Genetics of deep-learning-derived neuroimaging endophenotypes for Alzheimer's Disease (Parent grant)

阿尔茨海默氏病深度学习衍生的神经影像内表型的遗传学（家长资助）

• 批准号: 10827718
• 负责人: MYRIAM FORNAGE
• 金额: $ 38.06万
• 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/10827718
• 关键词: Administrative Supplement; Affect; Alzheimer' s Disease; Alzheimer’s disease biomarker; American; Architecture; Area; Award; Benchmarking; Biology; Caregivers; Clinical; Clinical Trials; Collaborations; Communities; Computer software; Coupled; Data; Data Set; Dementia; Elderly; Functional disorder; Funding; Genetic; Genetic Markers; Genetic study; Goals; Grant; Graph; Healthcare; Heritability; Image; Impaired cognition; Investigation; Link; Machine Learning; Magnetic Resonance Imaging; Memory; Methods; Modeling; Outcome Measure; Parents; Patients; Phenotype; Prevention strategy; Process; Prognosis; Public Health; Reproducibility; Research; Resources; Software Tools; Standardization; Suggestion; Testing; Time; U-Series Cooperative Agreements; United States National Institutes of Health; Work; artificial intelligence algorithm; biobank; brain magnetic resonance imaging; clinical predictors; data standards; deep learning; disorder risk; endophenotype; genetic architecture; genetic association; genome wide association study; genomic locus; high dimensionality; human old age (65+); imaging genetics; improved; interest; learning strategy; multimodal neuroimaging; neural; neuroimaging; novel; outcome prediction; parent grant; programs; response; synergism; therapeutic development; trait; vector; whole genome; Administrative Supplement; Affect; Alzheimer' s Disease; Alzheimer’s disease biomarker; American; Architecture; Area; Award; Benchmarking; Biology; Caregivers; Clinical; Clinical Trials; Collaborations; Communities; Computer software; Coupled; Data; Data Set; Dementia; Elderly; Functional disorder; Funding; Genetic; Genetic Markers; Genetic study; Goals; Grant; Graph; Healthcare; Heritability; Image; Impaired cognition; Investigation; Link; Machine Learning; Magnetic Resonance Imaging; Memory; Methods; Modeling; Outcome Measure; Parents; Patients; Phenotype; Prevention strategy; Process; Prognosis; Public Health; Reproducibility; Research; Resources; Software Tools; Standardization; Suggestion; Testing; Time; U-Series Cooperative Agreements; United States National Institutes of Health; Work; artificial intelligence algorithm; biobank; brain magnetic resonance imaging; clinical predictors; data standards; deep learning; disorder risk; endophenotype; genetic architecture; genetic association; genome wide association study; genomic locus; high dimensionality; human old age (65+); imaging genetics; improved; interest; learning strategy; multimodal neuroimaging; neural; neuroimaging; novel; outcome prediction; parent grant; programs; response; synergism; therapeutic development; trait; vector; whole genome

Project Summary Alzheimer’s disease (AD) is characterized by the progressive impairment of cognitive and memory functions and is the most common form of dementia in the elderly. It affects 5.6 million Americans over the age of 65 and exacts tremendous and increasing demands on patients, caregivers, and healthcare resources, making this condition among the most significant public health problems of our time. Despite extensive studies, our understanding of the biology and pathophysiology of AD is still limited, hindering advances in the development of therapeutic and preventive strategies. Genetic studies of AD have successfully identified 40 novel loci but these explain only a fraction of the overall disease risk, suggesting opportunities for additional discoveries. Advanced neuroimaging is an essential part of current AD clinical and research investigations, which generally focus on relatively few imaging phenotypes developed by neuro- radiologists. However, there is a growing interest in exploiting the high-content information in large-scale, high dimensional multimodal neuroimaging data to identify novel AD biomarkers. Deep learning (DL) methods, an emerging area of machine learning research, uses raw images to derive optimal vector representations of imaging contents, which can be used as informative AD endophenotypes. The overall goal of the proposed supplement is to benchmark the AI algorithms we are developing on a standardized neuroimaging dataset. We will work on two topics: Predicting clinical decline (prognosis) from baseline T1-weighted brain MRI, and Discovery of genetic loci in whole- genome sequence data associated with brain MRI-derived endophenotypes. This is a collaboration with the other two U01 awards to improve the rigor and reproducibility. We will make the software tools and results publicly available. This will positively impact the larger research community.

项目摘要 阿尔茨海默氏病（AD）的特征是认知和记忆功能的进行性损害 这是痴呆症中最常见的形式。它影响了65岁以上的560万美国人， 对患者，护理人员和医疗保健资源的巨大和日益增长的需求使这一要求 条件是我们这个时代最重要的公共卫生问题。尽管进行了广泛的研究，我们 对AD的生物学和病理生理学的了解仍然有限，阻碍了发展的进步 治疗和预防策略。 AD的遗传研究成功鉴定了40个新的基因座，但 这些解释仅占整体疾病风险的一小部分，这表明有其他发现的机会。 高级神经影像学是当前AD临床和研究研究的重要组成部分，通常 专注于神经放射队开发的相对较少的成像表型。但是，有一个增长 有兴趣利用大尺寸，高维多模仿的高含量信息 数据以识别新型的AD生物标志物。深度学习（DL）方法，机器学习的新兴领域 研究，使用原始图像来得出成像内容的最佳矢量表示，可以用作 信息丰富的广告式型。提议的补充剂的总体目标是对AI进行基准测试 我们正在标准化的神经影像数据集上开发算法。我们将研究两个主题：预测 基线T1加权脑MRI的临床下降（预后），并发现全遗传局部 基因组序列数据与脑MRI衍生的内表型相关。这是与 其他两个U01奖励，以提高严格性和可重复性。我们将制作软件工具和结果 公开可用。这将对较大的研究界产生积极影响。