Early Alzheimers Forecasting from Multimodal Data via Deep Transfer Learning, Evaluated on a Large-Scale Prospective Cohort Study

通过深度迁移学习从多模式数据预测早期阿尔茨海默病，并在大规模前瞻性队列研究中进行评估

• 批准号: 10732306
• 负责人: Joyita Dutta
• 金额: $ 28.71万
• 依托单位: UNIVERSITY OF MASSACHUSETTS AMHERST
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10732306
• 关键词: Address; Affect; Alzheimer disease detection; Alzheimer disease screening; Alzheimer' s Disease; Alzheimer' s disease related dementia; Apolipoprotein E; Biological Markers; Biology; Brain; Brain Diseases; Brain imaging; Classification; Clinical; Clinical Trials; Cognitive; Cohort Studies; Controlled Study; Data; Data Collection; Data Set; Diagnosis; Early Diagnosis; Effectiveness; Engineering; Evolution; Exhibits; General Population; Genes; Health; Health Status; High Prevalence; Hippocampus; Hospitals; Hybrids; Image; Incidence; Knowledge; Learning; MRI Scans; Magnetic Resonance Imaging; Maps; Measurement; Measures; Methodology; Methods; Modality; Modeling; Monitor; Outcome; Palliative Care; Parietal Lobe; Patient-Focused Outcomes; Patients; Performance; Persons; Population; Populations at Risk; Positron-Emission Tomography; Prevention strategy; Preventive treatment; Prospective, cohort study; Proxy; Questionnaires; Research; Risk; Signal Transduction; Structure; Subjects Selections; Survival Analysis; Symptoms; Techniques; Testing; Time; Training; United States; Visit; Visual attention; Work; biobank; brain magnetic resonance imaging; cognitive testing; cohort; deep learning; demographics; diagnosis standard; early screening; entorhinal cortex; experimental study; falls; feature extraction; genetic information; human old age (65+); improved; innovation; learning strategy; mild cognitive impairment; multimodal data; multimodality; neural; neuroimaging; predictive modeling; prospective; screening; tool; transfer learning

Project Summary Alzheimer's Disease, a debilitating and degenerative brain disease that has no cure, affects ~5.8 million people in the United States. This project will develop techniques to train, adapt and transfer models for the early detection of Alzheimer’s disease from multimodal data, including genetic information, brain MRIs and cognitive tests, with a focus on screening for AD in the general population (i.e., evaluated on a cross-sectional, prospective cohort study, representative of the populations). We will introduce new techniques, based on deep transfer learning, to extract representations from brain MRIs, applicable to prospectively collected data which is unaccompanied by expert annotations. We will incorporate the feature extraction in an end-to-end predictive framework using multimodal deep learning. Such methods will be useful for modeling, monitoring, and forecasting the progression of Alzheimer's disease, where MRIs accompany the clinical information collected at different levels of granularity. We will start with a model that predicts the evolution of AD, trained on multimodal longitudinal data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study. Models trained on ADNI data typically rely on specialized engineered features from the brain MRIs requiring a considerable amount of domain knowledge and pre-processing and which would not be generally available if a patient were to obtain an MRI scan in the hospital. Thus, we train CNN-based models that work directly with brain MRIs, optimized to capture the predictive capabilities of the engineered features present in ADNI. We integrate the brain MRI network with a forecasting model that uses deep learning to extract abstract representations of the subjects' health status based on their multimodal information at a given point, including demographics, genetic information (e.g., the ApoE genes), cognitive test scores and brain MRIs. The method learns health status transitions, as well as how to map the health status abstraction to a diagnosis. An important innovation is the incorporation of an image extraction component in an end-to-end manner in the framework using hybrid convolutional layers, visual attention guided by domain knowledge and information theoretical measurements to extract different features from images. Moreover, we introduce methodology for the seamless transfer of the models between datasets collected as part of different studies, where the recorded information, including clinical tests, images collected and subject questionnaires, differs across study cohorts. The methods mitigate the challenges presented by this otherwise rich and varied data by using fused signals and mappings between abstractions. At the end of this study, we will have created a general forecasting framework, capable of predicting the onset of Alzheimer’s years before symptoms arise, a striking advance that will enable clinicians to identify new prevention strategies and prepare for, rather that respond to, Alzheimer’s.

项目概要 阿尔茨海默病是一种无法治愈的使人衰弱和退化的脑部疾病，影响约 580 万人 该项目将开发训练、调整和转移模型的技术。 从多模态数据（包括遗传信息、大脑信息）早期检测阿尔茨海默病 MRI 和认知测试，重点是在普通人群中筛查 AD（即根据 横断面、前瞻性队列研究，代表人群）。 我们将引入基于深度迁移学习的新技术，从大脑中提取表征 MRI，适用于前瞻性收集的数据，但没有专家注释。 使用多模态深度学习将特征提取合并到端到端预测框架中。 这些方法将有助于建模、监测和预测阿尔茨海默病的进展 疾病，其中 MRI 伴随着以不同粒度级别收集的临床信息。 将从预测 AD 演变的模型开始，该模型根据来自 阿尔茨海默病神经影像倡议 (ADNI) 研究的模型通常依赖于 ADNI 数据。 需要大量领域的大脑 MRI 的专门工程特征 知识和预处理，如果患者要获得 因此，我们训练基于 CNN 的模型，直接与大脑 MRI 配合使用， 我们进行了优化以捕获 ADNI 中存在的工程特征的预测能力。 具有预测模型的大脑 MRI 网络，该模型使用深度学习来提取抽象表示 根据给定点的多模态信息评估受试者的健康状况，包括 人口统计、遗传信息（例如 ApoE 基因）、认知测试分数和脑部 MRI。 方法学习健康状态转换，以及如何将健康状态抽象映射到诊断。 一项重要的创新是以端到端的方式合并图像提取组件 在使用混合卷积层的框架中，由领域知识引导的视觉注意力和 从图像中提取不同特征的信息理论测量。 此外，我们介绍了在收集的数据集之间无缝传输模型的方法 作为不同研究的一部分，记录的信息包括临床测试、收集的图像和 不同研究群体的主题问卷有所不同，这些方法减轻了由此带来的挑战。 通过使用融合信号和抽象之间的映射来获取丰富多样的数据。 在本研究结束时，我们将创建一个通用预测框架，能够预测 阿尔茨海默病在症状出现前数年就已发病，这一惊人的进步将使信徒能够 确定新的预防策略并为阿尔茨海默病做好准备，而不是应对阿尔茨海默病。