集来搜索肺结节的胸片。然后将该模型扩展到多目标图像的多报告（“自由响应”）解释，严格要求观察者的检测能力和报告可能目标的标准在图像和对给定图像的连续报告中都保持不变。这个扩展模型产生了所谓的“自由响应”（FROC）曲线的公式和预测，以及最近提出的“可选FROC”（AFROC）曲线。该模型的“平稳性”假设的测试使用放射科医生对肺结节胸片的自由搜索解释来说明，他们认为人类观察者在对图像进行多次报告解释时可能经常违反这些假设。(C) 1996美国医学物理学家协会。
In this paper methods used to measure observer performance are reviewed, and a simple general model for finding and reporting target objects in gray-scale image backgrounds is presented. That model provides the basis for a combined measurement of detection and localization performance in various image-interpretation tasks, whether by human observers or by realized computer algorithms. The model assumes that (1) an observer's detection response and first choice of target location both depend on the ''maximally suspicious'' finding on an image, (2) a correct (first-choice) localization of the actual target occurs if and only if its location is selected as the most suspicious, and (3) a target's presence does not alter the degree of suspicion engendered by any other (normal) image findings. Formalization of these assumptions relates the ROC curve, which measures the ability to discriminate between images containing targets and images without targets, to the ''Localization Response'' (LROC) curve, which measures the conjoint ability to detect and correctly localize the actual targets in those images. A maximum-likelihood statistical procedure, developed for a two-parameter ''binormal'' version of this model, concurrently fits both the ROC and LROC curves from an observer's image ratings and target localizations for a set of image interpretations. The model's application is illustrated (and compared to standard ROC analysis) using sets of rating and localization data from radiologists asked to search chest films for pulmonary nodules. This model is then extended to multiple-report (''free-response'') interpretations of multiple-target images, under the stringent requirement that an observer's detection capability and criterion for reporting possible targets both remain stationary across images and across the successive reports made on a given image. That extended model yields formulations and predictions for the so-called ''Free-Response'' (FROC) curve, and for a recently proposed ''Alternative FROC'' (AFROC) curve. Tests of that model's ''stationarity'' assumptions are illustrated using radiologists' free-search interpretations of chest films for pulmonary nodules, and they suggest that human observers may often violate those assumptions when making multiple-report interpretations of images. (C) 1996 American Association of Physicists in Medicine.