Identification of Multi-modal Imaging Biomarkers for Early Prediction of MCI-AD Conversion via Multigraph Representation

通过多图表示识别多模态成像生物标志物以早期预测 MCI-AD 转换

• 批准号: 10510971
• 负责人: Xiang Li
• 金额: $ 32.92万
• 依托单位: MASSACHUSETTS GENERAL HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-01 至 2024-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10510971
• 关键词: Alzheimer' s Disease; Alzheimer' s disease diagnosis; Alzheimer' s disease patient; Alzheimer’s disease biomarker; Back; Big Data; Biological; Biological Markers; Brain; Brain region; Clinical; Clinical Trials; Cognition; Cognitive; Data; Data Analyses; Data Analytics; Data Collection; Data Set; Databases; Dementia; Development; Diagnosis; Diagnostic Imaging; Diffusion Magnetic Resonance Imaging; Disease; Disease Progression; Early Diagnosis; Early identification; Elderly; Functional Magnetic Resonance Imaging; Goals; Graph; Image; Impaired cognition; Individual; Informatics; Intervention; Label; Lead; Learning; Literature; Magnetic Resonance Imaging; Maps; Memory; Methodology; Methods; Modality; Modeling; Multimodal Imaging; Network-based; Neurologic; Pathologic; Patients; Pattern; Performance; Physiological; Population; Positron-Emission Tomography; Progressive Disease; Reporting; Sample Size; Sampling; Scheme; Series; Site; Spatial Distribution; Surface; Techniques; Testing; Therapeutic Intervention; Time; Training; Validation; aging brain; algorithm development; base; cohort; convolutional neural network; deep learning; diagnostic accuracy; diagnostic value; early detection biomarkers; effectiveness evaluation; graph neural network; imaging biomarker; imaging modality; improved; learning strategy; machine learning method; mild cognitive impairment; mortality; multimodal neuroimaging; multimodality; neurodegenerative dementia; neuroimaging; novel; predictive modeling; risk stratification; symptom treatment; tool

Summary Alzheimer’s disease (AD) is the most common form of neurodegenerative dementia and has an astounding impact at individual and societal levels. As the early-stage cognitive degeneration, mild cognitive impairment (MCI) has a high chance to convert to AD. Effective and early prediction of such conversion is of great importance for risk stratification, patient management, and possible symptomatic treatments. Identification of an MCI-AD conversion end point is also important for clinical trials for better evaluating the effectiveness of therapeutic interventions. Recent studies have shown that multi-modalities neuroimaging can offer a more comprehensive characterization for the MCI-AD conversion, revealing the physiologic underpinning of the clinical states, and ultimately result in higher prediction accuracy based on the multi-modal imaging biomarker. Advancement in deep learning, especially deep Graph Convolutional Networks, has provided us with powerful tools in modeling the multi-modal neuroimaging data on the brain networks. However, despite the high prediction accuracy of AD in literature, multi- modal imaging diagnostic still lacks generalizability and robustness in dealing with data from other sites/populations due to the combined effect of relatively smaller sample sizes and potential bias in the sample labels. In this proposal, we will investigate the interaction among structural, functional, and proteinopathies networks in MCI and AD patients via a contrastive learning-based, multigraph representation framework on the multi-modal neuroimaging data of MRI, fMRI and PET modalities. The proposed framework will be used to identify and evaluate a multi-modal image biomarker for the AD conversion in MCI population from a multi-site dataset. By analyzing the spatial and populational patterns of the identified multi-modal image biomarker, we will be able to discover novel neuroscientific and biological mechanisms of the MCI-AD conversion.

概括 阿尔茨海默氏病 (AD) 是神经退行性痴呆的最常见形式，具有 由于早期认知退化，对个人和社会层面产生了惊人的影响。 轻度认知障碍（MCI）有很高的机会有效且早期转化为 AD。 预测这种转化对于风险分层、患者管理、 以及可能的对症治疗的确定。 对于临床试验以更好地评估治疗干预措施的有效性非常重要。 最近的研究表明，多模态神经影像学可以提供更全面的 MCI-AD 转换的表征，揭示了 MCI-AD 转换的生理基础 临床状态，最终基于多模态获得更高的预测精度 成像生物标记物的进展，特别是深度图卷积。 网络为我们提供了多模态神经影像数据建模的强大工具 然而，尽管文献中 AD 的预测精度很高，但多 模态成像诊断在处理数据时仍然缺乏普遍性和鲁棒性 由于样本量相对较小的综合影响，其他地点/人群 样本标签中的潜在偏差。 在本提案中，我们将研究结构、功能和功能之间的相互作用 通过基于对比学习的多图研究 MCI 和 AD 患者的蛋白质病网络 MRI、fMRI 和 PET 多模态神经影像数据的表示框架 所提出的框架将用于识别和评估多模态图像。 通过分析来自多站点数据集的 MCI 人群 AD 转换的生物标志物。 已识别的多模态图像生物标志物的空间和人口统计模式，我们将能够 发现 MCI-AD 转化的新神经科学和生物学机制。