SCH: Novel and Interpretable Statistical Learning for Brain Images in AD/ADRDs

SCH：针对 AD/ADRD 大脑图像的新颖且可解释的统计学习

• 批准号: 10816764
• 负责人: XIAO SONG
• 金额: $ 30万
• 依托单位: GEORGE MASON UNIVERSITY
• 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 2027-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10816764
• 关键词: 3-Dimensional; 4D Imaging; Address; Adopted; Aging; Algorithms; Alzheimer' s Disease; Alzheimer' s disease diagnosis; Alzheimer' s disease related dementia; Biological Markers; Brain; Brain imaging; Brain region; Clinical; Computer software; Data; Diagnosis; Disease; Effectiveness; Ensure; Foundations; Four-dimensional; Friends; Functional Imaging; Genetic; Genetic Markers; Goals; Health; Healthcare; Heterogeneity; Image; Imaging technology; Institution; Magnetic Resonance Imaging; Measures; Medical; Medical Research; Methods; Modeling; Modernization; Multimodal Imaging; Outcome; Performance; Phenotype; Positron-Emission Tomography; Prognosis; Public Health; Research; Research Personnel; Resolution; Sampling; Science; Shapes; Signal Transduction; Statistical Methods; Statistical Models; Study Subject; Technology; Testing; Three-Dimensional Imaging; Uncertainty; Variant; X-Ray Computed Tomography; biomarker development; biomarker discovery; biomedical imaging; computational platform; diagnostic accuracy; disease diagnosis; disease prognosis; flexibility; genome wide association study; high dimensionality; image processing; imaging biomarker; imaging study; improved; innovation; insight; interest; learning strategy; novel; parallel computer; rapid growth; sound; statistical learning; structural imaging; tool; two-dimensional

Biomedical imaging technology has undergone rapid advancements over the last several decades, producing large volumes of multimodal imaging data that hold great promise as biomarkers for agingrelated diseases such as Alzheimer’s. Current imaging biomarkers are primarily based on specific extracted one-dimensional measures that may not fully capture the richness of imaging data. Utilizing three-dimensional (3D) or higher imaging information directly may facilitate the identification of more effective disease biomarkers to inform diagnosis, prognosis, and treatment. However, this also brings significant challenges, such as analyzing ir-regularly shaped 3D objects, managing high-dimensional and high-resolution data, addressing noisiness and complexity, quantifying uncertainty, and ensuring the interpretability of the results. Our multi-institutional, inter-disciplinary team of investigators will develop efficient statistical learning approaches and scalable computing tools to extract and assess biomarkers from large-scale brain imaging studies. We will also incorporate genetic and clinical information in constructing the biomarkers. Specifically, our proposal comprises five interrelated research aims carried out by investigators with complementary expertise from three institutions. Aim 1 focuses on developing an interpretable model for genome-wide association studies (GWAS) with brain imaging pheno-types and non-visual contextual information. Aim 2 targets to develop novel nonparametric distributed learning methods for analyzing 3D brain imaging data using an innovative domain decomposition strategy to improve computing performance. Aim 3 quantifies the bias effect in image processing and develops inference methods to reveal the underlying signal from brain imaging data and identify significant brain regions among different diagnosis groups. Aims 4-5 aim to develop statistical methods for obtaining and evaluating imaging-adjusted biomarkers for disease diagnosis and prognosis and assess the incremental value of imaging information over genetic biomarkers on diagnosis and prediction accuracy. The efficacy of the methods developed in this pro-posal will be tested by data collected from studies in Alzheimer’s disease and brain sciences. The proposed research will address critical gaps in current biomarker development and analysis by utilizing advanced sta-tistical learning approaches and computing tools to directly utilize the 3D or higher imaging information. This innovative approach holds the potential to provide more effective disease biomarkers, leading to improved accuracy in diagnosis, prognosis, and treatment for Alzheimer’s disease and related dementias.

生物医学成像技术在过去几十年中取得了快速发展， 产生大量多模态成像数据，这些数据有望成为阿尔茨海默氏症等衰老相关疾病的生物标志物。 提取的一维测量可能无法完全捕获丰富的成像数据。 三维（3D）或更高的成像信息直接可以促进更多的识别 有效的疾病生物标志物可以为诊断、预后和治疗提供信息。然而，这也带来了影响。 重大挑战，例如分析不规则形状的 3D 对象、管理高维和 高分辨率数据，解决噪音和复杂性，量化不确定性，并确保 我们的多机构、跨学科研究团队将开发结果的可解释性。 用于提取和评估生物标志物的高效统计学习方法和可扩展计算工具 我们还将把遗传和临床信息纳入大规模脑成像研究中。 具体来说，我们的建议包括五个相互关联的研究目标。 由来自三个机构具有互补专业知识的研究人员制定，目标 1 侧重于开发一个 具有脑成像表型的全基因组关联研究（GWAS）的可解释模型和 目标 2 的目标是开发新颖的非参数分布式学习。 使用创新的域分解策略分析 3D 脑成像数据的方法 目标3量化图像处理中的偏差效应并进行开发。 推理方法揭示大脑成像数据中的潜在信号并识别重要的大脑 目标 4-5 旨在开发统计方法来获取和 评估用于疾病诊断和预后的成像调整生物标志物，并评估增量 成像信息相对于遗传生物标志物在诊断和预测准确性方面的价值。 本提案中开发的方法将通过阿尔茨海默氏症研究收集的数据进行测试 拟议的研究将解决当前生物标志物的关键差距。 利用先进的统计学习方法和计算工具进行开发和分析 直接利用 3D 或更高的成像信息这种创新方法具有提供的潜力。 更有效的疾病生物标志物，从而提高诊断、预后和治疗的准确性 用于阿尔茨海默病和相关痴呆症。