CRCNS: Multimodal Dynamic Causal Learning for Neuroimaging

CRCNS：神经影像多模式动态因果学习

• 批准号: 10396137
• 负责人: Sergey Plis
• 金额: $ 35.37万
• 依托单位: GEORGIA STATE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-08-05 至 2025-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10396137
• 关键词: Ache; Address; Adoption; Algorithms; Base of the Brain; Biological Markers; Brain; Brain Diseases; Brain imaging; Brain region; Cognitive; Communication; Communities; Computer software; Data; Data Collection; Data Set; Diagnostic; Diffusion Magnetic Resonance Imaging; Disease; Disease model; Electroencephalography; Environment; Functional Magnetic Resonance Imaging; Functional disorder; Goals; Individual; Knowledge; Lead; Learning; Link; Magnetic Resonance Imaging; Maps; Measurement; Measures; Mental disorders; Methods; Modality; Modeling; Names; Neurosciences; Output; Psyche structure; Research; Research Proposals; Sample Size; Sampling; Schizophrenia; Scientific Advances and Accomplishments; Scientist; Signal Transduction; Specific qualifier value; Speed; Structure; System; Techniques; Testing; Uncertainty; algorithmic methodologies; base; causal model; diverse data; dynamic system; experimental study; imaging modality; improved; insight; learning algorithm; learning strategy; machine learning method; member; multimodal data; multimodality; neural circuit; neuroimaging; novel; predictive tools; psychologic; relating to nervous system; success; theories; virtual

CRCNS Research Proposal: Collaborative Research: Multimodal Dynamic Causal Learning for Neuroimaging A Project Description A.1 Introduction Many analyses of fMRI and other neuroimaging data aim to discover the underlying causal or commu- nication structures that generated that activity.1,2 An accurate characterization of these brain structures is important for understanding neural circuits, systems-level neuroscience, and the neural bases of var- ious cognitive psychological phenomena or mental diseases. Brain structures learned from neuroimag- ing data also provide a powerful diagnostic tool for predicting everything from the concepts currently in one’s mind3–5 to whether one suffers from different mental diseases.6–10 Given the importance of such brain connectivity networks, it is unsurprising that a wide variety of learning algorithms have been developed for different neuroimaging modalities. In particular, many of these methods aim to infer the underlying causal or connectivity networks from data (in contrast with model comparison methods such as dynamic causal modeling (DCM)11). These network discovery methods have achieved some notable successes,2,6,12–21 but have also largely failed to address two issues that can impede our ability to achieve improved understanding of the full, working brain. Our project will develop, validate, and apply methods that solve both of these challenges. First, existing brain connectivity inference methods can be roughly divided into two groups: static me- thods that do not actually treat the brain as a dynamic system (e.g., IMaGES22 and most of the ap- proaches tested by Smith et al.23); and dynamic methods that explicitly measure and model the dy- namics of the brain. Static methods obviously fail to use all of the available information. In contrast, dynamic methods use the full structure of the measurements, but essentially all such methods24–28 infer causal and connectivity structures at the timescale of the measurement modality, rather than at the brain’s causal timescale. However, the networks learned from data at the measurement and brain timescales can be quite different, even given solutions for all of the other statistical and measurement problems facing neuroimaging analysis.29 Moreover, the important facts about causal or connectivity structure are frequently about which brain regions communicate directly with which other brain re- gions, which requires a focus on the brain timescale, not the measurement modality timescale. It is thus scientifically critical that we have methods that can determine the causal connections that exist at the timescale of the underlying neural systems, not just those that are found at the timescale of our particular neuroimaging methods. Second, there are multiple neuroimaging measurement modalities, each with their own strengths and weaknesses. There are obvious and widely recognized advantages of multimodal information fusion: 1) access to multiple, richer datasets, larger sample sizes, and improved estimation quality; 2) improved spatial coverage of the brain compared to fast dynamic modalities alone; 3) improved dynamic coverage of the range of signals that are informative about interactions of brain networks; and 4) enhanced estimation quality and reductions in modality-specific deficiencies due to complementary aspects of different modalities. These advantages are heavily exploited for feature and representation learning; our group has been highly active in this field.10,30–37 However, to our knowledge, no methods have been developed and validated that can learn causal information (effective connectivity) using data from multiple modalities. There exist machine learning methods (developed by members of our group) that can combine causal information from disparate datasets,38–41 but these methods have never been applied to multimodal neuroimaging data. Moreover, use of these methods to combine spatially precise (e.g. fMRI) and dynamically precise (e.g. EEG, MEG) modalities requires a theory of the differences in 1

CRCNS研究计划：协作研究：多模式 神经成像的动态因果学习 A项目说明 A.1简介 许多对功能磁共振成像和其他神经成像数据的分析旨在发现潜在的原因或联系。 产生这种活动的通信结构。1，2对这些大脑结构的准确描述 对于理解神经回路、系统级别的神经科学以及变量的神经基础是重要的。 借条认知心理现象或精神疾病。从神经成像学到的大脑结构- ING数据还提供了一个强大的诊断工具，用于预测当前 一个人是否患有不同的精神疾病3-5。 考虑到这种大脑连接网络的重要性，就不足为奇了，各种各样的 已经为不同的神经成像方式开发了学习算法。特别是，许多 这些方法旨在从数据中推断潜在的因果或连通性网络(与 模型比较方法，如动态因果建模(DCM)11)。这些网络发现 方法取得了一些显著的成功，2，6，12-21，但在很大程度上也未能解决两个问题 这些问题可能会阻碍我们更好地理解完整的、工作的大脑。我们的 Project将开发、验证和应用解决这两个挑战的方法。 首先，现有的大脑连通性推理方法大致可以分为两类：静态Me-Me。 实际上并不将大脑视为动态系统的方法(例如，IMAGES22和大多数AP- 由Smith等人测试的方法)；以及显式测量和建模Dy-Dy的动态方法。 大脑的运动学。静态方法显然无法使用所有可用的信息。相比之下， 动态方法使用测量的完整结构，但基本上所有此类方法24-28 在测量模式的时间尺度上推断因果和连通性结构，而不是在 大脑的因果时标。然而，这些网络从测量和大脑的数据中学习 时间尺度可以是完全不同的，即使给出了所有其他统计和测量的解决方案 神经成像分析面临的问题。29此外，关于因果关系或连通性的重要事实 结构通常是关于哪些大脑区域直接与哪些其他大脑区域联系。 Gions，这需要关注大脑的时间尺度，而不是测量方式的时间尺度。它是 因此，Sciencefi至关重要的是，我们有方法可以确定存在的因果联系 在基础神经系统的时间尺度上，而不仅仅是那些在我们的 特殊的神经成像方法。 其次，有多种神经成像测量方式，每一种都有自己的长处 和弱点。多模式信息具有明显且得到广泛认可的优势 融合：1)获得更多、更丰富的数据集、更大的样本量和更高的估计质量； 2)与快速动态模式相比，提高了大脑的空间覆盖率；3)改进了 动态覆盖关于大脑网络相互作用的信息的信号范围；以及 4)由于互补性，提高了估计质量并降低了通道-规格fic-fi相关性 不同模式的各个方面。这些优势被大量用于要素和制图表达 学习；我们的团队在这个fi领域非常活跃。10，30-37然而，据我们所知，没有方法 已经开发和验证，可以使用数据学习因果信息(有效连接) 来自多个医疗机构。存在机器学习方法(由我们小组的成员开发) 可以组合来自不同数据集的因果信息，38-41，但这些方法从未被 应用于多模式神经成像数据。此外，使用这些方法将空间精确度 (例如，功能磁共振成像)和动态精确(例如，脑电、脑磁图)模式需要一个关于 1