Genetics of deep-learning-derived neuroimaging endophenotypes for Alzheimer's Disease

阿尔茨海默病深度学习神经影像内表型的遗传学

• 批准号: 10653800
• 负责人: MYRIAM FORNAGE
• 金额: $ 37.37万
• 依托单位: UNIVERSITY OF TEXAS HLTH SCI CTR HOUSTON
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-01 至 2026-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10653800
• 关键词: 3-Dimensional; Address; Administrative Supplement; Affect; Aging; Alzheimer' s Disease; American; Artificial Intelligence; Attention; Award; Brain; Caregivers; Data; Data Reporting; Dependence; Evaluation; Genes; Genetic; Genetic Databases; Genetic Processes; Genome; Goals; Heritability; Image; Image Analysis; Learning; Light; Literature; Magnetic Resonance Imaging; Maps; Methods; Modality; Neurodegenerative Disorders; Pain; Parents; Partner in relationship; Patients; Performance; Process; Research; Resolution; Scheme; Societies; Structure; base; brain magnetic resonance imaging; cost; deep learning; deep neural network; design; endophenotype; gene discovery; genetic information; genome wide association study; high dimensionality; imaging genetics; learning strategy; machine learning method; neuroimaging; novel; parent project

Project Summary/Abstract Alzheimer's disease (AD) is a severe neurodegenerative disease affecting aging Americans and generates dra- matic costs and pains on patients, caregivers, and the society. This administrative supplement proposes to develop new deep learning methods that integrate neuroimaging data with genetic information, thereby generating enriched gene-related data representations. There are at least three challenges to accomplish this research objective. Firstly, commonly used image encoders employ deep neural networks to extract high-level features for downstream tasks, but gene-related information can be contained in features at different levels and resolutions in deep neural networks. Secondly, using deep learning to process genetic data has been largely unexplored in literature. It is hard to design an effective encoder to tackle high-dimensional and discrete genetic data based on deep learning methods. Thirdly, there lacks a principled contrastive learning framework to learn from both imaging and genetic data for GWAS pur- poses. In this administrative supplement, we propose a novel trans-modality contrastive learning framework (TM-CL) to address these limitations and then faithfully accomplish our research goal. Our TM-CL contains novel and spe- cially designed imaging and genetic encoders to process brain MRI data and high-dimensional genetic data as well as a novel contrastive learning scheme to learn enriched gene-related information to benefit downstream tasks such as GWAS. Specifically, TM-CL contains a uniquely designed MRI encoder to integrate features at different scales and resolutions. In addition, our MRI encoder contains an attention-based multi-scale global transformation to extract global information from MRI data. Overall, gene-related information contained in MRI data can be largely captured in the representations. We also design a transformer-based genetic encoder for computing genetic representations. As genetic data is high-dimensional and discrete, it is hard to design deep learning based encoders to process such data. Our genetic encoder is proposed based on swin-transformer, where window attention and shifted window attention are designed to perform attention within splitting windows. By doing this, our genetic encoder can aggregate sufficient gene-related information, while largely reducing the computing cost. More importantly, when performing attention in our genetic encoder, the computed attention scores can capture three types of dependencies among different SNPs, As a result, the complicated genetic dependencies of the input genome data can be effectively captured. Finally, we propose a novel trans-modality contrastive learning scheme for integrating imaging data and genetics. Based on the proposed MRI and genetic encoders, we perform mutual information maximization between the MRI representation and genetic representation as the learning objective. Our contrastive framework is able to generate more informa- tive and discriminate gene-related representations, boosting the performance of downstream tasks such as GWAS. By faithfully accomplishing these research goals, we expect to facilitate the discovery of new genes relevant to AD, thereby shedding light on the causes and cures of AD.

项目总结/摘要 阿尔茨海默病（AD）是一种严重的神经退行性疾病，影响美国老年人，并产生dra- 对患者、护理人员和社会造成巨大的成本和痛苦。这份行政补充文件提出， 新的深度学习方法，将神经成像数据与遗传信息相结合，从而产生丰富的 基因相关的数据表示。要实现这一研究目标，至少有三个挑战。第一、 通常使用的图像编码器采用深度神经网络来提取用于下游任务的高级特征， 但是基因相关信息可以包含在深度神经网络中不同级别和分辨率的特征中。 其次，使用深度学习来处理遗传数据在文献中基本上没有被探索过。很难设计 一种有效的编码器，用于处理基于深度学习方法的高维和离散遗传数据。第三， 缺乏一个原则性的对比学习框架来从成像和遗传数据中学习GWAS pur， 摆姿势。本文提出了一个新的跨通道对比学习框架（TM-CL） 克服这些局限性，忠实地完成我们的研究目标。我们的TM-CL包含新颖和特殊的- 科学设计的成像和遗传编码器，用于处理大脑MRI数据和高维遗传数据 作为一种新的对比学习方案，可以学习丰富的基因相关信息，从而使下游任务受益， 作为GWAS。特别是，TM-CL包含一个独特设计的MRI编码器，可集成不同尺度的功能 和决议。此外，我们的MRI编码器包含一个基于注意力的多尺度全局变换， 来自MRI数据的全局信息。总体而言，MRI数据中包含的基因相关信息可以在很大程度上被捕获 in the representations申述.我们还设计了一个基于变换的遗传编码器计算遗传表示。作为 遗传数据是高维和离散的，很难设计基于深度学习的编码器来处理这样的数据。 我们的遗传编码器是基于swin变换器，其中窗口注意力和转移窗口注意力是 设计用于在分割窗口内执行注意力。通过这样做，我们的遗传编码器可以聚集足够的 基因相关信息，同时大大降低了计算成本。更重要的是，在执行注意力 在我们的遗传编码器中，计算的注意力分数可以捕获不同SNP之间的三种类型的依赖性， 结果，可以有效地捕获输入基因组数据的复杂遗传依赖性。最后我们 提出了一种新的跨模态对比学习方案，用于整合成像数据和遗传学。基于 提出的MRI和遗传编码器，我们执行MRI表示之间的互信息最大化 和遗传表征作为学习目标。我们的对比框架能够产生更多的信息- 积极和歧视基因相关的表示，提高下游任务，如GWAS的性能。 通过忠实地完成这些研究目标，我们期望促进发现与AD相关的新基因， 从而揭示AD的原因和治疗。