Automated Diagnosis and Progression Rate of IPF Using HRCT

使用 HRCT 自动诊断 IPF 并确定其进展率

• 批准号: 9765383
• 负责人: Grace Hyun Jung Kim
• 金额: $ 11.32万
• 依托单位: UNIVERSITY OF CALIFORNIA LOS ANGELES
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-08-16 至 2020-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9765383
• 关键词: Acute; Air; Algorithms; Anatomy; Archives; Automation; Biological; Biopsy; Categories; Clinical; Clinical Data; Computer Analysis; Computer Assisted; Computer Vision Systems; Data; Data Element; Data Set; Data Sources; Deterioration; Development; Diagnosis; Diagnostic; Diffuse; Disease; Disease Progression; Disease stratification; Elderly; Etiology; Exhibits; General Population; Glass; Goals; Growth; High Resolution Computed Tomography; Image; Image Analysis; Impairment; Individual; Informatics; Interstitial Lung Diseases; Intraobserver Variability; Laboratories; Lobar; Lobe; Lung; Lung Transplantation; Lung diseases; Measurement; Measures; Methods; Modeling; Multicenter Trials; Natural History; Operative Surgical Procedures; Pathology; Patient Triage; Patients; Pattern; Pharmacologic Substance; Pharmacotherapy; Phenotype; Prevalence; Probability; Progression-Free Survivals; Progressive Disease; Public Health; Pulmonary Fibrosis; Registries; Reproducibility; Research; Risk; Role; Scanning; Spatial Distribution; Stable Disease; Standardization; Testing; Texture; Time; Time Management; Training; Transplantation; Visual; X-Ray Computed Tomography; base; clinical application; clinically relevant; cohort; computerized; data archive; digital imaging; disease natural history; disease phenotype; functional decline; idiopathic pulmonary fibrosis; image processing; imaging biomarker; improved; individual patient; individualized medicine; new therapeutic target; novel; novel therapeutics; predictive modeling; prognostic; programs; pulmonary function; quantitative imaging; respiratory; success; survival prediction; tool

Project Summary: Idiopathic pulmonary fibrosis (IPF) is a devastating disease of unknown etiology occurring in older adults. IPF is ultimately fatal with a median survival of 2 to 5 years, and exhibits a highly heterogeneous natural history. Broad categories of disease progression have been defined, but are not predictable at the time of diagnosis. Diagnosis and stratification of disease phenotypes are important in order to decipher the effects of novel therapies among individuals with biologically dissimilar natural histories and to better tailor therapy to individuals. Few computerized diagnostic tools have been developed for IPF that correlate with visual and surgical lung biopsy; most use clinical and functional variables independent of imaging findings. Prognostic determinants based on imaging features rely largely on subjective visual assessment of disease. In contrast, no good predictive models with localized region exist that anticipate the natural history of disease in advance of significant functional decline. Given the indispensable role of high resolution computed tomography (HRCT) in the diagnosis and surveillance of IPF, we propose to mine the rich information in HRCT data sets to develop robust, quantitative features that can anticipate disease progression in advance of debilitating respiratory compromise. We propose to use as a derivative dataset the anonymized clinical data and source images on 234 patients with IPF and 266 patients with IPF suspected, but not IPF based on HRCT and the surgical biopsy who have participated in multicenter trials, and whose data are archived at the UCLA Computer Vision and Imaging Biomarkers Laboratory. Using an image processing pipeline developed in our laboratory for high through-put quantitative image analysis, we will train a classifier with features of anatomic distribution and reproducible imaging features expressed with a quantitative lung fibrosis (QLF) score, testing on separate data from in an independent institutional registry of clinical and image data on patients with IPF seen in the UCLA Interstitial Lung Disease Program. Furthermore, the second aim is to develop a rate of progression at local region and to aggregate predictive models using Cox proportional regression models, which will be derived using only clinical covariates and combined clinical and imaging covariates, correlating these models with progression free survival. Our objectives are centered on the goals of using preexisting datasets to develop clinically meaningful models that diagnose and anticipate disease course in patients with IPF and subdividing patients into more homogeneous groups prior to the development of significant respiratory impairment. We anticipate that models can be used clinically at the individual patient level to enable more informed and timely management decisions to define more homogeneous cohorts for purposes of testing new targeted therapies and to better elucidate the effects of therapies in patients with biologically heterogeneous disease progression.

项目总结： 特发性肺纤维化(IPF)是一种发生在老年人的原因不明的破坏性疾病。IPF 最终是致命的，中位生存期为2至5年，并表现出高度异质性的自然历史。 疾病进展的广泛类别已经确定，但在诊断时无法预测。 疾病表型的诊断和分层对于破译新的 在具有生物不同自然病史的个人之间进行治疗，并更好地为个人量身定做治疗。 几乎没有为IPF开发出与视觉和外科肺相关的计算机化诊断工具 活组织检查；大多数使用独立于影像表现的临床和功能变量。预后决定因素 基于影像的特征在很大程度上依赖于对疾病的主观视觉评估。相比之下，没有什么好的 存在具有局部区域的预测模型，它们可以提前预测疾病的自然病史 功能衰退。鉴于高分辨率计算机断层扫描(HRCT)在 对于IPF的诊断和监测，我们建议从HRCT数据集中挖掘丰富的信息来开发健壮的， 可以在衰弱的呼吸损害之前预测疾病进展的量化特征。 我们建议使用234名患者的匿名临床数据和原始图像作为衍生数据集。 经HRCT和手术活检怀疑为IPF的266例IPF患者。 参与了多中心试验，其数据在加州大学洛杉矶分校的计算机视觉和成像中心存档 生物标志物实验室。使用我们实验室开发的图像处理流水线实现高吞吐量 定量图像分析，我们将训练一个具有解剖分布和可重复性特征的分类器 用定量肺纤维化(QLF)评分表达的影像特征，测试来自于 加州大学洛杉矶分校间质中IPF患者临床和影像资料的独立机构登记 肺病项目。此外，第二个目标是在当地制定一个进展速度，并 使用COX比例回归模型的聚合预测模型，该模型将仅使用临床数据导出 协变量以及临床和影像的联合协变量，将这些模型与无进展生存期相关联。 我们的目标是利用已有的数据集开发具有临床意义的模型 诊断和预测IPF患者的病程，并将患者细分为更多 同质组发展前有明显的呼吸功能损害。我们预计这款车型 可在单个患者级别的临床上使用，以实现更明智和及时的管理决策 为了测试新的靶向治疗而定义更多的同质性队列，并更好地阐明 治疗对生物异质性疾病进展患者的影响。

项目成果

Quantitative interstitial lung disease scores in idiopathic inflammatory myopathies: longitudinal changes and clinical implications.

特发性炎症性肌病的间质性肺疾病定量评分：纵向变化和临床意义。

• DOI: 10.1093/rheumatology/kead122
• 发表时间: 2023
• 期刊: Rheumatology (Oxford, England)
• 作者: Yeo,Jina;Yoon,SoonHo;Kim,JuYeon;Lee,JeongSeok;Lee,EunYoung;Goo,JinMo;Pourzand,Lila;Goldin,JonathanG;Kim,Grace-HyunJ;Ha,You-Jung
• 通讯作者: Ha,You-Jung