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

生物医学成像技术在过去几十年中经历了快速发展， 产生大量的多模态成像数据，这些数据作为衰老的生物标志物具有很大的前景相关疾病，如阿尔茨海默氏症。目前的成像生物标志物主要是基于特定的 提取的一维测量可能无法完全捕获成像数据的丰富性。利用 三维（3D）或更高的成像信息直接可以有助于识别更多的 有效的疾病生物标志物，为诊断、预后和治疗提供信息。然而，这也带来了 显著的挑战，如分析不规则形状的3D对象，管理高维和 高分辨率数据，解决噪声和复杂性，量化不确定性，并确保 结果的可解释性。我们的多机构，跨学科的调查团队将开发 有效的统计学习方法和可扩展的计算工具，以提取和评估生物标志物 从大规模的脑成像研究。我们还将把遗传和临床信息纳入 构建生物标志物。具体来说，我们的建议包括五个相互关联的研究目标进行 由来自三个机构的具有互补专业知识的调查人员进行调查。目标1侧重于开发 全基因组关联研究（GWAS）的可解释模型， 非视觉上下文信息。目标2的目标是开发新的非参数分布式学习 本发明涉及一种使用创新的区域分解策略来分析3D脑成像数据的方法， 提高计算性能。目标3量化了图像处理中的偏差效应，并发展了 推理方法，以揭示来自脑成像数据的潜在信号并识别重要的脑 不同诊断组之间的区域。目标4-5旨在开发统计方法， 评估用于疾病诊断和预后的成像调整的生物标志物， 影像学信息在诊断和预测准确性方面的价值高于遗传生物标志物。疗效 本项目中开发的方法将通过从阿尔茨海默氏症研究中收集的数据进行测试 疾病和脑科学拟议的研究将解决目前生物标志物的关键差距 开发和分析，利用先进的统计学习方法和计算工具， 直接利用3D或更高的成像信息。这种创新的方法有可能提供 更有效的疾病生物标志物，提高诊断、预后和治疗的准确性 阿尔茨海默氏症和相关痴呆症的治疗。

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.