Characterization of Early Response to Chronic Lung Injury using Chest CT

使用胸部 CT 表征慢性肺损伤的早期反应

• 批准号: 10079021
• 负责人: Samuel Ash
• 金额: $ 17.03万
• 依托单位: BRIGHAM AND WOMEN'S HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10079021
• 关键词: Advisory Committees; Area; Award; Chest; Chronic; Cicatrix; Clinical; Critical Care; Densitometry; Detection; Development; Development Plans; Disease; Disease Progression; Early identification; Educational workshop; Evolution; Fibrosis; Goals; Hospitals; Image; Image Analysis; Imaging Techniques; Individual; Inflammation; Inflammatory; Laboratories; Lung; Lung diseases; Measurement; Measures; Medical Imaging; Medicine; Mentors; Mentorship; Methodology; Methods; Minority; Monitor; National Heart, Lung, and Blood Institute; Network-based; Outcome; Patients; Peripheral; Pharmaceutical Preparations; Predictive Factor; Primary Prevention; Principal Investigator; Publications; Pulmonary Emphysema; Pulmonary Fibrosis; Radiologic Finding; Radiology Specialty; Research Personnel; Risk; Risk Factors; Scanning; Scientist; Sensitivity and Specificity; Severity of illness; Smoker; Smoking; Structure of parenchyma of lung; Symptoms; Teaching Hospitals; Techniques; Tissues; Training; Training Programs; Visual; Woman; Work; X-Ray Computed Tomography; attenuation; base; career; career development; chest computed tomography; cigarette smoking; clinically relevant; clinically significant; convolutional neural network; deep learning; density; disorder prevention; disorder risk; exercise capacity; follow-up; improved; interstitial; lung injury; mange; medical schools; modifiable risk; mortality; new technology; novel; palliate; palliating symptoms; palliation; predictive modeling; prevent; protein biomarkers; pulmonary function; quantitative imaging; respiratory; response; skills; smoking-related lung disease; statistical and machine learning; tobacco smoke exposure; tool; treatment strategy

Project Summary In some individuals chronic tobacco smoke exposure results in emphysema and pulmonary fibrosis. Both of these parenchymal changes are irreversible, highlighting the importance of the early identification of their development and progression. Unfortunately, currently available methods for detecting the presence and evolution of these changes have limited sensitivity and specificity for very early disease and for subtle disease progression. Dr. Ash’s work has shown that automated objective analysis of computed tomography (CT) scans of the chest can detect clinically relevant radiologic findings called interstitial changes that may represent early pulmonary fibrosis, even in individuals without visually apparent disease. In the first aim of this proposal, Dr. Ash will refine and utilize a more sensitive and specific automated CT analysis tool that he and his lab have developed for the detection of both emphysema and interstitial changes. He will determine if emphysema and interstitial changes detected using this method are clinically significant in those patients deemed normal by previously performed visual analysis and in those deemed normal by other objective approaches. In the second aim, he will determine if areas of locally high density tissue in visually normal appearing lung parenchyma measured using augmented versions of his objective analysis tools are associated with mortality, other clinical outcomes, and peripheral measures of inflammation. Finally, in the third aim he will utilize these techniques to analyze longitudinal CT scans from the COPDGene study that were obtained over 10 years of follow-up, and will identify factors that predict or modify the development and progression of parenchymal changes on CT. Dr. Ash will perform this work in the Division of Pulmonary and Critical Care Medicine at Brigham and Women’s Hospital (BWH), a core teaching hospital of Harvard Medical School, under the mentorship of Dr. George Washko, an expert in the field of medical image analysis and the co-principal investigator of the Applied Chest Imaging Laboratory at BWH. With the guidance of Dr. Washko and his scientific advisory committee, Dr. Ash has developed a comprehensive five year training program to develop the skills needed to become an independent investigator with expertise in quantitative image analysis, including predictive modeling and statistical machine learning. Dr. Ash is dedicated to a career in academic medicine. His goal is to become a clinician-scientist using the skills gained during this award to improve our ability to detect and monitor smoking related lung disease. The techniques he has proposed may help identify modifiable risk factors and treatments for smoking related lung disease, determine which patients are likely to benefit from treatment, and monitor the response to therapy.

项目摘要 在某些人中，慢性烟草烟雾暴露导致肺气肿和肺纤维化。 这两种实质变化都是不可逆的，突出了早期识别的重要性。 他们的发展和进步。不幸的是，目前可用的用于检测存在和 这些变化的演变对于非常早期的疾病和细微的疾病具有有限的敏感性和特异性 进展阿什博士的工作表明，计算机断层扫描（CT）的自动客观分析 胸部扫描可以发现临床相关的放射学发现，称为间质性变化， 代表早期肺纤维化，即使在没有视觉明显疾病的个体中。第一个目标是 根据这项提议，Ash博士将改进和利用一种更灵敏、更具体的自动化CT分析工具， 他的实验室已经开发出用于检测肺气肿和间质变化的方法。他将决定是否 使用该方法检测的肺气肿和间质变化在这些患者中具有临床意义 先前进行的目视分析认为正常，其他目标认为正常 接近。在第二个目标中，他将确定局部高密度组织区域是否在视觉上正常， 使用他的客观分析工具的增强版本测量的肺实质出现相关 死亡率、其他临床结果和炎症的外周指标。最后，在第三个目标中， 将利用这些技术来分析从COPDGene研究中获得的纵向CT扫描， 超过10年的随访，并将确定预测或改变的发展和进展的因素， CT上的实质改变。 Ash博士将在布里格姆的肺部和重症监护医学部开展这项工作， 妇女医院是哈佛医学院的核心教学医院。 乔治沃什科是医学图像分析领域的专家，也是该研究的联合首席研究员。 BWH应用胸部成像实验室。在沃什科博士的指导下 委员会，阿什博士制定了一个全面的五年培训计划，以发展所需的技能， 成为一名独立的研究者，拥有定量图像分析的专业知识，包括预测 建模和统计机器学习。 阿什博士致力于学术医学的职业生涯。他的目标是成为一名临床科学家， 在此奖项期间获得的技能，以提高我们的能力，以检测和监测吸烟相关的肺部疾病。 他提出的技术可能有助于确定可改变的风险因素和治疗吸烟相关的疾病。 肺部疾病，确定哪些患者可能从治疗中受益，并监测对 疗法