Multivariate methods for identifying multitask/multimodal brain imaging biomarkers

项目总结/摘要 正如我们所知，大脑是极其复杂的，涉及功能信息之间复杂的相互作用， 与结构（但不是静态）衬底相互作用的信息。大脑成像技术提供了一种方法， 大脑的各个方面，尽管不完全，提供了丰富的多任务和多模式信息。的 该领域在处理多模态数据方面取得了显著进展，因为有更多的研究相关，例如， 功能和结构措施。然而，绝大多数研究仍然忽略了 两个或多个模式或任务。这些信息是至关重要的考虑，因为每一个脑成像模式的报告 大脑的不同方面（例如，灰质完整性、血流变化、白色物质完整性）。领域 仍在努力了解如何诊断和治疗复杂的精神疾病，如精神分裂症，躁郁症， 障碍，抑郁症和其他，忽视任务和模式之间的联合信息错过了一个关键的， 但又可用，这是难题的一部分组合多模态成像数据并不容易，因为除其他原因外， 由数千个体素或时间点组成的多个数据集的组合产生非常高的维度， 统计问题，需要适当的数据减少战略。在项目的前一阶段，我们开发了- 采用先进的方法来捕捉2个或更多模态之间的高维关系。我们的工作 继续大力支持多模式数据融合的好处，既提供了一个更完整的图片， 大脑的功能和结构，而且还提高我们的能力，研究和预测复杂的心理影响 病在这个项目的新阶段，我们将重点关注可以填补一些现有空白的方法，例如 连接空间/时间以及结构/功能连接尺度的能力。我们还提出了一个新的 框架整合单峰和多峰功能称为彩色融合，搜索组合， 在潜在（或字典）空间中占据独特位置的多模态“注释”。提议的冰毒- 将使用模拟、混合数据和大N标准成像数据对ODS进行确认。我们所提出的方法 将使用这个大型数据集进行彻底测试，其中包括具有重叠症状的多种疾病， 有时会被误诊，用错误的药物治疗数月或数年 （精神分裂症、双相情感障碍和单相抑郁症）。我们将提供开源工具并发布数据 在整个项目期间，通过GitHub和NITRIC存储库，从而使其他研究人员 将他们自己的方法与我们自己的方法进行比较，并将其应用于各种各样的大脑疾病。 37

Project Summary/Abstract The brain is extremely complex as we know, and involves a complicated interplay between functional infor- mation interacting with a structural (but not static) substrate. Brain imaging technology provides a way to sample various aspects of the brain albeit incompletely, providing a rich set of multitask and multimodal information. The field has advanced significantly in its approach to multimodal data, as there are more studies correlating, e.g. functional and structural measures. However, the vast majority of studies still ignore the joint information among two or more modalities or tasks. Such information is critical to consider as each brain imaging modality reports on a different aspect of the brain (e.g. gray matter integrity, blood flow changes, white matter integrity). The field is still striving to understand how to diagnose and treat complex mental illness, such as schizophrenia, bipolar disorder, depression, and others, and ignoring the joint information among tasks and modalities misses a critical, but available, part of the puzzle. Combining multimodal imaging data is not easy since, among other reasons, the combination of multiple data sets consisting of thousands of voxels or timepoints yields a very high dimen- sional problem, requiring appropriate data reduction strategies. In the previous phase of the project we devel- oped advanced approaches to capture high-dimensional relationships among 2 or more modalities. Our work continues to strongly support the benefits of multimodal data fusion to both provide a more complete picture of brain function and structure, but also to improve our ability to study and predict the impact of complex mental illness. In this new phase of the project, we will focus on methods that can fill some existing gaps, such as the ability to bridge spatial/temporal as well as structural/functional connectivity scales. We also propose a novel framework to integrate unimodal and multimodal features called chromatic fusion, which searches for combina- tions of multimodal `notes' which occupy a unique position in a latent (or dictionary) space. The proposed meth- ods will be validated using simulations, hybrid-data, and large N normative imaging data. Our proposed approach will be thoroughly tested using this large data set which includes multiple illnesses that have overlapping symp- toms and which can sometimes be misdiagnosed and treated with the wrong medications for months or years (schizophrenia, bipolar disorder, and unipolar depression). We will provide open source tools and release data throughout the duration of the project via GitHub and the NITRIC repository, hence enabling other investigators to compare their own methods with our own as well as to apply them to a large variety of brain disorders. 37