Scalable Bayesian methods for big imaging data analysis

用于大成像数据分析的可扩展贝叶斯方法

• 批准号: 10269912
• 负责人: Timothy D Johnson
• 金额: $ 31.54万
• 依托单位: UNIVERSITY OF MICHIGAN AT ANN ARBOR
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-30 至 2025-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10269912
• 关键词: Address; Adolescence; Adolescent; Affect; Age; Algorithms; Bayesian Analysis; Bayesian Method; Bayesian Modeling; Behavioral; Big Data; Biological; Brain; Brain imaging; Cations; Child; Child Health; Childhood; Clinical; Clinical Research; Complex; Computational algorithm; Computer software; Data; Data Analyses; Dependence; Development; Discipline; Electronic Health Record; Environmental Risk Factor; Etiology; Frequencies; Functional Magnetic Resonance Imaging; Funding; Gaussian model; Goals; High Performance Computing; Human; Human Genome; Image; Individual; Intervention; Joints; Knowledge; Longitudinal Studies; Magnetic Resonance Imaging; Maps; Measurement; Mediating; Mediation; Medicine; Methods; Modeling; Modernization; Modification; Multimodal Imaging; Neural Network Simulation; Neurosciences; Online Systems; Outcome; Pathology; Pattern; Performance; Process; Psychology; Psychopathology; Research; Rest; Risk; Route; Sample Size; Sampling; Seminal; Smoking; Sports; Statistical Data Interpretation; Statistical Methods; Structure; Substance Use Disorder; Technology; Time; Translational Research; United States; United States National Institutes of Health; Video Games; Work; Youth; addiction; cluster computing; cognitive development; computerized tools; experience; feature selection; high dimensionality; high resolution imaging; high risk; imaging biomarker; imaging modality; innovation; neural network; neuroimaging; novel; parallel computer; precision medicine; predict clinical outcome; predictive modeling; risk prediction; screening; sleep pattern; social; social factors; social media; substance use; tool; user friendly software; vector; web page; young adult

ABSTRACT! This proposal will address the most timely and important issues in statistical analysis of big imaging data. Our project is motivated by "The Adolescent Brain Cognitive Development (ABCD) Study”, which is the largest long-term study of brain development and child health in the United States and is funded by the National Institutes of Health (NIH). Innovative aspects of this proposal are: 1) We develop a new Bayesian image-on- vector regression model with novel sparse and smooth Gaussian process priors. It enables to perform association analysis between high-resolution images of brain activity and high-dimensional vectors of social environmental factors and clinical variables. To the best of our knowledge no existing methods can efficiently and jointly analyze high-resolution images and high-dimensional vectors of covariates simultaneously under a systematic modeling framework; 2) We develop a new Bayesian scalar-on-image neural network model with sparse, smooth, and spatially-varying coefficients. This new model has great potential to make better predictions about the risk of an adolescent initiating substance use compared to all existing methods; and more importantly, it will identify important imaging biomarkers that are associated with substance use patterns. This will provide a better understanding of the pathology of substance use initiation; 3) We propose a Bayesian model for high-dimensional mediation analysis of multimodality imaging data by combining image-on-vector regression and scalar-on-image regression with modifications. Under the potential outcome framework, ! we will define the direct effects of environmental factors/electronic health records on psychopathology, as well as their indirect effects that are mediated through the changes in brain functions and/or structures. 4) We develop scalable posterior computation algorithms for all of the proposed models. These efficient computation tools will enable the possibility to apply the statistical methods in the clinical and translational research and applications. Our methods can address two key questions about adolescent brain cognitive development: 1) they will identify important childhood experiences and social environmental factors, such as sports, video games, social media, unhealthy sleep patterns, and smoking, that affect brain development; 2) understand the inferences of brain development on the risk of substance use initiation and patterns, including detailed quantity, frequency, route of administration, and co-use patterns. ! !

抽象的！ 该建议将解决大型成像数据统计分析中最及时，最重要的问题。我们的 项目是由“青少年脑认知发展（ABCD）研究”的动机，这是最大的 美国大脑发育和儿童健康的长期研究，由国家资助 卫生研究院（NIH）。该提案的创新方面是：1）我们开发了新的贝叶斯图像。 具有新型稀疏和光滑的高斯工艺先验的矢量回归模型。它可以执行 大脑活动的高分辨率图像与社会高维矢量之间的关联分析 环境因素和临床变量。据我们所知，没有现有方法可以有效 并共同分析仅在a下的协变量的高分辨率图像和高维数 系统建模框架； 2）我们开发了一个新的贝叶斯标量图像神经网络模型 稀疏，光滑和空间变化的系数。这个新模型具有更好的潜力 与所有现有方法相比，关于青少年启动物质使用风险的预测；还有更多 重要的是，它将确定与物质使用模式相关的重要成像生物标志物。这 将更好地了解物质使用倡议的病理； 3）我们提出了贝叶斯人 通过结合矢量形象，用于多模式成像数据的高维中介分析的模型 通过修改的回归和标量图像回归。在潜在的结果框架下，！ 我们将定义环境因素/电子健康记录对心理病理学的直接影响 由于它们的间接效应是通过大脑功能和/或结构的变化介导的。 4）我们 为所有提出的模型开发可扩展的后验计算算法。这些有效的计算 工具将使有可能在临床和转化研究中应用统计方法， 申请。我们的方法可以解决有关青少年脑认知发展的两个关键问题：1） 他们将确定重要的童年经历和社会环境因素，例如体育，视频 影响大脑发育的游戏，社交媒体，不健康的睡眠模式和吸烟； 2）了解 大脑发育对物质使用和模式的风险的推论，包括详细数量， 频率，管理途径和共用模式。呢 呢