Developing an Individualized Deep Connectome Framework for ADRD Analysis

开发用于 ADRD 分析的个性化深度连接组框架

• 批准号: 10515550
• 负责人: Gang Li
• 金额: $ 168.66万
• 依托单位: UNIVERSITY OF TEXAS ARLINGTON
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-18 至 2025-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10515550
• 关键词: Alzheimer' s Disease; Alzheimer' s disease related dementia; Alzheimer’s disease biomarker; Americas; Anatomy; Architecture; Base of the Brain; Biological Markers; Brain; Brain Mapping; Clinical; Clinical assessments; Communities; Computing Methodologies; Data; Data Set; Dementia; Dementia with Lewy Bodies; Development; Diagnosis; Diffusion Magnetic Resonance Imaging; Family; Free Will; Functional Magnetic Resonance Imaging; Goals; Healthcare Systems; Heterogeneity; Hour; Human; Individual; Infrastructure; Learning; Lewy Body Dementia; Magnetic Resonance Imaging; Maps; Measures; Methods; Modality; Multimodal Imaging; Parkinson' s Dementia; Pathology; Patients; Population; Process; Public Health; Research; Shapes; Structure; Surface; Symptoms; System; Techniques; Time; Training; Work; base; biobank; clinical predictors; computerized tools; connectome; connectome data; cost; deep learning; deep learning model; diagnostic criteria; flexibility; fluorodeoxyglucose positron emission tomography; human old age (65+); individual patient; individual variation; innovation; interest; mental state; neural network; neuroimaging; neuroimaging marker; normal aging; response; single photon emission computed tomography; tool

As the most and the second most common type of dementia, AD and Lewy body dementias (LBD), including dementia with Lewy bodies and Parkinson’s disease dementia, account for 65% to 85% individuals with AD/ADRD. Misdiagnosis between AD and ADRD, e.g., AD vs. LBD, will lead to non-beneficial, incomplete, or even harmful treatment and management options. Comparing to diagnosis and prediction of AD from normal aging, differentiation between AD and LBD is very challenging, due to both mixed pathologies and clinical symptoms. Current MRI-based neuroimaging studies are limited to group-wise analysis between AD and LBD patients and controls, and there are significant challenges in dealing with the remarkable heterogeneity in AD/ADRD pathologies and clinical symptoms, and in pinpointing specific and subtle abnormalities across different individual AD/ADRD brains. In this project, we will significantly advance and integrate our powerful methods/tools and apply them to multiple AD/LBD datasets to discover and identify individualized connectome- scale differences between AD and LBD, by leveraging the cutting-edge deep learning techniques. Specifically, we will 1) discover, define and represent individual GyralNets to characterize brain connectome heterogeneity and AD/LBD related abnormalities for individual AD/LBD patient; 2) learn a cortical surface transformation to align GyralNets from population to individuals using unsupervised spherical networks and 3) develop a new infrastructure to integrate multiple types of connectome data including anatomical, structural and functional connectome, and characterize, represent and summarize their deep relationship as a “individual connectome signature” by maximizing its prediction capability between AD and LBD.

AD 和路易体痴呆 (LBD) 作为最常见和第二常见的痴呆类型，包括 路易体痴呆和帕金森病痴呆占 65% 至 85% 的患者 AD/ADRD 之间的误诊，例如 AD 与 LBD，将导致无益的、不完整的或 与正常的 AD 诊断和预测相比，甚至是有害的治疗和管理选择。 随着年龄的增长，由于混合的病理学和临床，AD 和 LBD 的区分非常具有挑战性。 目前基于 MRI 的神经影像学研究仅限于 AD 和 LBD 之间的分组分析。 患者和对照之间的差异，并且在处理显着的异质性方面存在重大挑战 AD/ADRD 病理学和临床症状，以及查明特定和微妙的异常 在这个项目中，我们将显着推进和整合我们强大的 AD/ADRD 大脑。 方法/工具并将其应用于多个 AD/LBD 数据集以发现和识别个性化连接组 通过利用尖端的深度学习技术来缩小 AD 和 LBD 之间的差异具体来说， 我们将 1) 发现、定义和表示个体 GyralNets 以表征大脑连接组异质性 以及个别 AD/LBD 患者的 AD/LBD 相关异常 2) 学习皮质表面转化 使用无监督的球形网络将 GyralNets 从群体到个体进行对齐，并且 3）开发一个新的 集成多种类型的连接组数据（包括解剖、结构和功能）的基础设施 连接组，并将它们的深层关系表征、表示和总结为“个体连接组” 通过最大化 AD 和 LBD 之间的预测能力来实现“签名”。