Isolating and mitigating sequentially dependent perceptual errors in clinical visual search

隔离和减轻临床视觉搜索中的顺序相关感知错误

• 批准号: 10382244
• 负责人: DAVID V WHITNEY
• 金额: $ 30.52万
• 依托单位: UNIVERSITY OF CALIFORNIA BERKELEY
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-04-17 至 2024-03-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10382244
• 关键词: Benign; Classification; Clinical; Computer Vision Systems; Data; Decision Making; Dependence; Detection; Diagnosis; Diagnostic; Event; Goals; Guidelines; Health; Human; Image; Impairment; Judgment; Machine Learning; Measurable; Patients; Perception; Performance; Personal Satisfaction; Play; Positioning Attribute; Radiology Specialty; Reading; Recommendation; Reporting; Research Project Grants; Roentgen Rays; Role; Scanning; Series; Speed; Stimulus; Structure; Testing; Time; Training; Visual; Visual system structure; Work; X-Ray Medical Imaging; base; clinically relevant; design; diagnostic accuracy; diagnostic criteria; experience; improved; laboratory experiment; radiologist; tumor; visual search

Project Summary When looking at an x-ray, radiologists are typically asked to localize a tumor (if present), and to classify it, judging its size, class, position and so on. Importantly, during this task, radiologists examine on a daily basis hundreds and hundreds of x-rays, seeing several images one after the other. A main underlying assumption of this task is that radiologists’ percepts and decisions on a current X-ray are completely independent of prior events. Recent results showed that this is not true: our perception and decisions are strongly biased by our past visual experience. Although serial dependencies were proposed to be a purposeful mechanism to achieve perceptual stability of our otherwise noisy visual input, serial dependencies play a crucial and deleterious role in the everyday task performed by radiologists. For example, an x-ray containing a tumor can be classified as benign depending on the content of the previously seen x-ray. Given the importance and the impact of serial dependencies in clinical tasks, in this proposal, we plan to (1) establish, (2) identify and (3) mitigate the conditions under which serial effects determine our percepts and decisions in tumor search tasks. In Aim 1, we will establish the presence of serial effects in four different clinically relevant domains: tumor detection, tumor classification, tumor position and recognition speed. In Aim 2, we plan to identify the specific boundary conditions under which visual serial dependence impacts tumor search in radiology. In Aim 3, once we will fully understand these boundary conditions in Aim 2, we will propose a series of task and stimulus manipulations to control and mitigate the deleterious effects of visual serial dependence on tumor search. As a result of these manipulations, visual search performance should improve in measurable ways (detection, classification, position, speed). Aim 3 is particularly crucial because it will allow us to propose new guidelines which will greatly improve tumor recognition in x-ray images, making this task even more effective and reliable. Taken together, the proposed studies in Aim 1, 2, and 3 will allow us to establish, identify, and mitigate the deleterious effect of serial dependencies in radiological search tasks, which could have a significant impact on the health and well-being of patients everywhere. ! ! !

项目总结