Cerebrovascular Reserve Imaging with Simultaneous PET/MRI Using Arterial Spin Labeling and Deep Learning

使用动脉自旋标记和深度学习同时进行 PET/MRI 脑血管储备成像

• 批准号: 9789276
• 负责人: Gregory George Zaharchuk
• 金额: $ 58.63万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-20 至 2022-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9789276
• 关键词: Acetazolamide; Address; Age; Artificial Intelligence; Biological; Blood flow; Brain; Brain imaging; Bypass; Cardiac; Cardiology; Carotid Stenosis; Cause of Death; Cerebrovascular Circulation; Cerebrovascular Disorders; Clinical; Clinical Trials Design; Computer Vision Systems; Consensus; Cytolysis; Data; Deposition; Diagnostic; Excision; Gadolinium; Gender; Goals; Gold; Guidelines; ImProv; Image; Imaging problem; Impairment; Individual; Intervention; Intervention Trial; Japanese Population; Label; Link; Machine Learning; Magnetic Resonance Imaging; Measurement; Measures; Meta-Analysis; Methodology; Methods; Modeling; Motion; Noise; Nutrient; Outcome; Oxygen; Patient Triage; Patients; Physiologic pulse; Physiological; Play; Positron-Emission Tomography; Premenopause; Procedures; Radiation; Reference Standards; Reproducibility; Rest; Risk; Role; Scanning; Signal Transduction; Solid; Spin Labels; Stress Tests; Stroke prevention; Techniques; Testing; Time; Training; United States; Validation; Waste Products; Water; Woman; Xenon; base; blood flow measurement; cerebral hemodynamics; cerebrovascular; cerebrovascular imaging; clinical application; cohort; convolutional neural network; deep field survey; deep learning; design; direct application; disability; evidence based guidelines; gender difference; imaging modality; improved; learning network; men; nervous system disorder; novel strategies; performance tests; prospective; response; stressor; stroke risk; systematic review; time use; tool

Cerebrovascular disease remains a common cause of death and major disability in the United States, and identifying and preventing strokes should be a high priority. Direct measurement of regional cerebral blood flow (CBF) is challeng- ing in these patients, since we do not have a non-invasive, radiation-free imaging method that has been appropriately validated against gold standard techniques. This is important, because there is compelling evidence that measuring the CBF change before and after a stress test meant to increase CBF (a measurement known as cerebrovascular reserve [CVR]) can identify patients at increased stroke risk. Stress tests have been a mainstay of the diagnostic workup of cardiology patients for many years, and we believe strongly that their use will benefit cerebrovascular disease patients as well. The goal of this project is to improve the quality of arterial spin label (ASL) MRI using deep learning, a powerful form of machine learning, that is currently undergoing tremendous progress. We will then to apply this in a prospective, adaptive validation trial against oxygen-15 water PET CBF, using simultaneous PET/MRI to minimize biological variability. Finally, we will apply this improv- ed tool to study the effects of gender on CVR and its reproducibility. Successful completion of this study will result in a validated methodology to assess CVR in cerebrovascular disease patients without the use of radiation or contrast. As such, it will provide solid, evidence-based recommendations for clinicians developing new paradigms and interventions in patients with impaired CVR.

脑血管疾病仍然是死亡和重大残疾的常见原因 在美国，识别和预防中风应该是一项高度重视的工作 优先事项。直接测量局部脑血流量 (CBF) 具有挑战性 对这些患者进行治疗，因为我们没有无创、无辐射的治疗方法 已根据金标准进行适当验证的成像方法 技术。这很重要，因为有令人信服的证据表明 测量旨在增加 CBF 的压力测试前后的 CBF 变化 （一种称为脑血管储备 [CVR] 的测量方法）可以识别患者 中风风险增加。压力测试一直是诊断的主要手段 对心脏病患者进行了多年的检查，我们坚信他们的 使用也将使脑血管疾病患者受益。 该项目的目标是提高动脉旋转标签（ASL）的质量 使用深度学习的 MRI，深度学习是机器学习的一种强大形式，目前 正在取得巨大的进步。然后我们将把它应用到未来， 针对氧 15 水 PET CBF 的自适应验证试验，使用同时 PET/MRI 可最大限度地减少生物变异性。最后，我们将应用这个改进 ed 工具来研究性别对 CVR 及其再现性的影响。 成功完成这项研究将产生一种经过验证的方法 评估脑血管疾病患者的 CVR，无需使用放射或 对比。因此，它将提供可靠的、基于证据的建议 临床医生为患者开发新的范例和干预措施 CVR 受损。