Visual-search ideal observers for modeling reader variability

视觉搜索理想观察者对读者变异性进行建模

• 批准号: 10530899
• 负责人: Howard Carl Gifford
• 金额: $ 57.73万
• 依托单位: UNIVERSITY OF HOUSTON
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-01 至 2027-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10530899
• 关键词: Adopted; Adoption; Agreement; Behavior; Clinical; Clinical Research; Cognitive; Computer Models; Data; Data Set; Dependence; Detection; Diagnostic; Diagnostic Imaging; Digital Breast Tomosynthesis; Discipline of Nuclear Medicine; Dose; Goals; Gold; Human; Hybrids; Image; Imaging technology; Individual; Information Retrieval; Joints; Kidney; Location; Methods; Modality; Modeling; Outcome; Patient Care; Patient Simulation; Patients; Performance; Physiological; Primates; Process; Property; Protocols documentation; Radiology Specialty; Reader; Reading; Research; Research Personnel; Resources; Roentgen Rays; Sampling; Scanning; Source; Structure; Study models; Task Performances; Technology; Testing; Three-Dimensional Image; Training; Validation; Variant; Work; clinical diagnostics; clinical imaging; clinically relevant; cost; flexibility; human data; ideal observer (Bayesian); imaging study; improved; in silico; insight; interest; novel; operation; prevent; radiologist; reconstruction; sample fixation; single photon emission computed tomography; skills; theories; tool; virtual; visual search

Project Summary/Abstract The goal of this project is to develop novel methods for predicting human decisions with diagnostic images. Expected project outcomes include new insights into sources of radiologist variability and advanced tools to accelerate imaging trials in clinical research. Such trials with expert readers and known-truth cases are an accepted but burdensome gold standard for evaluating imaging technology. The necessary trial resources are not available to many clinical researchers. Virtual trials with sur- rogate model observers have been proposed, but important limitations, including primarily correlative estimates and persistent model reliance on human data for training, prevent their widespread adop- tion. Quantitative models with minimal dependence on human input will substantially improve clinical access to advanced imaging technology. Our approach to develop such “low-resource” models will explore reader variability in target detection and estimation tasks. Ideal observers (IOs) derived from gist-processing and extreme-value theories will be the starting point. These IOs are optimal for de- cision processes that maximize over sets of extracted feature values, a common premise for tasks involving visual search. The result will be adaptive observer models that produce tighter bounds on human performance compared to existing models. These new models will test if reader variability can be attributed to candidate pooling and cognitive threshold mechanisms that define image struc- ture of interest. Analytic figures of merit for diagnostic visual-search tasks will be developed. We will test model generalizability across radiological modalities, tasks, imaging models (e.g., simula- tion/patient data), and reader classes (lay/clinician), all of relevance for researchers. The tasks will include location-known, localization, and joint detection-estimation formats. The joint task compels more precise information extraction than target detection alone; we hypothesize that detection perfor- mance correlates with estimation skill, with the latter helping to resolve structure. We shall leverage our findings to devise multireader virtual trial protocols for improved statistical rigor. Enhanced stochastic target modeling for studies with 2D and 3D images will be supporting aims. The IO will also allow examination of nonlinear behaviors for individual readers. The project studies relate to dose reduction and reconstruction methods for x-ray and nuclear medicine modalities, but the methods can apply more generally. By accelerating the clinical adoption of advanced imaging technology, our model observers will have a direct and widespread impact on clinical operations and patient care.

项目概要/摘要 该项目的目标是开发通过诊断来预测人类决策的新方法 图像。预期的项目成果包括对放射科医生变异性来源的新见解和 加速临床研究中成像试验的先进工具。与专家读者进行的此类试验 已知真相案例是评估成像技术的公认但繁琐的黄金标准。 许多临床研究人员无法获得必要的试验资源。虚拟试验与sur- 已经提出了 rogate 模型观察者，但存在重要的局限性，包括主要是相关的 估计和模型持续依赖人类数据进行训练，阻碍了它们的广泛采用 。对人类输入的依赖性最小的定量模型将大大改善临床 获得先进的成像技术。我们开发这种“低资源”模型的方法将 探索目标检测和估计任务中读者的可变性。理想观察者 (IO) 源自 要点处理和极值理论将是起点。这些IO是最佳的de- 最大化提取的特征值集的决策过程，这是任务的共同前提 涉及视觉搜索。结果将是自适应观察者模型，产生更严格的界限 与现有模型相比的人类表现。这些新模型将测试读者的可变性 可以归因于候选池和定义图像结构的认知阈值机制 兴趣的真实性。将开发诊断视觉搜索任务的分析品质因数。我们 将测试模型在放射学模式、任务、成像模型（例如模拟 化/患者数据）和读者类别（非专业人士/临床医生），所有这些都与研究人员相关。任务将 包括位置已知、定位和联合检测估计格式。联合任务迫使 比单独目标检测更精确的信息提取；我们假设检测性能 曼斯与估计技能相关，后者有助于解决结构问题。我们将利用我们的 设计多读者虚拟试验方案以提高统计严谨性的研究结果。增强随机 2D 和 3D 图像研究的目标建模将成为支持目标。 IO 还将允许 检查个体读者的非线性行为。该项目研究涉及剂量减少 X 射线和核医学模式的重建方法，但这些方法可以应用 更一般地说。通过加速先进成像技术的临床应用，我们的模型 观察员将对临床操作和患者护理产生直接而广泛的影响。