Statistical methods for structural and functional integration in multi-modal neuroimaging data

多模态神经影像数据结构和功能整合的统计方法

• 批准号: 10445053
• 负责人: BRIAN Scott CAFFO
• 金额: $ 48.44万
• 依托单位: JOHNS HOPKINS UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-05 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10445053
• 关键词: Adoption; Affect; Bayesian Method; Bayesian Modeling; Biological Markers; Brain; Clinical; Cognitive; Communities; Complex; Computer software; Data; Data Set; Detection; Diffusion; Diffusion Magnetic Resonance Imaging; Dimensions; Disease; Disease Outcome; Disease model; Dropout; Elements; Family member; Functional Magnetic Resonance Imaging; Goals; Impaired cognition; Individual; Infrastructure; Intuition; Joints; Knowledge; Learning; Magnetic Resonance Imaging; Measures; Medical; Meta-Analysis; Methodology; Methods; Modality; Modeling; Neurons; Neurosciences; Pathway Analysis; Patients; Pattern; Performance; Persons; Procedures; Process; Research; Rest; Route; Schizophrenia; Selection Criteria; Services; Severities; Signal Transduction; Specific qualifier value; Statistical Data Interpretation; Statistical Methods; Structure; Students; System; Techniques; Training; Weight; Work; application programming interface; autism spectrum disorder; base; behavioral outcome; behavioral phenotyping; biomarker discovery; cloud platform; cost; data framework; deep learning; deep neural network; density; developmental disease; direct application; feature extraction; flexibility; imaging modality; interest; model building; motor impairment; multimodal neuroimaging; multimodality; network models; neuroimaging; neuroimaging marker; neuropsychiatric disorder; non-invasive imaging; novel; patient variability; programs; relating to nervous system; socioeconomics; software development; theories; user-friendly

Abstract Neuropsychiatric disorders, such as autism and schizophrenia, affect millions of people worldwide and place a considerable burden on both patients and family members. Existing treatments for these disorders have limited efficacy, in part due the varied clinical manifestations, and to our narrow understanding of the impacted neural processes, particularly at the system (i.e., network) level. Two key elements of networks are the underlying infrastructure or physical connections between elements and the functional signaling between entities that rides on top of this infrastructure. Recent advancements in noninvasive imaging have given us the ability to quantify structural and functional relationships in the brain via diffusion MRI, resting-state functional MRI, respectively. The size and scope of datasets measuring network structure and function are increasing in neuroimaging, and other domains, which heightens the need for new statistical frameworks that make full use of the data. Our goal is to develop frameworks for the analysis of structure-function integration in large-scale and complex networks, applied to neuroimaging studies, but also broadly applicable. This proposal will introduce three analytic paradigms: Bayesian network modeling that uses a priori structure-function knowledge for simultaneous network anomaly detection and clinical severity prediction; density regression using optimal transport theory; and end-to-end prediction using deep neural networks. In our application, infrastructure will be measured via dMRI, while function will be measured rs-fMRI. Each of our frameworks will provide a unique means to integrate these distinct imaging modalities, while also respecting the unique information provided by each data type. We also propose a unique software development effort that creates an application program interface to core software and implementations as software as as a service hosted on cloud platforms.

摘要 神经精神障碍，如自闭症和精神分裂症，影响数百万人 这在世界范围内是一个巨大的问题，给患者和家庭成员带来了相当大的负担。现有 这些疾病的治疗效果有限，部分原因是不同的临床表现。 表现，以及我们对受影响的神经过程的狭隘理解，特别是 在系统（即，网络）级。网络的两个关键要素是 基础设施或元件之间的物理连接以及元件之间的功能信令 在这个基础设施之上的实体。无创成像的最新进展 让我们有能力量化大脑的结构和功能关系， 弥散磁共振成像，静息态功能磁共振成像。数据集的大小和范围 测量网络结构和功能在神经成像和其他领域中越来越多， 这就更加需要建立充分利用数据的新统计框架。 我们的目标是发展大规模结构-功能整合分析的框架， 和复杂网络，应用于神经影像学研究，但也广泛适用。这 一个提案将介绍三种分析范式：贝叶斯网络建模，使用先验 用于同时进行网络异常检测和临床严重性结构-功能知识 预测;密度回归使用最佳运输理论;和端到端预测使用 深层神经网络。在我们的应用程序中，基础设施将通过dMRI测量，而 功能将被测量rs-fMRI。我们的每个框架都将提供一种独特的方法， 整合这些不同的成像模式，同时也尊重独特的信息， 每个数据类型提供。我们还提出了一个独特的软件开发工作， 核心软件的应用程序接口和作为软件的实现， 服务托管在云平台上。