ROC Analysis of Imaging System Evaluations

超出提供的空间。当评估成像系统可能用于临床环境以及监管审批过程时，对技术和实践的诊断性能的评估成为决策过程中越来越重要的部分。在医学成像中，这些评估中的很大一部分包括使用ROC类型响应或其导数进行分析的特定任务评级。本项目的总体目标是提高我们对当观察者、计算机化方案(例如CAD)或两者的组合成为诊断系统的组成部分时，我们在系统评估和比较期间遇到的实际(方法学)和计算(相关分析)问题的理解。在当前的供资期间，我们开发和测试了一种新的方法来分析在执行ROC类型研究期间确定的评分数据，并开始处理与将基于相关性的实用程序纳入分析有关的问题。基本方法使用负面和正面案例(检查)之间的所有配对观察，使用非参数方法构建业绩摘要指数。无条件测试和条件测试都已被开发和测试，并被证明在小样本量研究中具有明显的实验优势。使用这一一般方法提出了五项主要工作。我们建议将该方法扩展到多读者、多模式、多疾病的设置，并将各种实用函数纳入分析中。最后，我们将研究如何使用这种方法和其他方法来识别和可能地处理ROC类型研究中的离群值。表演网站========================================Section End===========================================

EXCEED THE SPACE PROVIDED. Assessment of diagnostic performance of technologies and practices constitute an increasingly important part of the decision making process when imaging systems are evaluated for possible use in the clinical environment as well as during the regulatory approval process. In medical imaging a substantial fraction of these evaluations include task specific ratings that are being analyzed using an ROC type response or derivative thereof. The overall objective of this project is to improve our understanding of the practical (methodological) and computational (analyses related) issues that we encounter during systems evaluations and comparisons when the observer, a computerized scheme (e.g. CAD), or a combination of both become an integral part of the diagnostic system. During the current period of funding we developed and tested a new approach to analyzing scoring data ascertained during the performance of ROC type studies and began to address issues related to the incorporation of relevance based utilities into the analyses. The underlying approach uses all paired observations between negative and positive cases (examinations) to construct summary indices of performance using a non-parametric methodology. Both unconditional and conditional tests have been developed and tested and were shown to have distinct experimental advantages for small sample size studies. Five primary efforts are proposed using this general approach. We propose to expand the method to a multi-reader, multi-modality, multi-disease settings as well as to incorporate a variety of utility functions into the analysis. Last, we will investigate how this and other methods can be used to identify and possibly treat outliers in ROC type studies. PERFORMANCE SITE ========================================Section End===========================================