Enhanced Clinical Diagnosis through Imaging and Modeling: A Machine Learning Data Fusion Framework

通过成像和建模增强临床诊断：机器学习数据融合框架

• 批准号: 10483126
• 负责人: Hessam Babaee
• 金额: $ 19.47万
• 依托单位: UNIVERSITY OF PITTSBURGH AT PITTSBURGH
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-07 至 2024-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10483126
• 关键词: 3-Dimensional; 4D MRI; Adoption; Age; Angiography; Architecture; Bayesian learning; Blood Vessels; Blood Volume; Blood flow; Brain; Brain scan; Cerebrovascular Circulation; Cerebrum; Certification; Clinic; Clinical; Computational Technique; Computer Models; Computer Simulation; Consequentialism; Core-Binding Factor; Correlation Studies; Data; Data Set; Databases; Doppler Ultrasound; Future; Gaussian model; Gender; Goals; Healthcare; Heterogeneity; Image; Ischemic Stroke; Lead; Machine Learning; Maps; Measurement; Medical Imaging; Medicine; Methodology; Modality; Modeling; Modernization; Partner in relationship; Patients; Perfusion; Physics; Population; Positioning Attribute; Process; Radiation exposure; Research; Resolution; Scanning; Scheme; Source; Stroke; Techniques; Technology; Testing; Time; Training; Uncertainty; Validation; base; blood perfusion; cerebral artery; clinical application; clinical decision-making; clinical diagnosis; cost; data fusion; health application; hemodynamics; innovation; interest; novel; perfusion imaging; population based; predictive modeling; relating to nervous system; sensor; simulation; spatiotemporal; stroke patient; temporal measurement

PROJECT SUMMARY/ABSTRACT In this proposal, we will use modern machine learning techniques to combine and enhance computational modeling predictions. We will overcome the physics deficiencies that are inherent in modeling assumptions by including ground-truth clinical measurements, but in turn provide predictions that are more informative (higher spatial and temporal resolution) than the original clinical measurements. Furthermore, we will implement this framework as a surrogate model that can be used in real time and can replace current models with prohibitively high computation cost. If successful, the proposed research will enable lab-to-bedside deployment of a vast array of existing and future computational models and it ultimately could lead to a paradigm shift in health care workflow. Our overarching hypothesis is that the statistical correlations between computational models and clinical measurements can be exploited in a probabilistic data-fusion framework for more accurate predictions. Our multi-fidelity framework is based on an autoregressive Gaussian Process (GP) scheme. Our proposed scheme is a non-parametric Bayesian machine learning technique that has a probabilistic workflow and estimates uncertainty at different levels of fidelity in a principled manner. As a template for other clinical applications, we will develop this framework for perfusion scanning of brain hemodynamics in healthy and stroke populations, which has a significant health application. In Aim 1, we will simulate cerebral perfusion in healthy and stroke populations based on CT and MR angiography (CTA and MRA) scans. We will simulate and validate cerebral blood perfusion in healthy and stroke gender-balanced subjects. In Aim 2, we construct subject-specific multi-fidelity models by combining computational results and perfusion scans. We propose to leverage the multi-fidelity model to reduce scan time and radiation exposure by incorporating simulated perfusion maps with CT perfusion scans.

项目摘要/摘要 在此建议中，我们将使用现代机器学习技术结合和增强 计算建模预测。我们将克服物理缺陷 通过包括基地真实临床测量值，但又 提供的预测比较有用的预测（更高的空间和时间分辨率） 原始临床测量。此外，我们将把这个框架作为代理 可以实时使用的模型，并且可以用高度替代当前模型 计算成本。如果成功，拟议的研究将使实验室到床边部署 一系列现有和未来的计算模型，最终可能导致范式 医疗保健工作流程的转移。 我们的总体假设是计算之间的统计相关性 模型和临床测量可以在概率数据融合框架中利用 为了进行更准确的预测。我们的多保真框架是基于自回归的 高斯过程（GP）方案。我们提出的计划是非参数贝叶斯机器 具有概率工作流程并估算不同的不确定性的学习技术 有原则的忠诚度。 作为其他临床应用的模板，我们将开发此框架 健康和中风种群中脑血流动力学的灌注扫描 大量健康应用。在AIM 1中，我们将模拟健康和 基于CT和MR血管造影（CTA和MRA）扫描的中风种群。我们将模拟和 在健康和中风性别平衡受试者中验证脑血灌注。在AIM 2中，我们 通过结合计算结果和 灌注扫描。我们建议利用多保真模型来减少扫描时间和 通过将模拟的灌注图与CT灌注扫描结合在一起，辐射暴露。