Deep Learning with Neuroimaging Genetic Data for Alzheimer's Disease

总结 阿尔茨海默病 (AD) 影响全球超过 4400 万人，预计这一数字将增加两倍 到 2050 年。然而，目前还没有治愈 AD 的方法。该项目旨在开发和应用新的统计方法 方法，特别是深度学习，来推进 AD 的神经影像遗传学。它涉及新颖的方法论 目标 1-4 的进展，大规模英国生物银行神经影像遗传数据的成本效益应用 AD（目标 5）和软件开发（目标 6）。方法开发的所有四个目标都解决了新兴的重要问题 深度学习的重要主题及其在 AD 神经影像遗传学中的应用；尽管其他三个目标 处理独立的主题及其自己的其他广泛应用，它们反过来服务于目标 1：1) 目标 1 适用 手动搜索深度学习模型，以从神经图像中自动提取特征/表型，从而 随后全基因组关联研究 (GWAS) 的统计功效和生物学解释 预计将得到加强； 2) 目标 2 采用（自动）神经架构搜索 (NAS) 来更有效地 确定更好的深度学习模型，然后将其应用于目标 1 以增强特征提取/表型分析 从而增强 GWAS 的力量； 3) 目标 3 侧重于可解释的深度学习，提供生物学见解 通过本地化和突出显示深度学习模型提取的最重要的特征，这些特征可用于 目标1； 4) 目标 4 开发了一种新颖的深度学习推理理论，然后将其应用于严格测试 目标 1 中使用的任何选定/突出显示的特征的统计显着性。在目标 5 中，这些新方法将 应用于英国生物银行神经影像和 GWAS 数据，以确定新的遗传位点和神经影像特征 对于AD。作为副产品，我们将开发和分发实现目标 6 中提出的方法的软件。

Summary Alzheimer's disease (AD) affects over 44 million individuals worldwide, and the number is projected to triple by 2050. However, currently there is no cure for AD. This project aims to develop and apply novel statistical methods, especially deep learning, to advance neuroimaging genetics for AD. It involves novel methodological developments in Aims 1-4, cost-effective applications to the large-scale UK Biobank neuroimaging genetic data for AD (Aim 5), and software development (Aim 6). All four Aims for the methods development tackle emerging impor- tant topics in deep learning with their applications to neuroimaging genetics for AD; although the other three Aims deal with independent topics with their own other broad applications, they in turn serve for Aim 1: 1) Aim 1 applies manually searched deep learning models for automatic feature extraction/phenotyping from neuroimages, by which both the statistical power and biological interpretation of subsequent genome-wide association studies (GWAS) are expected to be enhanced; 2) Aim 2 employs (automatic) neural architecture search (NAS) to more efficiently identify better deep learning models, which are then applied to Aim 1 for enhancing feature extraction/phenotyping and thus boosting the power of GWAS; 3) Aim 3 focuses on explainable deep learning, offering biological insights by localizing and highlighting the most important features extracted by deep learning models that can be used for Aim 1; 4) Aim 4 develops a novel inferential theory for deep learning, which is then applied to rigorously test for the statistical significance of any selected/highlighted features used in Aim 1. In Aim 5, these new methods will be applied to the UK Biobank neuroimaging and GWAS data to identify novel genetic loci and neuroimaging features for AD. As a byproduct, we will develop and distribute software implementing the proposed methods in Aim 6.